Downloads: 1
Diff of
/Regression RFS/RFSDevelopment.ipynb
[000000]
..
[624d49]
Switch to side-by-side view
--- a
+++ b/Regression RFS/RFSDevelopment.ipynb
@@ -0,0 +1,5003 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 32,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import numpy as np\n",
+ "import matplotlib.pyplot as plt\n",
+ "import warnings\n",
+ "warnings.filterwarnings('ignore')\n",
+ "import pandas as pd\n",
+ "import seaborn as sns\n",
+ "from sklearn.experimental import enable_iterative_imputer\n",
+ "from sklearn.impute import IterativeImputer\n",
+ "from sklearn.feature_selection import f_regression, mutual_info_regression\n",
+ "from sklearn.pipeline import make_pipeline\n",
+ "from sklearn.preprocessing import StandardScaler\n",
+ "from sklearn.model_selection import train_test_split, GridSearchCV\n",
+ "from sklearn.svm import SVR\n",
+ "from sklearn.linear_model import Lasso\n",
+ "from sklearn.ensemble import RandomForestRegressor\n",
+ "from sklearn.metrics import mean_absolute_error\n",
+ "from sklearn.model_selection import cross_val_score\n",
+ "from sklearn.feature_selection import RFE\n",
+ "from sklearn.model_selection import cross_val_score, GridSearchCV, train_test_split\n",
+ "from sklearn.preprocessing import StandardScaler, PolynomialFeatures\n",
+ "from sklearn.metrics import mean_absolute_error\n",
+ "\n",
+ "from scipy import stats\n",
+ "\n",
+ "\n",
+ "# Regression part for Breast Cancer dataset\n",
+ "pd.set_option('display.max_columns', None)\n",
+ "pd.set_option('display.max_info_columns', 500)\n",
+ "pd.set_option('display.max_seq_items', 500)\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Reading data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 33,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<class 'pandas.core.frame.DataFrame'>\n",
+ "RangeIndex: 400 entries, 0 to 399\n",
+ "Data columns (total 121 columns):\n",
+ " # Column Non-Null Count Dtype \n",
+ "--- ------ -------------- ----- \n",
+ " 0 ID 400 non-null object \n",
+ " 1 pCR (outcome) 400 non-null int64 \n",
+ " 2 RelapseFreeSurvival (outcome) 400 non-null float64\n",
+ " 3 Age 400 non-null float64\n",
+ " 4 ER 400 non-null int64 \n",
+ " 5 PgR 400 non-null int64 \n",
+ " 6 HER2 400 non-null int64 \n",
+ " 7 TrippleNegative 400 non-null int64 \n",
+ " 8 ChemoGrade 400 non-null int64 \n",
+ " 9 Proliferation 400 non-null int64 \n",
+ " 10 HistologyType 400 non-null int64 \n",
+ " 11 LNStatus 400 non-null int64 \n",
+ " 12 TumourStage 400 non-null int64 \n",
+ " 13 Gene 400 non-null int64 \n",
+ " 14 original_shape_Elongation 400 non-null float64\n",
+ " 15 original_shape_Flatness 400 non-null float64\n",
+ " 16 original_shape_LeastAxisLength 400 non-null float64\n",
+ " 17 original_shape_MajorAxisLength 400 non-null float64\n",
+ " 18 original_shape_Maximum2DDiameterColumn 400 non-null float64\n",
+ " 19 original_shape_Maximum2DDiameterRow 400 non-null float64\n",
+ " 20 original_shape_Maximum2DDiameterSlice 400 non-null float64\n",
+ " 21 original_shape_Maximum3DDiameter 400 non-null float64\n",
+ " 22 original_shape_MeshVolume 400 non-null float64\n",
+ " 23 original_shape_MinorAxisLength 400 non-null float64\n",
+ " 24 original_shape_Sphericity 400 non-null float64\n",
+ " 25 original_shape_SurfaceArea 400 non-null float64\n",
+ " 26 original_shape_SurfaceVolumeRatio 400 non-null float64\n",
+ " 27 original_shape_VoxelVolume 400 non-null int64 \n",
+ " 28 original_firstorder_10Percentile 400 non-null float64\n",
+ " 29 original_firstorder_90Percentile 400 non-null float64\n",
+ " 30 original_firstorder_Energy 400 non-null float64\n",
+ " 31 original_firstorder_Entropy 400 non-null float64\n",
+ " 32 original_firstorder_InterquartileRange 400 non-null float64\n",
+ " 33 original_firstorder_Kurtosis 400 non-null float64\n",
+ " 34 original_firstorder_Maximum 400 non-null float64\n",
+ " 35 original_firstorder_MeanAbsoluteDeviation 400 non-null float64\n",
+ " 36 original_firstorder_Mean 400 non-null float64\n",
+ " 37 original_firstorder_Median 400 non-null float64\n",
+ " 38 original_firstorder_Minimum 400 non-null float64\n",
+ " 39 original_firstorder_Range 400 non-null float64\n",
+ " 40 original_firstorder_RobustMeanAbsoluteDeviation 400 non-null float64\n",
+ " 41 original_firstorder_RootMeanSquared 400 non-null float64\n",
+ " 42 original_firstorder_Skewness 400 non-null float64\n",
+ " 43 original_firstorder_TotalEnergy 400 non-null float64\n",
+ " 44 original_firstorder_Uniformity 400 non-null float64\n",
+ " 45 original_firstorder_Variance 400 non-null float64\n",
+ " 46 original_glcm_Autocorrelation 400 non-null float64\n",
+ " 47 original_glcm_ClusterProminence 400 non-null float64\n",
+ " 48 original_glcm_ClusterShade 400 non-null float64\n",
+ " 49 original_glcm_ClusterTendency 400 non-null float64\n",
+ " 50 original_glcm_Contrast 400 non-null float64\n",
+ " 51 original_glcm_Correlation 400 non-null float64\n",
+ " 52 original_glcm_DifferenceAverage 400 non-null float64\n",
+ " 53 original_glcm_DifferenceEntropy 400 non-null float64\n",
+ " 54 original_glcm_DifferenceVariance 400 non-null float64\n",
+ " 55 original_glcm_Id 400 non-null float64\n",
+ " 56 original_glcm_Idm 400 non-null float64\n",
+ " 57 original_glcm_Idmn 400 non-null float64\n",
+ " 58 original_glcm_Idn 400 non-null float64\n",
+ " 59 original_glcm_Imc1 400 non-null float64\n",
+ " 60 original_glcm_Imc2 400 non-null float64\n",
+ " 61 original_glcm_InverseVariance 400 non-null float64\n",
+ " 62 original_glcm_JointAverage 400 non-null float64\n",
+ " 63 original_glcm_JointEnergy 400 non-null float64\n",
+ " 64 original_glcm_JointEntropy 400 non-null float64\n",
+ " 65 original_glcm_MCC 400 non-null float64\n",
+ " 66 original_glcm_MaximumProbability 400 non-null float64\n",
+ " 67 original_glcm_SumAverage 400 non-null float64\n",
+ " 68 original_glcm_SumEntropy 400 non-null float64\n",
+ " 69 original_glcm_SumSquares 400 non-null float64\n",
+ " 70 original_gldm_DependenceEntropy 400 non-null float64\n",
+ " 71 original_gldm_DependenceNonUniformity 400 non-null float64\n",
+ " 72 original_gldm_DependenceNonUniformityNormalized 400 non-null float64\n",
+ " 73 original_gldm_DependenceVariance 400 non-null float64\n",
+ " 74 original_gldm_GrayLevelNonUniformity 400 non-null float64\n",
+ " 75 original_gldm_GrayLevelVariance 400 non-null float64\n",
+ " 76 original_gldm_HighGrayLevelEmphasis 400 non-null float64\n",
+ " 77 original_gldm_LargeDependenceEmphasis 400 non-null float64\n",
+ " 78 original_gldm_LargeDependenceHighGrayLevelEmphasis 400 non-null float64\n",
+ " 79 original_gldm_LargeDependenceLowGrayLevelEmphasis 400 non-null float64\n",
+ " 80 original_gldm_LowGrayLevelEmphasis 400 non-null float64\n",
+ " 81 original_gldm_SmallDependenceEmphasis 400 non-null float64\n",
+ " 82 original_gldm_SmallDependenceHighGrayLevelEmphasis 400 non-null float64\n",
+ " 83 original_gldm_SmallDependenceLowGrayLevelEmphasis 400 non-null float64\n",
+ " 84 original_glrlm_GrayLevelNonUniformity 400 non-null float64\n",
+ " 85 original_glrlm_GrayLevelNonUniformityNormalized 400 non-null float64\n",
+ " 86 original_glrlm_GrayLevelVariance 400 non-null float64\n",
+ " 87 original_glrlm_HighGrayLevelRunEmphasis 400 non-null float64\n",
+ " 88 original_glrlm_LongRunEmphasis 400 non-null float64\n",
+ " 89 original_glrlm_LongRunHighGrayLevelEmphasis 400 non-null float64\n",
+ " 90 original_glrlm_LongRunLowGrayLevelEmphasis 400 non-null float64\n",
+ " 91 original_glrlm_LowGrayLevelRunEmphasis 400 non-null float64\n",
+ " 92 original_glrlm_RunEntropy 400 non-null float64\n",
+ " 93 original_glrlm_RunLengthNonUniformity 400 non-null float64\n",
+ " 94 original_glrlm_RunLengthNonUniformityNormalized 400 non-null float64\n",
+ " 95 original_glrlm_RunPercentage 400 non-null float64\n",
+ " 96 original_glrlm_RunVariance 400 non-null float64\n",
+ " 97 original_glrlm_ShortRunEmphasis 400 non-null float64\n",
+ " 98 original_glrlm_ShortRunHighGrayLevelEmphasis 400 non-null float64\n",
+ " 99 original_glrlm_ShortRunLowGrayLevelEmphasis 400 non-null float64\n",
+ " 100 original_glszm_GrayLevelNonUniformity 400 non-null float64\n",
+ " 101 original_glszm_GrayLevelNonUniformityNormalized 400 non-null float64\n",
+ " 102 original_glszm_GrayLevelVariance 400 non-null float64\n",
+ " 103 original_glszm_HighGrayLevelZoneEmphasis 400 non-null float64\n",
+ " 104 original_glszm_LargeAreaEmphasis 400 non-null float64\n",
+ " 105 original_glszm_LargeAreaHighGrayLevelEmphasis 400 non-null float64\n",
+ " 106 original_glszm_LargeAreaLowGrayLevelEmphasis 400 non-null float64\n",
+ " 107 original_glszm_LowGrayLevelZoneEmphasis 400 non-null float64\n",
+ " 108 original_glszm_SizeZoneNonUniformity 400 non-null float64\n",
+ " 109 original_glszm_SizeZoneNonUniformityNormalized 400 non-null float64\n",
+ " 110 original_glszm_SmallAreaEmphasis 400 non-null float64\n",
+ " 111 original_glszm_SmallAreaHighGrayLevelEmphasis 400 non-null float64\n",
+ " 112 original_glszm_SmallAreaLowGrayLevelEmphasis 400 non-null float64\n",
+ " 113 original_glszm_ZoneEntropy 400 non-null float64\n",
+ " 114 original_glszm_ZonePercentage 400 non-null float64\n",
+ " 115 original_glszm_ZoneVariance 400 non-null float64\n",
+ " 116 original_ngtdm_Busyness 400 non-null float64\n",
+ " 117 original_ngtdm_Coarseness 400 non-null float64\n",
+ " 118 original_ngtdm_Complexity 400 non-null float64\n",
+ " 119 original_ngtdm_Contrast 400 non-null float64\n",
+ " 120 original_ngtdm_Strength 400 non-null float64\n",
+ "dtypes: float64(108), int64(12), object(1)\n",
+ "memory usage: 378.3+ KB\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>pCR (outcome)</th>\n",
+ " <th>RelapseFreeSurvival (outcome)</th>\n",
+ " <th>Age</th>\n",
+ " <th>ER</th>\n",
+ " <th>PgR</th>\n",
+ " <th>HER2</th>\n",
+ " <th>TrippleNegative</th>\n",
+ " <th>ChemoGrade</th>\n",
+ " <th>Proliferation</th>\n",
+ " <th>HistologyType</th>\n",
+ " <th>LNStatus</th>\n",
+ " <th>TumourStage</th>\n",
+ " <th>Gene</th>\n",
+ " <th>original_shape_Elongation</th>\n",
+ " <th>original_shape_Flatness</th>\n",
+ " <th>original_shape_LeastAxisLength</th>\n",
+ " <th>original_shape_MajorAxisLength</th>\n",
+ " <th>original_shape_Maximum2DDiameterColumn</th>\n",
+ " <th>original_shape_Maximum2DDiameterRow</th>\n",
+ " <th>original_shape_Maximum2DDiameterSlice</th>\n",
+ " <th>original_shape_Maximum3DDiameter</th>\n",
+ " <th>original_shape_MeshVolume</th>\n",
+ " <th>original_shape_MinorAxisLength</th>\n",
+ " <th>original_shape_Sphericity</th>\n",
+ " <th>original_shape_SurfaceArea</th>\n",
+ " <th>original_shape_SurfaceVolumeRatio</th>\n",
+ " <th>original_shape_VoxelVolume</th>\n",
+ " <th>original_firstorder_10Percentile</th>\n",
+ " <th>original_firstorder_90Percentile</th>\n",
+ " <th>original_firstorder_Energy</th>\n",
+ " <th>original_firstorder_Entropy</th>\n",
+ " <th>original_firstorder_InterquartileRange</th>\n",
+ " <th>original_firstorder_Kurtosis</th>\n",
+ " <th>original_firstorder_Maximum</th>\n",
+ " <th>original_firstorder_MeanAbsoluteDeviation</th>\n",
+ " <th>original_firstorder_Mean</th>\n",
+ " <th>original_firstorder_Median</th>\n",
+ " <th>original_firstorder_Minimum</th>\n",
+ " <th>original_firstorder_Range</th>\n",
+ " <th>original_firstorder_RobustMeanAbsoluteDeviation</th>\n",
+ " <th>original_firstorder_RootMeanSquared</th>\n",
+ " <th>original_firstorder_Skewness</th>\n",
+ " <th>original_firstorder_TotalEnergy</th>\n",
+ " <th>original_firstorder_Uniformity</th>\n",
+ " <th>original_firstorder_Variance</th>\n",
+ " <th>original_glcm_Autocorrelation</th>\n",
+ " <th>original_glcm_ClusterProminence</th>\n",
+ " <th>original_glcm_ClusterShade</th>\n",
+ " <th>original_glcm_ClusterTendency</th>\n",
+ " <th>original_glcm_Contrast</th>\n",
+ " <th>original_glcm_Correlation</th>\n",
+ " <th>original_glcm_DifferenceAverage</th>\n",
+ " <th>original_glcm_DifferenceEntropy</th>\n",
+ " <th>original_glcm_DifferenceVariance</th>\n",
+ " <th>original_glcm_Id</th>\n",
+ " <th>original_glcm_Idm</th>\n",
+ " <th>original_glcm_Idmn</th>\n",
+ " <th>original_glcm_Idn</th>\n",
+ " <th>original_glcm_Imc1</th>\n",
+ " <th>original_glcm_Imc2</th>\n",
+ " <th>original_glcm_InverseVariance</th>\n",
+ " <th>original_glcm_JointAverage</th>\n",
+ " <th>original_glcm_JointEnergy</th>\n",
+ " <th>original_glcm_JointEntropy</th>\n",
+ " <th>original_glcm_MCC</th>\n",
+ " <th>original_glcm_MaximumProbability</th>\n",
+ " <th>original_glcm_SumAverage</th>\n",
+ " <th>original_glcm_SumEntropy</th>\n",
+ " <th>original_glcm_SumSquares</th>\n",
+ " <th>original_gldm_DependenceEntropy</th>\n",
+ " <th>original_gldm_DependenceNonUniformity</th>\n",
+ " <th>original_gldm_DependenceNonUniformityNormalized</th>\n",
+ " <th>original_gldm_DependenceVariance</th>\n",
+ " <th>original_gldm_GrayLevelNonUniformity</th>\n",
+ " <th>original_gldm_GrayLevelVariance</th>\n",
+ " <th>original_gldm_HighGrayLevelEmphasis</th>\n",
+ " <th>original_gldm_LargeDependenceEmphasis</th>\n",
+ " <th>original_gldm_LargeDependenceHighGrayLevelEmphasis</th>\n",
+ " <th>original_gldm_LargeDependenceLowGrayLevelEmphasis</th>\n",
+ " <th>original_gldm_LowGrayLevelEmphasis</th>\n",
+ " <th>original_gldm_SmallDependenceEmphasis</th>\n",
+ " <th>original_gldm_SmallDependenceHighGrayLevelEmphasis</th>\n",
+ " <th>original_gldm_SmallDependenceLowGrayLevelEmphasis</th>\n",
+ " <th>original_glrlm_GrayLevelNonUniformity</th>\n",
+ " <th>original_glrlm_GrayLevelNonUniformityNormalized</th>\n",
+ " <th>original_glrlm_GrayLevelVariance</th>\n",
+ " <th>original_glrlm_HighGrayLevelRunEmphasis</th>\n",
+ " <th>original_glrlm_LongRunEmphasis</th>\n",
+ " <th>original_glrlm_LongRunHighGrayLevelEmphasis</th>\n",
+ " <th>original_glrlm_LongRunLowGrayLevelEmphasis</th>\n",
+ " <th>original_glrlm_LowGrayLevelRunEmphasis</th>\n",
+ " <th>original_glrlm_RunEntropy</th>\n",
+ " <th>original_glrlm_RunLengthNonUniformity</th>\n",
+ " <th>original_glrlm_RunLengthNonUniformityNormalized</th>\n",
+ " <th>original_glrlm_RunPercentage</th>\n",
+ " <th>original_glrlm_RunVariance</th>\n",
+ " <th>original_glrlm_ShortRunEmphasis</th>\n",
+ " <th>original_glrlm_ShortRunHighGrayLevelEmphasis</th>\n",
+ " <th>original_glrlm_ShortRunLowGrayLevelEmphasis</th>\n",
+ " <th>original_glszm_GrayLevelNonUniformity</th>\n",
+ " <th>original_glszm_GrayLevelNonUniformityNormalized</th>\n",
+ " <th>original_glszm_GrayLevelVariance</th>\n",
+ " <th>original_glszm_HighGrayLevelZoneEmphasis</th>\n",
+ " <th>original_glszm_LargeAreaEmphasis</th>\n",
+ " <th>original_glszm_LargeAreaHighGrayLevelEmphasis</th>\n",
+ " <th>original_glszm_LargeAreaLowGrayLevelEmphasis</th>\n",
+ " <th>original_glszm_LowGrayLevelZoneEmphasis</th>\n",
+ " <th>original_glszm_SizeZoneNonUniformity</th>\n",
+ " <th>original_glszm_SizeZoneNonUniformityNormalized</th>\n",
+ " <th>original_glszm_SmallAreaEmphasis</th>\n",
+ " <th>original_glszm_SmallAreaHighGrayLevelEmphasis</th>\n",
+ " <th>original_glszm_SmallAreaLowGrayLevelEmphasis</th>\n",
+ " <th>original_glszm_ZoneEntropy</th>\n",
+ " <th>original_glszm_ZonePercentage</th>\n",
+ " <th>original_glszm_ZoneVariance</th>\n",
+ " <th>original_ngtdm_Busyness</th>\n",
+ " <th>original_ngtdm_Coarseness</th>\n",
+ " <th>original_ngtdm_Complexity</th>\n",
+ " <th>original_ngtdm_Contrast</th>\n",
+ " <th>original_ngtdm_Strength</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.00000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>4.000000e+02</td>\n",
+ " <td>4.000000e+02</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>4.000000e+02</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>4.000000e+02</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>4.000000e+02</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>4.000000e+02</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>4.000000e+02</td>\n",
+ " <td>4.000000e+02</td>\n",
+ " <td>4.000000e+02</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>4.000000e+02</td>\n",
+ " <td>4.000000e+02</td>\n",
+ " <td>4.000000e+02</td>\n",
+ " <td>4.000000e+02</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>4.000000e+02</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " <td>400.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>12.697500</td>\n",
+ " <td>56.000208</td>\n",
+ " <td>51.804674</td>\n",
+ " <td>0.547500</td>\n",
+ " <td>2.902500</td>\n",
+ " <td>2.797500</td>\n",
+ " <td>2.830000</td>\n",
+ " <td>9.875000</td>\n",
+ " <td>6.562500</td>\n",
+ " <td>8.63250</td>\n",
+ " <td>3.030000</td>\n",
+ " <td>2.607500</td>\n",
+ " <td>220.077500</td>\n",
+ " <td>0.716766</td>\n",
+ " <td>0.549817</td>\n",
+ " <td>23.072117</td>\n",
+ " <td>47.123568</td>\n",
+ " <td>47.975044</td>\n",
+ " <td>44.691151</td>\n",
+ " <td>47.519888</td>\n",
+ " <td>55.959049</td>\n",
+ " <td>20175.896562</td>\n",
+ " <td>31.331673</td>\n",
+ " <td>0.599114</td>\n",
+ " <td>7077.862397</td>\n",
+ " <td>0.394303</td>\n",
+ " <td>20286.662500</td>\n",
+ " <td>0.349420</td>\n",
+ " <td>2.553621</td>\n",
+ " <td>7.558204e+04</td>\n",
+ " <td>3.013113e-01</td>\n",
+ " <td>1.225883</td>\n",
+ " <td>2.810679</td>\n",
+ " <td>3.990295</td>\n",
+ " <td>0.692241</td>\n",
+ " <td>1.489130</td>\n",
+ " <td>1.529670</td>\n",
+ " <td>-1.047928</td>\n",
+ " <td>5.038224</td>\n",
+ " <td>0.506843</td>\n",
+ " <td>1.734983</td>\n",
+ " <td>-0.201434</td>\n",
+ " <td>7.558204e+04</td>\n",
+ " <td>0.886395</td>\n",
+ " <td>0.774701</td>\n",
+ " <td>3.715999</td>\n",
+ " <td>0.259496</td>\n",
+ " <td>-0.151342</td>\n",
+ " <td>0.127558</td>\n",
+ " <td>0.053479</td>\n",
+ " <td>0.325161</td>\n",
+ " <td>0.053479</td>\n",
+ " <td>2.698481e-01</td>\n",
+ " <td>0.048426</td>\n",
+ " <td>0.973261</td>\n",
+ " <td>0.973261</td>\n",
+ " <td>0.989304</td>\n",
+ " <td>0.982174</td>\n",
+ " <td>-0.140517</td>\n",
+ " <td>0.227191</td>\n",
+ " <td>0.053479</td>\n",
+ " <td>1.914246</td>\n",
+ " <td>0.861056</td>\n",
+ " <td>4.535711e-01</td>\n",
+ " <td>0.325201</td>\n",
+ " <td>0.922351</td>\n",
+ " <td>3.828492</td>\n",
+ " <td>4.000923e-01</td>\n",
+ " <td>0.045259</td>\n",
+ " <td>3.306906</td>\n",
+ " <td>5812.507878</td>\n",
+ " <td>0.243763</td>\n",
+ " <td>33.267788</td>\n",
+ " <td>18419.534984</td>\n",
+ " <td>0.056803</td>\n",
+ " <td>3.699739</td>\n",
+ " <td>541.950347</td>\n",
+ " <td>2085.262204</td>\n",
+ " <td>156.122383</td>\n",
+ " <td>0.325065</td>\n",
+ " <td>0.005497</td>\n",
+ " <td>0.011484</td>\n",
+ " <td>0.004000</td>\n",
+ " <td>2157.297056</td>\n",
+ " <td>0.694601</td>\n",
+ " <td>0.152700</td>\n",
+ " <td>3.190580</td>\n",
+ " <td>80.401079</td>\n",
+ " <td>310.756281</td>\n",
+ " <td>22.812278</td>\n",
+ " <td>0.452355</td>\n",
+ " <td>3.955578</td>\n",
+ " <td>340.638141</td>\n",
+ " <td>0.120189</td>\n",
+ " <td>0.172449</td>\n",
+ " <td>33.417605</td>\n",
+ " <td>0.278120</td>\n",
+ " <td>0.547245</td>\n",
+ " <td>0.210838</td>\n",
+ " <td>48.730722</td>\n",
+ " <td>0.874733</td>\n",
+ " <td>0.062633</td>\n",
+ " <td>1.260478</td>\n",
+ " <td>1.038107e+08</td>\n",
+ " <td>3.000160e+08</td>\n",
+ " <td>5.475941e+07</td>\n",
+ " <td>0.934880</td>\n",
+ " <td>10.672010</td>\n",
+ " <td>0.239151</td>\n",
+ " <td>3.920331e-01</td>\n",
+ " <td>3.957637e-01</td>\n",
+ " <td>3.911005e-01</td>\n",
+ " <td>2.722189e+00</td>\n",
+ " <td>0.003347</td>\n",
+ " <td>5.679717e+07</td>\n",
+ " <td>178.311246</td>\n",
+ " <td>32500.032620</td>\n",
+ " <td>0.056935</td>\n",
+ " <td>0.005965</td>\n",
+ " <td>0.029322</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>111.107417</td>\n",
+ " <td>27.137584</td>\n",
+ " <td>10.948522</td>\n",
+ " <td>0.498362</td>\n",
+ " <td>49.932114</td>\n",
+ " <td>49.937068</td>\n",
+ " <td>49.935558</td>\n",
+ " <td>86.092911</td>\n",
+ " <td>70.444284</td>\n",
+ " <td>86.20034</td>\n",
+ " <td>49.925801</td>\n",
+ " <td>0.897473</td>\n",
+ " <td>414.192346</td>\n",
+ " <td>0.164057</td>\n",
+ " <td>0.169573</td>\n",
+ " <td>9.948258</td>\n",
+ " <td>29.863864</td>\n",
+ " <td>24.136364</td>\n",
+ " <td>25.745205</td>\n",
+ " <td>27.378215</td>\n",
+ " <td>31.281043</td>\n",
+ " <td>34032.604046</td>\n",
+ " <td>14.929817</td>\n",
+ " <td>0.166765</td>\n",
+ " <td>13124.982232</td>\n",
+ " <td>0.124785</td>\n",
+ " <td>34116.955026</td>\n",
+ " <td>0.500398</td>\n",
+ " <td>0.720593</td>\n",
+ " <td>1.771190e+05</td>\n",
+ " <td>2.228900e-01</td>\n",
+ " <td>0.432459</td>\n",
+ " <td>0.794289</td>\n",
+ " <td>1.375773</td>\n",
+ " <td>0.214059</td>\n",
+ " <td>0.498683</td>\n",
+ " <td>0.490532</td>\n",
+ " <td>0.506797</td>\n",
+ " <td>1.435835</td>\n",
+ " <td>0.171557</td>\n",
+ " <td>0.480297</td>\n",
+ " <td>0.447253</td>\n",
+ " <td>1.771190e+05</td>\n",
+ " <td>0.100164</td>\n",
+ " <td>0.500969</td>\n",
+ " <td>0.548813</td>\n",
+ " <td>0.259498</td>\n",
+ " <td>0.153708</td>\n",
+ " <td>0.136369</td>\n",
+ " <td>0.045359</td>\n",
+ " <td>0.197784</td>\n",
+ " <td>0.045359</td>\n",
+ " <td>1.800264e-01</td>\n",
+ " <td>0.038106</td>\n",
+ " <td>0.022679</td>\n",
+ " <td>0.022679</td>\n",
+ " <td>0.009072</td>\n",
+ " <td>0.015120</td>\n",
+ " <td>0.103186</td>\n",
+ " <td>0.158959</td>\n",
+ " <td>0.045359</td>\n",
+ " <td>0.182253</td>\n",
+ " <td>0.123831</td>\n",
+ " <td>3.513830e-01</td>\n",
+ " <td>0.197970</td>\n",
+ " <td>0.076163</td>\n",
+ " <td>0.364506</td>\n",
+ " <td>3.079711e-01</td>\n",
+ " <td>0.044094</td>\n",
+ " <td>0.523883</td>\n",
+ " <td>10647.454674</td>\n",
+ " <td>0.095050</td>\n",
+ " <td>9.133694</td>\n",
+ " <td>33036.794878</td>\n",
+ " <td>0.050082</td>\n",
+ " <td>0.547861</td>\n",
+ " <td>51.098921</td>\n",
+ " <td>367.144828</td>\n",
+ " <td>76.371655</td>\n",
+ " <td>0.136965</td>\n",
+ " <td>0.002186</td>\n",
+ " <td>0.002953</td>\n",
+ " <td>0.002099</td>\n",
+ " <td>4168.813124</td>\n",
+ " <td>0.171297</td>\n",
+ " <td>0.085648</td>\n",
+ " <td>0.629373</td>\n",
+ " <td>48.801495</td>\n",
+ " <td>197.947990</td>\n",
+ " <td>16.930694</td>\n",
+ " <td>0.157343</td>\n",
+ " <td>0.406319</td>\n",
+ " <td>475.055615</td>\n",
+ " <td>0.043528</td>\n",
+ " <td>0.050184</td>\n",
+ " <td>22.730155</td>\n",
+ " <td>0.104823</td>\n",
+ " <td>0.137347</td>\n",
+ " <td>0.115990</td>\n",
+ " <td>69.761309</td>\n",
+ " <td>0.123567</td>\n",
+ " <td>0.061783</td>\n",
+ " <td>0.387635</td>\n",
+ " <td>1.048229e+09</td>\n",
+ " <td>3.174131e+09</td>\n",
+ " <td>7.352483e+08</td>\n",
+ " <td>0.096909</td>\n",
+ " <td>14.404000</td>\n",
+ " <td>0.132594</td>\n",
+ " <td>1.617334e-01</td>\n",
+ " <td>1.666319e-01</td>\n",
+ " <td>1.615922e-01</td>\n",
+ " <td>7.648849e-01</td>\n",
+ " <td>0.002419</td>\n",
+ " <td>7.063846e+08</td>\n",
+ " <td>1045.453432</td>\n",
+ " <td>177545.921568</td>\n",
+ " <td>0.047179</td>\n",
+ " <td>0.008379</td>\n",
+ " <td>0.115915</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>23.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>1.00000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.139299</td>\n",
+ " <td>0.099076</td>\n",
+ " <td>5.488466</td>\n",
+ " <td>12.466885</td>\n",
+ " <td>12.165525</td>\n",
+ " <td>13.038405</td>\n",
+ " <td>12.369317</td>\n",
+ " <td>15.524175</td>\n",
+ " <td>522.541667</td>\n",
+ " <td>9.197979</td>\n",
+ " <td>0.144064</td>\n",
+ " <td>438.477231</td>\n",
+ " <td>0.137183</td>\n",
+ " <td>539.000000</td>\n",
+ " <td>-1.717478</td>\n",
+ " <td>0.550056</td>\n",
+ " <td>9.187304e+02</td>\n",
+ " <td>-3.200000e-16</td>\n",
+ " <td>0.176432</td>\n",
+ " <td>1.703169</td>\n",
+ " <td>1.789861</td>\n",
+ " <td>0.278008</td>\n",
+ " <td>-0.495257</td>\n",
+ " <td>-0.782357</td>\n",
+ " <td>-3.489104</td>\n",
+ " <td>2.609159</td>\n",
+ " <td>0.174026</td>\n",
+ " <td>0.450734</td>\n",
+ " <td>-1.549694</td>\n",
+ " <td>9.187304e+02</td>\n",
+ " <td>0.560138</td>\n",
+ " <td>0.137128</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>-0.698575</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>-0.001169</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>-3.200000e-16</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.851249</td>\n",
+ " <td>0.851249</td>\n",
+ " <td>0.940500</td>\n",
+ " <td>0.900833</td>\n",
+ " <td>-0.704224</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.318974</td>\n",
+ " <td>-3.200000e-16</td>\n",
+ " <td>0.000011</td>\n",
+ " <td>0.462222</td>\n",
+ " <td>2.000000</td>\n",
+ " <td>-3.200000e-16</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>1.746059</td>\n",
+ " <td>26.291280</td>\n",
+ " <td>0.048778</td>\n",
+ " <td>15.274312</td>\n",
+ " <td>389.055659</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>271.103940</td>\n",
+ " <td>483.218378</td>\n",
+ " <td>90.322356</td>\n",
+ " <td>0.250008</td>\n",
+ " <td>0.001935</td>\n",
+ " <td>0.001969</td>\n",
+ " <td>0.000496</td>\n",
+ " <td>114.422115</td>\n",
+ " <td>0.500911</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>8.805742</td>\n",
+ " <td>17.663852</td>\n",
+ " <td>4.270105</td>\n",
+ " <td>0.250082</td>\n",
+ " <td>2.891378</td>\n",
+ " <td>28.080182</td>\n",
+ " <td>0.039053</td>\n",
+ " <td>0.067764</td>\n",
+ " <td>2.772991</td>\n",
+ " <td>0.065387</td>\n",
+ " <td>0.065387</td>\n",
+ " <td>0.018789</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.500000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>5.717762e+04</td>\n",
+ " <td>2.280370e+05</td>\n",
+ " <td>1.446278e+04</td>\n",
+ " <td>0.400000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.066991</td>\n",
+ " <td>7.050000e-11</td>\n",
+ " <td>7.050000e-11</td>\n",
+ " <td>7.050000e-11</td>\n",
+ " <td>-3.200000e-16</td>\n",
+ " <td>0.000008</td>\n",
+ " <td>0.000000e+00</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000248</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>38.000000</td>\n",
+ " <td>44.516769</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>2.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>1.00000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>2.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.614122</td>\n",
+ " <td>0.419926</td>\n",
+ " <td>16.262250</td>\n",
+ " <td>28.392261</td>\n",
+ " <td>31.144823</td>\n",
+ " <td>29.017098</td>\n",
+ " <td>30.083218</td>\n",
+ " <td>34.874576</td>\n",
+ " <td>5505.239584</td>\n",
+ " <td>20.903237</td>\n",
+ " <td>0.470205</td>\n",
+ " <td>2231.665958</td>\n",
+ " <td>0.308054</td>\n",
+ " <td>5569.250000</td>\n",
+ " <td>0.017428</td>\n",
+ " <td>2.074745</td>\n",
+ " <td>1.447680e+04</td>\n",
+ " <td>1.137992e-01</td>\n",
+ " <td>0.912450</td>\n",
+ " <td>2.331916</td>\n",
+ " <td>3.085950</td>\n",
+ " <td>0.534436</td>\n",
+ " <td>1.160005</td>\n",
+ " <td>1.213290</td>\n",
+ " <td>-1.350085</td>\n",
+ " <td>4.039714</td>\n",
+ " <td>0.380808</td>\n",
+ " <td>1.413895</td>\n",
+ " <td>-0.506042</td>\n",
+ " <td>1.447680e+04</td>\n",
+ " <td>0.826570</td>\n",
+ " <td>0.444353</td>\n",
+ " <td>3.719606</td>\n",
+ " <td>0.049899</td>\n",
+ " <td>-0.238660</td>\n",
+ " <td>0.025996</td>\n",
+ " <td>0.017185</td>\n",
+ " <td>0.201195</td>\n",
+ " <td>0.017185</td>\n",
+ " <td>1.250156e-01</td>\n",
+ " <td>0.016882</td>\n",
+ " <td>0.960104</td>\n",
+ " <td>0.960104</td>\n",
+ " <td>0.984041</td>\n",
+ " <td>0.973402</td>\n",
+ " <td>-0.170635</td>\n",
+ " <td>0.109379</td>\n",
+ " <td>0.017185</td>\n",
+ " <td>1.921287</td>\n",
+ " <td>0.792010</td>\n",
+ " <td>1.649499e-01</td>\n",
+ " <td>0.201212</td>\n",
+ " <td>0.887377</td>\n",
+ " <td>3.842575</td>\n",
+ " <td>1.470214e-01</td>\n",
+ " <td>0.010937</td>\n",
+ " <td>2.936179</td>\n",
+ " <td>1139.215458</td>\n",
+ " <td>0.172886</td>\n",
+ " <td>25.742684</td>\n",
+ " <td>4884.762486</td>\n",
+ " <td>0.015007</td>\n",
+ " <td>3.677587</td>\n",
+ " <td>513.414113</td>\n",
+ " <td>2007.247351</td>\n",
+ " <td>134.087546</td>\n",
+ " <td>0.264226</td>\n",
+ " <td>0.003773</td>\n",
+ " <td>0.009998</td>\n",
+ " <td>0.002418</td>\n",
+ " <td>671.804105</td>\n",
+ " <td>0.535692</td>\n",
+ " <td>0.079064</td>\n",
+ " <td>2.822364</td>\n",
+ " <td>47.025407</td>\n",
+ " <td>176.723255</td>\n",
+ " <td>12.721094</td>\n",
+ " <td>0.335310</td>\n",
+ " <td>3.704837</td>\n",
+ " <td>115.002731</td>\n",
+ " <td>0.085970</td>\n",
+ " <td>0.135429</td>\n",
+ " <td>18.058657</td>\n",
+ " <td>0.189805</td>\n",
+ " <td>0.477469</td>\n",
+ " <td>0.104734</td>\n",
+ " <td>9.181818</td>\n",
+ " <td>0.834711</td>\n",
+ " <td>0.018428</td>\n",
+ " <td>1.056342</td>\n",
+ " <td>1.311764e+06</td>\n",
+ " <td>5.031858e+06</td>\n",
+ " <td>3.567324e+05</td>\n",
+ " <td>0.931818</td>\n",
+ " <td>2.087413</td>\n",
+ " <td>0.160370</td>\n",
+ " <td>3.199015e-01</td>\n",
+ " <td>3.199017e-01</td>\n",
+ " <td>3.184398e-01</td>\n",
+ " <td>2.340783e+00</td>\n",
+ " <td>0.001389</td>\n",
+ " <td>1.030473e+06</td>\n",
+ " <td>18.760570</td>\n",
+ " <td>0.001826</td>\n",
+ " <td>0.018628</td>\n",
+ " <td>0.000310</td>\n",
+ " <td>0.001464</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>55.000000</td>\n",
+ " <td>51.019507</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>2.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>1.00000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>2.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.744712</td>\n",
+ " <td>0.550761</td>\n",
+ " <td>21.600941</td>\n",
+ " <td>39.244226</td>\n",
+ " <td>41.115528</td>\n",
+ " <td>38.373141</td>\n",
+ " <td>39.427143</td>\n",
+ " <td>47.644499</td>\n",
+ " <td>11989.520835</td>\n",
+ " <td>27.704988</td>\n",
+ " <td>0.611201</td>\n",
+ " <td>4007.332154</td>\n",
+ " <td>0.370412</td>\n",
+ " <td>12080.000000</td>\n",
+ " <td>0.321150</td>\n",
+ " <td>2.433500</td>\n",
+ " <td>3.361665e+04</td>\n",
+ " <td>2.736016e-01</td>\n",
+ " <td>1.167068</td>\n",
+ " <td>2.638978</td>\n",
+ " <td>3.738263</td>\n",
+ " <td>0.667524</td>\n",
+ " <td>1.404673</td>\n",
+ " <td>1.457954</td>\n",
+ " <td>-1.104206</td>\n",
+ " <td>4.763696</td>\n",
+ " <td>0.488671</td>\n",
+ " <td>1.641282</td>\n",
+ " <td>-0.205314</td>\n",
+ " <td>3.361665e+04</td>\n",
+ " <td>0.910380</td>\n",
+ " <td>0.660989</td>\n",
+ " <td>3.861755</td>\n",
+ " <td>0.174519</td>\n",
+ " <td>-0.110508</td>\n",
+ " <td>0.085468</td>\n",
+ " <td>0.044440</td>\n",
+ " <td>0.290378</td>\n",
+ " <td>0.044440</td>\n",
+ " <td>2.614990e-01</td>\n",
+ " <td>0.042419</td>\n",
+ " <td>0.977780</td>\n",
+ " <td>0.977780</td>\n",
+ " <td>0.991112</td>\n",
+ " <td>0.985187</td>\n",
+ " <td>-0.122807</td>\n",
+ " <td>0.203644</td>\n",
+ " <td>0.044440</td>\n",
+ " <td>1.962628</td>\n",
+ " <td>0.890470</td>\n",
+ " <td>4.025256e-01</td>\n",
+ " <td>0.291124</td>\n",
+ " <td>0.942980</td>\n",
+ " <td>3.925257</td>\n",
+ " <td>3.563955e-01</td>\n",
+ " <td>0.032970</td>\n",
+ " <td>3.300025</td>\n",
+ " <td>2733.962122</td>\n",
+ " <td>0.237305</td>\n",
+ " <td>32.911012</td>\n",
+ " <td>10513.130930</td>\n",
+ " <td>0.044810</td>\n",
+ " <td>3.841732</td>\n",
+ " <td>545.821152</td>\n",
+ " <td>2157.785843</td>\n",
+ " <td>142.045819</td>\n",
+ " <td>0.289567</td>\n",
+ " <td>0.005473</td>\n",
+ " <td>0.011393</td>\n",
+ " <td>0.003985</td>\n",
+ " <td>1208.131646</td>\n",
+ " <td>0.645412</td>\n",
+ " <td>0.177294</td>\n",
+ " <td>3.249865</td>\n",
+ " <td>66.868684</td>\n",
+ " <td>260.943909</td>\n",
+ " <td>18.143410</td>\n",
+ " <td>0.437534</td>\n",
+ " <td>3.949369</td>\n",
+ " <td>207.088943</td>\n",
+ " <td>0.113047</td>\n",
+ " <td>0.167160</td>\n",
+ " <td>27.838675</td>\n",
+ " <td>0.273416</td>\n",
+ " <td>0.555676</td>\n",
+ " <td>0.208185</td>\n",
+ " <td>24.076923</td>\n",
+ " <td>0.916824</td>\n",
+ " <td>0.041588</td>\n",
+ " <td>1.130435</td>\n",
+ " <td>3.760290e+06</td>\n",
+ " <td>1.446362e+07</td>\n",
+ " <td>9.685342e+05</td>\n",
+ " <td>0.967391</td>\n",
+ " <td>5.170909</td>\n",
+ " <td>0.208256</td>\n",
+ " <td>4.073021e-01</td>\n",
+ " <td>4.095627e-01</td>\n",
+ " <td>4.054695e-01</td>\n",
+ " <td>2.814884e+00</td>\n",
+ " <td>0.002944</td>\n",
+ " <td>3.277334e+06</td>\n",
+ " <td>67.929659</td>\n",
+ " <td>0.004383</td>\n",
+ " <td>0.047740</td>\n",
+ " <td>0.002330</td>\n",
+ " <td>0.003276</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>73.000000</td>\n",
+ " <td>60.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>3.000000</td>\n",
+ " <td>2.000000</td>\n",
+ " <td>1.00000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>3.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.840051</td>\n",
+ " <td>0.688378</td>\n",
+ " <td>27.723218</td>\n",
+ " <td>58.117748</td>\n",
+ " <td>59.407491</td>\n",
+ " <td>54.426544</td>\n",
+ " <td>58.753127</td>\n",
+ " <td>69.160947</td>\n",
+ " <td>23289.718750</td>\n",
+ " <td>38.054546</td>\n",
+ " <td>0.736629</td>\n",
+ " <td>7631.329455</td>\n",
+ " <td>0.459572</td>\n",
+ " <td>23473.500000</td>\n",
+ " <td>0.631555</td>\n",
+ " <td>2.852893</td>\n",
+ " <td>7.541352e+04</td>\n",
+ " <td>4.559082e-01</td>\n",
+ " <td>1.494012</td>\n",
+ " <td>3.035065</td>\n",
+ " <td>4.465178</td>\n",
+ " <td>0.819270</td>\n",
+ " <td>1.726168</td>\n",
+ " <td>1.764246</td>\n",
+ " <td>-0.770777</td>\n",
+ " <td>5.535964</td>\n",
+ " <td>0.611346</td>\n",
+ " <td>1.966944</td>\n",
+ " <td>0.039787</td>\n",
+ " <td>7.541352e+04</td>\n",
+ " <td>0.969985</td>\n",
+ " <td>0.982922</td>\n",
+ " <td>3.949659</td>\n",
+ " <td>0.402064</td>\n",
+ " <td>-0.032731</td>\n",
+ " <td>0.178206</td>\n",
+ " <td>0.079793</td>\n",
+ " <td>0.391504</td>\n",
+ " <td>0.079793</td>\n",
+ " <td>4.001249e-01</td>\n",
+ " <td>0.073295</td>\n",
+ " <td>0.991407</td>\n",
+ " <td>0.991407</td>\n",
+ " <td>0.996563</td>\n",
+ " <td>0.994272</td>\n",
+ " <td>-0.075312</td>\n",
+ " <td>0.320900</td>\n",
+ " <td>0.079793</td>\n",
+ " <td>1.986543</td>\n",
+ " <td>0.961267</td>\n",
+ " <td>6.799232e-01</td>\n",
+ " <td>0.391504</td>\n",
+ " <td>0.980355</td>\n",
+ " <td>3.973086</td>\n",
+ " <td>5.974409e-01</td>\n",
+ " <td>0.066728</td>\n",
+ " <td>3.641061</td>\n",
+ " <td>6814.045363</td>\n",
+ " <td>0.312826</td>\n",
+ " <td>40.010517</td>\n",
+ " <td>20866.900640</td>\n",
+ " <td>0.086715</td>\n",
+ " <td>3.943094</td>\n",
+ " <td>578.142544</td>\n",
+ " <td>2296.464498</td>\n",
+ " <td>149.927289</td>\n",
+ " <td>0.330603</td>\n",
+ " <td>0.006835</td>\n",
+ " <td>0.013148</td>\n",
+ " <td>0.005240</td>\n",
+ " <td>2288.530082</td>\n",
+ " <td>0.841872</td>\n",
+ " <td>0.232154</td>\n",
+ " <td>3.658762</td>\n",
+ " <td>103.354029</td>\n",
+ " <td>402.953448</td>\n",
+ " <td>28.606576</td>\n",
+ " <td>0.544409</td>\n",
+ " <td>4.227176</td>\n",
+ " <td>407.634309</td>\n",
+ " <td>0.147702</td>\n",
+ " <td>0.199018</td>\n",
+ " <td>43.591408</td>\n",
+ " <td>0.369707</td>\n",
+ " <td>0.627946</td>\n",
+ " <td>0.312460</td>\n",
+ " <td>61.054579</td>\n",
+ " <td>0.963144</td>\n",
+ " <td>0.082645</td>\n",
+ " <td>1.272727</td>\n",
+ " <td>1.012511e+07</td>\n",
+ " <td>3.861245e+07</td>\n",
+ " <td>2.688915e+06</td>\n",
+ " <td>0.985915</td>\n",
+ " <td>12.702912</td>\n",
+ " <td>0.277568</td>\n",
+ " <td>4.956921e-01</td>\n",
+ " <td>5.000049e-01</td>\n",
+ " <td>4.956920e-01</td>\n",
+ " <td>3.304411e+00</td>\n",
+ " <td>0.004798</td>\n",
+ " <td>9.079686e+06</td>\n",
+ " <td>157.370294</td>\n",
+ " <td>0.013769</td>\n",
+ " <td>0.085321</td>\n",
+ " <td>0.007962</td>\n",
+ " <td>0.009479</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>999.000000</td>\n",
+ " <td>144.000000</td>\n",
+ " <td>79.603012</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>999.000000</td>\n",
+ " <td>999.000000</td>\n",
+ " <td>999.000000</td>\n",
+ " <td>999.000000</td>\n",
+ " <td>999.000000</td>\n",
+ " <td>999.00000</td>\n",
+ " <td>999.000000</td>\n",
+ " <td>4.000000</td>\n",
+ " <td>999.000000</td>\n",
+ " <td>0.985424</td>\n",
+ " <td>0.872753</td>\n",
+ " <td>92.516207</td>\n",
+ " <td>326.866827</td>\n",
+ " <td>155.756220</td>\n",
+ " <td>241.530536</td>\n",
+ " <td>237.033753</td>\n",
+ " <td>242.614921</td>\n",
+ " <td>528765.458300</td>\n",
+ " <td>126.141700</td>\n",
+ " <td>0.888133</td>\n",
+ " <td>219501.845200</td>\n",
+ " <td>0.839124</td>\n",
+ " <td>529659.000000</td>\n",
+ " <td>2.118644</td>\n",
+ " <td>5.940469</td>\n",
+ " <td>2.928334e+06</td>\n",
+ " <td>9.114111e-01</td>\n",
+ " <td>3.078672</td>\n",
+ " <td>9.176538</td>\n",
+ " <td>11.180875</td>\n",
+ " <td>1.664640</td>\n",
+ " <td>3.414142</td>\n",
+ " <td>3.395508</td>\n",
+ " <td>0.969298</td>\n",
+ " <td>12.240681</td>\n",
+ " <td>1.253614</td>\n",
+ " <td>3.786760</td>\n",
+ " <td>2.515312</td>\n",
+ " <td>2.928334e+06</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>3.959871</td>\n",
+ " <td>3.999955</td>\n",
+ " <td>1.209880</td>\n",
+ " <td>0.633704</td>\n",
+ " <td>0.767273</td>\n",
+ " <td>0.297502</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.297502</td>\n",
+ " <td>8.669089e-01</td>\n",
+ " <td>0.205763</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.793518</td>\n",
+ " <td>0.297502</td>\n",
+ " <td>1.999989</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>1.815373e+00</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>3.999978</td>\n",
+ " <td>1.517871e+00</td>\n",
+ " <td>0.237631</td>\n",
+ " <td>4.929221</td>\n",
+ " <td>137989.523900</td>\n",
+ " <td>0.602150</td>\n",
+ " <td>58.513781</td>\n",
+ " <td>528500.270300</td>\n",
+ " <td>0.219931</td>\n",
+ " <td>3.999970</td>\n",
+ " <td>655.755882</td>\n",
+ " <td>2617.871609</td>\n",
+ " <td>608.902614</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.016475</td>\n",
+ " <td>0.023252</td>\n",
+ " <td>0.014780</td>\n",
+ " <td>71002.622480</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.249544</td>\n",
+ " <td>3.999673</td>\n",
+ " <td>461.989676</td>\n",
+ " <td>1845.719103</td>\n",
+ " <td>149.377763</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>5.651427</td>\n",
+ " <td>6957.420630</td>\n",
+ " <td>0.262586</td>\n",
+ " <td>0.423848</td>\n",
+ " <td>227.216258</td>\n",
+ " <td>0.498117</td>\n",
+ " <td>1.025800</td>\n",
+ " <td>0.457650</td>\n",
+ " <td>594.003356</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>0.250000</td>\n",
+ " <td>3.400000</td>\n",
+ " <td>1.467713e+10</td>\n",
+ " <td>5.870849e+10</td>\n",
+ " <td>1.419410e+10</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>117.476510</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>8.571429e-01</td>\n",
+ " <td>8.773779e-01</td>\n",
+ " <td>8.571429e-01</td>\n",
+ " <td>4.947427e+00</td>\n",
+ " <td>0.011301</td>\n",
+ " <td>1.390001e+10</td>\n",
+ " <td>20764.693790</td>\n",
+ " <td>1000000.000000</td>\n",
+ " <td>0.285100</td>\n",
+ " <td>0.060742</td>\n",
+ " <td>1.145601</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " pCR (outcome) RelapseFreeSurvival (outcome) Age ER \\\n",
+ "count 400.000000 400.000000 400.000000 400.000000 \n",
+ "mean 12.697500 56.000208 51.804674 0.547500 \n",
+ "std 111.107417 27.137584 10.948522 0.498362 \n",
+ "min 0.000000 0.000000 23.000000 0.000000 \n",
+ "25% 0.000000 38.000000 44.516769 0.000000 \n",
+ "50% 0.000000 55.000000 51.019507 1.000000 \n",
+ "75% 0.000000 73.000000 60.000000 1.000000 \n",
+ "max 999.000000 144.000000 79.603012 1.000000 \n",
+ "\n",
+ " PgR HER2 TrippleNegative ChemoGrade Proliferation \\\n",
+ "count 400.000000 400.000000 400.000000 400.000000 400.000000 \n",
+ "mean 2.902500 2.797500 2.830000 9.875000 6.562500 \n",
+ "std 49.932114 49.937068 49.935558 86.092911 70.444284 \n",
+ "min 0.000000 0.000000 0.000000 1.000000 1.000000 \n",
+ "25% 0.000000 0.000000 0.000000 2.000000 1.000000 \n",
+ "50% 0.000000 0.000000 0.000000 2.000000 1.000000 \n",
+ "75% 1.000000 1.000000 1.000000 3.000000 2.000000 \n",
+ "max 999.000000 999.000000 999.000000 999.000000 999.000000 \n",
+ "\n",
+ " HistologyType LNStatus TumourStage Gene \\\n",
+ "count 400.00000 400.000000 400.000000 400.000000 \n",
+ "mean 8.63250 3.030000 2.607500 220.077500 \n",
+ "std 86.20034 49.925801 0.897473 414.192346 \n",
+ "min 1.00000 0.000000 1.000000 0.000000 \n",
+ "25% 1.00000 0.000000 2.000000 0.000000 \n",
+ "50% 1.00000 1.000000 2.000000 1.000000 \n",
+ "75% 1.00000 1.000000 3.000000 1.000000 \n",
+ "max 999.00000 999.000000 4.000000 999.000000 \n",
+ "\n",
+ " original_shape_Elongation original_shape_Flatness \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 0.716766 0.549817 \n",
+ "std 0.164057 0.169573 \n",
+ "min 0.139299 0.099076 \n",
+ "25% 0.614122 0.419926 \n",
+ "50% 0.744712 0.550761 \n",
+ "75% 0.840051 0.688378 \n",
+ "max 0.985424 0.872753 \n",
+ "\n",
+ " original_shape_LeastAxisLength original_shape_MajorAxisLength \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 23.072117 47.123568 \n",
+ "std 9.948258 29.863864 \n",
+ "min 5.488466 12.466885 \n",
+ "25% 16.262250 28.392261 \n",
+ "50% 21.600941 39.244226 \n",
+ "75% 27.723218 58.117748 \n",
+ "max 92.516207 326.866827 \n",
+ "\n",
+ " original_shape_Maximum2DDiameterColumn \\\n",
+ "count 400.000000 \n",
+ "mean 47.975044 \n",
+ "std 24.136364 \n",
+ "min 12.165525 \n",
+ "25% 31.144823 \n",
+ "50% 41.115528 \n",
+ "75% 59.407491 \n",
+ "max 155.756220 \n",
+ "\n",
+ " original_shape_Maximum2DDiameterRow \\\n",
+ "count 400.000000 \n",
+ "mean 44.691151 \n",
+ "std 25.745205 \n",
+ "min 13.038405 \n",
+ "25% 29.017098 \n",
+ "50% 38.373141 \n",
+ "75% 54.426544 \n",
+ "max 241.530536 \n",
+ "\n",
+ " original_shape_Maximum2DDiameterSlice \\\n",
+ "count 400.000000 \n",
+ "mean 47.519888 \n",
+ "std 27.378215 \n",
+ "min 12.369317 \n",
+ "25% 30.083218 \n",
+ "50% 39.427143 \n",
+ "75% 58.753127 \n",
+ "max 237.033753 \n",
+ "\n",
+ " original_shape_Maximum3DDiameter original_shape_MeshVolume \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 55.959049 20175.896562 \n",
+ "std 31.281043 34032.604046 \n",
+ "min 15.524175 522.541667 \n",
+ "25% 34.874576 5505.239584 \n",
+ "50% 47.644499 11989.520835 \n",
+ "75% 69.160947 23289.718750 \n",
+ "max 242.614921 528765.458300 \n",
+ "\n",
+ " original_shape_MinorAxisLength original_shape_Sphericity \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 31.331673 0.599114 \n",
+ "std 14.929817 0.166765 \n",
+ "min 9.197979 0.144064 \n",
+ "25% 20.903237 0.470205 \n",
+ "50% 27.704988 0.611201 \n",
+ "75% 38.054546 0.736629 \n",
+ "max 126.141700 0.888133 \n",
+ "\n",
+ " original_shape_SurfaceArea original_shape_SurfaceVolumeRatio \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 7077.862397 0.394303 \n",
+ "std 13124.982232 0.124785 \n",
+ "min 438.477231 0.137183 \n",
+ "25% 2231.665958 0.308054 \n",
+ "50% 4007.332154 0.370412 \n",
+ "75% 7631.329455 0.459572 \n",
+ "max 219501.845200 0.839124 \n",
+ "\n",
+ " original_shape_VoxelVolume original_firstorder_10Percentile \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 20286.662500 0.349420 \n",
+ "std 34116.955026 0.500398 \n",
+ "min 539.000000 -1.717478 \n",
+ "25% 5569.250000 0.017428 \n",
+ "50% 12080.000000 0.321150 \n",
+ "75% 23473.500000 0.631555 \n",
+ "max 529659.000000 2.118644 \n",
+ "\n",
+ " original_firstorder_90Percentile original_firstorder_Energy \\\n",
+ "count 400.000000 4.000000e+02 \n",
+ "mean 2.553621 7.558204e+04 \n",
+ "std 0.720593 1.771190e+05 \n",
+ "min 0.550056 9.187304e+02 \n",
+ "25% 2.074745 1.447680e+04 \n",
+ "50% 2.433500 3.361665e+04 \n",
+ "75% 2.852893 7.541352e+04 \n",
+ "max 5.940469 2.928334e+06 \n",
+ "\n",
+ " original_firstorder_Entropy original_firstorder_InterquartileRange \\\n",
+ "count 4.000000e+02 400.000000 \n",
+ "mean 3.013113e-01 1.225883 \n",
+ "std 2.228900e-01 0.432459 \n",
+ "min -3.200000e-16 0.176432 \n",
+ "25% 1.137992e-01 0.912450 \n",
+ "50% 2.736016e-01 1.167068 \n",
+ "75% 4.559082e-01 1.494012 \n",
+ "max 9.114111e-01 3.078672 \n",
+ "\n",
+ " original_firstorder_Kurtosis original_firstorder_Maximum \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 2.810679 3.990295 \n",
+ "std 0.794289 1.375773 \n",
+ "min 1.703169 1.789861 \n",
+ "25% 2.331916 3.085950 \n",
+ "50% 2.638978 3.738263 \n",
+ "75% 3.035065 4.465178 \n",
+ "max 9.176538 11.180875 \n",
+ "\n",
+ " original_firstorder_MeanAbsoluteDeviation original_firstorder_Mean \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 0.692241 1.489130 \n",
+ "std 0.214059 0.498683 \n",
+ "min 0.278008 -0.495257 \n",
+ "25% 0.534436 1.160005 \n",
+ "50% 0.667524 1.404673 \n",
+ "75% 0.819270 1.726168 \n",
+ "max 1.664640 3.414142 \n",
+ "\n",
+ " original_firstorder_Median original_firstorder_Minimum \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 1.529670 -1.047928 \n",
+ "std 0.490532 0.506797 \n",
+ "min -0.782357 -3.489104 \n",
+ "25% 1.213290 -1.350085 \n",
+ "50% 1.457954 -1.104206 \n",
+ "75% 1.764246 -0.770777 \n",
+ "max 3.395508 0.969298 \n",
+ "\n",
+ " original_firstorder_Range \\\n",
+ "count 400.000000 \n",
+ "mean 5.038224 \n",
+ "std 1.435835 \n",
+ "min 2.609159 \n",
+ "25% 4.039714 \n",
+ "50% 4.763696 \n",
+ "75% 5.535964 \n",
+ "max 12.240681 \n",
+ "\n",
+ " original_firstorder_RobustMeanAbsoluteDeviation \\\n",
+ "count 400.000000 \n",
+ "mean 0.506843 \n",
+ "std 0.171557 \n",
+ "min 0.174026 \n",
+ "25% 0.380808 \n",
+ "50% 0.488671 \n",
+ "75% 0.611346 \n",
+ "max 1.253614 \n",
+ "\n",
+ " original_firstorder_RootMeanSquared original_firstorder_Skewness \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 1.734983 -0.201434 \n",
+ "std 0.480297 0.447253 \n",
+ "min 0.450734 -1.549694 \n",
+ "25% 1.413895 -0.506042 \n",
+ "50% 1.641282 -0.205314 \n",
+ "75% 1.966944 0.039787 \n",
+ "max 3.786760 2.515312 \n",
+ "\n",
+ " original_firstorder_TotalEnergy original_firstorder_Uniformity \\\n",
+ "count 4.000000e+02 400.000000 \n",
+ "mean 7.558204e+04 0.886395 \n",
+ "std 1.771190e+05 0.100164 \n",
+ "min 9.187304e+02 0.560138 \n",
+ "25% 1.447680e+04 0.826570 \n",
+ "50% 3.361665e+04 0.910380 \n",
+ "75% 7.541352e+04 0.969985 \n",
+ "max 2.928334e+06 1.000000 \n",
+ "\n",
+ " original_firstorder_Variance original_glcm_Autocorrelation \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 0.774701 3.715999 \n",
+ "std 0.500969 0.548813 \n",
+ "min 0.137128 1.000000 \n",
+ "25% 0.444353 3.719606 \n",
+ "50% 0.660989 3.861755 \n",
+ "75% 0.982922 3.949659 \n",
+ "max 3.959871 3.999955 \n",
+ "\n",
+ " original_glcm_ClusterProminence original_glcm_ClusterShade \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 0.259496 -0.151342 \n",
+ "std 0.259498 0.153708 \n",
+ "min 0.000000 -0.698575 \n",
+ "25% 0.049899 -0.238660 \n",
+ "50% 0.174519 -0.110508 \n",
+ "75% 0.402064 -0.032731 \n",
+ "max 1.209880 0.633704 \n",
+ "\n",
+ " original_glcm_ClusterTendency original_glcm_Contrast \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 0.127558 0.053479 \n",
+ "std 0.136369 0.045359 \n",
+ "min 0.000000 0.000000 \n",
+ "25% 0.025996 0.017185 \n",
+ "50% 0.085468 0.044440 \n",
+ "75% 0.178206 0.079793 \n",
+ "max 0.767273 0.297502 \n",
+ "\n",
+ " original_glcm_Correlation original_glcm_DifferenceAverage \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 0.325161 0.053479 \n",
+ "std 0.197784 0.045359 \n",
+ "min -0.001169 0.000000 \n",
+ "25% 0.201195 0.017185 \n",
+ "50% 0.290378 0.044440 \n",
+ "75% 0.391504 0.079793 \n",
+ "max 1.000000 0.297502 \n",
+ "\n",
+ " original_glcm_DifferenceEntropy original_glcm_DifferenceVariance \\\n",
+ "count 4.000000e+02 400.000000 \n",
+ "mean 2.698481e-01 0.048426 \n",
+ "std 1.800264e-01 0.038106 \n",
+ "min -3.200000e-16 0.000000 \n",
+ "25% 1.250156e-01 0.016882 \n",
+ "50% 2.614990e-01 0.042419 \n",
+ "75% 4.001249e-01 0.073295 \n",
+ "max 8.669089e-01 0.205763 \n",
+ "\n",
+ " original_glcm_Id original_glcm_Idm original_glcm_Idmn \\\n",
+ "count 400.000000 400.000000 400.000000 \n",
+ "mean 0.973261 0.973261 0.989304 \n",
+ "std 0.022679 0.022679 0.009072 \n",
+ "min 0.851249 0.851249 0.940500 \n",
+ "25% 0.960104 0.960104 0.984041 \n",
+ "50% 0.977780 0.977780 0.991112 \n",
+ "75% 0.991407 0.991407 0.996563 \n",
+ "max 1.000000 1.000000 1.000000 \n",
+ "\n",
+ " original_glcm_Idn original_glcm_Imc1 original_glcm_Imc2 \\\n",
+ "count 400.000000 400.000000 400.000000 \n",
+ "mean 0.982174 -0.140517 0.227191 \n",
+ "std 0.015120 0.103186 0.158959 \n",
+ "min 0.900833 -0.704224 0.000000 \n",
+ "25% 0.973402 -0.170635 0.109379 \n",
+ "50% 0.985187 -0.122807 0.203644 \n",
+ "75% 0.994272 -0.075312 0.320900 \n",
+ "max 1.000000 0.000000 0.793518 \n",
+ "\n",
+ " original_glcm_InverseVariance original_glcm_JointAverage \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 0.053479 1.914246 \n",
+ "std 0.045359 0.182253 \n",
+ "min 0.000000 1.000000 \n",
+ "25% 0.017185 1.921287 \n",
+ "50% 0.044440 1.962628 \n",
+ "75% 0.079793 1.986543 \n",
+ "max 0.297502 1.999989 \n",
+ "\n",
+ " original_glcm_JointEnergy original_glcm_JointEntropy \\\n",
+ "count 400.000000 4.000000e+02 \n",
+ "mean 0.861056 4.535711e-01 \n",
+ "std 0.123831 3.513830e-01 \n",
+ "min 0.318974 -3.200000e-16 \n",
+ "25% 0.792010 1.649499e-01 \n",
+ "50% 0.890470 4.025256e-01 \n",
+ "75% 0.961267 6.799232e-01 \n",
+ "max 1.000000 1.815373e+00 \n",
+ "\n",
+ " original_glcm_MCC original_glcm_MaximumProbability \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 0.325201 0.922351 \n",
+ "std 0.197970 0.076163 \n",
+ "min 0.000011 0.462222 \n",
+ "25% 0.201212 0.887377 \n",
+ "50% 0.291124 0.942980 \n",
+ "75% 0.391504 0.980355 \n",
+ "max 1.000000 1.000000 \n",
+ "\n",
+ " original_glcm_SumAverage original_glcm_SumEntropy \\\n",
+ "count 400.000000 4.000000e+02 \n",
+ "mean 3.828492 4.000923e-01 \n",
+ "std 0.364506 3.079711e-01 \n",
+ "min 2.000000 -3.200000e-16 \n",
+ "25% 3.842575 1.470214e-01 \n",
+ "50% 3.925257 3.563955e-01 \n",
+ "75% 3.973086 5.974409e-01 \n",
+ "max 3.999978 1.517871e+00 \n",
+ "\n",
+ " original_glcm_SumSquares original_gldm_DependenceEntropy \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 0.045259 3.306906 \n",
+ "std 0.044094 0.523883 \n",
+ "min 0.000000 1.746059 \n",
+ "25% 0.010937 2.936179 \n",
+ "50% 0.032970 3.300025 \n",
+ "75% 0.066728 3.641061 \n",
+ "max 0.237631 4.929221 \n",
+ "\n",
+ " original_gldm_DependenceNonUniformity \\\n",
+ "count 400.000000 \n",
+ "mean 5812.507878 \n",
+ "std 10647.454674 \n",
+ "min 26.291280 \n",
+ "25% 1139.215458 \n",
+ "50% 2733.962122 \n",
+ "75% 6814.045363 \n",
+ "max 137989.523900 \n",
+ "\n",
+ " original_gldm_DependenceNonUniformityNormalized \\\n",
+ "count 400.000000 \n",
+ "mean 0.243763 \n",
+ "std 0.095050 \n",
+ "min 0.048778 \n",
+ "25% 0.172886 \n",
+ "50% 0.237305 \n",
+ "75% 0.312826 \n",
+ "max 0.602150 \n",
+ "\n",
+ " original_gldm_DependenceVariance original_gldm_GrayLevelNonUniformity \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 33.267788 18419.534984 \n",
+ "std 9.133694 33036.794878 \n",
+ "min 15.274312 389.055659 \n",
+ "25% 25.742684 4884.762486 \n",
+ "50% 32.911012 10513.130930 \n",
+ "75% 40.010517 20866.900640 \n",
+ "max 58.513781 528500.270300 \n",
+ "\n",
+ " original_gldm_GrayLevelVariance original_gldm_HighGrayLevelEmphasis \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 0.056803 3.699739 \n",
+ "std 0.050082 0.547861 \n",
+ "min 0.000000 1.000000 \n",
+ "25% 0.015007 3.677587 \n",
+ "50% 0.044810 3.841732 \n",
+ "75% 0.086715 3.943094 \n",
+ "max 0.219931 3.999970 \n",
+ "\n",
+ " original_gldm_LargeDependenceEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 541.950347 \n",
+ "std 51.098921 \n",
+ "min 271.103940 \n",
+ "25% 513.414113 \n",
+ "50% 545.821152 \n",
+ "75% 578.142544 \n",
+ "max 655.755882 \n",
+ "\n",
+ " original_gldm_LargeDependenceHighGrayLevelEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 2085.262204 \n",
+ "std 367.144828 \n",
+ "min 483.218378 \n",
+ "25% 2007.247351 \n",
+ "50% 2157.785843 \n",
+ "75% 2296.464498 \n",
+ "max 2617.871609 \n",
+ "\n",
+ " original_gldm_LargeDependenceLowGrayLevelEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 156.122383 \n",
+ "std 76.371655 \n",
+ "min 90.322356 \n",
+ "25% 134.087546 \n",
+ "50% 142.045819 \n",
+ "75% 149.927289 \n",
+ "max 608.902614 \n",
+ "\n",
+ " original_gldm_LowGrayLevelEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 0.325065 \n",
+ "std 0.136965 \n",
+ "min 0.250008 \n",
+ "25% 0.264226 \n",
+ "50% 0.289567 \n",
+ "75% 0.330603 \n",
+ "max 1.000000 \n",
+ "\n",
+ " original_gldm_SmallDependenceEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 0.005497 \n",
+ "std 0.002186 \n",
+ "min 0.001935 \n",
+ "25% 0.003773 \n",
+ "50% 0.005473 \n",
+ "75% 0.006835 \n",
+ "max 0.016475 \n",
+ "\n",
+ " original_gldm_SmallDependenceHighGrayLevelEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 0.011484 \n",
+ "std 0.002953 \n",
+ "min 0.001969 \n",
+ "25% 0.009998 \n",
+ "50% 0.011393 \n",
+ "75% 0.013148 \n",
+ "max 0.023252 \n",
+ "\n",
+ " original_gldm_SmallDependenceLowGrayLevelEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 0.004000 \n",
+ "std 0.002099 \n",
+ "min 0.000496 \n",
+ "25% 0.002418 \n",
+ "50% 0.003985 \n",
+ "75% 0.005240 \n",
+ "max 0.014780 \n",
+ "\n",
+ " original_glrlm_GrayLevelNonUniformity \\\n",
+ "count 400.000000 \n",
+ "mean 2157.297056 \n",
+ "std 4168.813124 \n",
+ "min 114.422115 \n",
+ "25% 671.804105 \n",
+ "50% 1208.131646 \n",
+ "75% 2288.530082 \n",
+ "max 71002.622480 \n",
+ "\n",
+ " original_glrlm_GrayLevelNonUniformityNormalized \\\n",
+ "count 400.000000 \n",
+ "mean 0.694601 \n",
+ "std 0.171297 \n",
+ "min 0.500911 \n",
+ "25% 0.535692 \n",
+ "50% 0.645412 \n",
+ "75% 0.841872 \n",
+ "max 1.000000 \n",
+ "\n",
+ " original_glrlm_GrayLevelVariance \\\n",
+ "count 400.000000 \n",
+ "mean 0.152700 \n",
+ "std 0.085648 \n",
+ "min 0.000000 \n",
+ "25% 0.079064 \n",
+ "50% 0.177294 \n",
+ "75% 0.232154 \n",
+ "max 0.249544 \n",
+ "\n",
+ " original_glrlm_HighGrayLevelRunEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 3.190580 \n",
+ "std 0.629373 \n",
+ "min 1.000000 \n",
+ "25% 2.822364 \n",
+ "50% 3.249865 \n",
+ "75% 3.658762 \n",
+ "max 3.999673 \n",
+ "\n",
+ " original_glrlm_LongRunEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 80.401079 \n",
+ "std 48.801495 \n",
+ "min 8.805742 \n",
+ "25% 47.025407 \n",
+ "50% 66.868684 \n",
+ "75% 103.354029 \n",
+ "max 461.989676 \n",
+ "\n",
+ " original_glrlm_LongRunHighGrayLevelEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 310.756281 \n",
+ "std 197.947990 \n",
+ "min 17.663852 \n",
+ "25% 176.723255 \n",
+ "50% 260.943909 \n",
+ "75% 402.953448 \n",
+ "max 1845.719103 \n",
+ "\n",
+ " original_glrlm_LongRunLowGrayLevelEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 22.812278 \n",
+ "std 16.930694 \n",
+ "min 4.270105 \n",
+ "25% 12.721094 \n",
+ "50% 18.143410 \n",
+ "75% 28.606576 \n",
+ "max 149.377763 \n",
+ "\n",
+ " original_glrlm_LowGrayLevelRunEmphasis original_glrlm_RunEntropy \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 0.452355 3.955578 \n",
+ "std 0.157343 0.406319 \n",
+ "min 0.250082 2.891378 \n",
+ "25% 0.335310 3.704837 \n",
+ "50% 0.437534 3.949369 \n",
+ "75% 0.544409 4.227176 \n",
+ "max 1.000000 5.651427 \n",
+ "\n",
+ " original_glrlm_RunLengthNonUniformity \\\n",
+ "count 400.000000 \n",
+ "mean 340.638141 \n",
+ "std 475.055615 \n",
+ "min 28.080182 \n",
+ "25% 115.002731 \n",
+ "50% 207.088943 \n",
+ "75% 407.634309 \n",
+ "max 6957.420630 \n",
+ "\n",
+ " original_glrlm_RunLengthNonUniformityNormalized \\\n",
+ "count 400.000000 \n",
+ "mean 0.120189 \n",
+ "std 0.043528 \n",
+ "min 0.039053 \n",
+ "25% 0.085970 \n",
+ "50% 0.113047 \n",
+ "75% 0.147702 \n",
+ "max 0.262586 \n",
+ "\n",
+ " original_glrlm_RunPercentage original_glrlm_RunVariance \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 0.172449 33.417605 \n",
+ "std 0.050184 22.730155 \n",
+ "min 0.067764 2.772991 \n",
+ "25% 0.135429 18.058657 \n",
+ "50% 0.167160 27.838675 \n",
+ "75% 0.199018 43.591408 \n",
+ "max 0.423848 227.216258 \n",
+ "\n",
+ " original_glrlm_ShortRunEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 0.278120 \n",
+ "std 0.104823 \n",
+ "min 0.065387 \n",
+ "25% 0.189805 \n",
+ "50% 0.273416 \n",
+ "75% 0.369707 \n",
+ "max 0.498117 \n",
+ "\n",
+ " original_glrlm_ShortRunHighGrayLevelEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 0.547245 \n",
+ "std 0.137347 \n",
+ "min 0.065387 \n",
+ "25% 0.477469 \n",
+ "50% 0.555676 \n",
+ "75% 0.627946 \n",
+ "max 1.025800 \n",
+ "\n",
+ " original_glrlm_ShortRunLowGrayLevelEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 0.210838 \n",
+ "std 0.115990 \n",
+ "min 0.018789 \n",
+ "25% 0.104734 \n",
+ "50% 0.208185 \n",
+ "75% 0.312460 \n",
+ "max 0.457650 \n",
+ "\n",
+ " original_glszm_GrayLevelNonUniformity \\\n",
+ "count 400.000000 \n",
+ "mean 48.730722 \n",
+ "std 69.761309 \n",
+ "min 1.000000 \n",
+ "25% 9.181818 \n",
+ "50% 24.076923 \n",
+ "75% 61.054579 \n",
+ "max 594.003356 \n",
+ "\n",
+ " original_glszm_GrayLevelNonUniformityNormalized \\\n",
+ "count 400.000000 \n",
+ "mean 0.874733 \n",
+ "std 0.123567 \n",
+ "min 0.500000 \n",
+ "25% 0.834711 \n",
+ "50% 0.916824 \n",
+ "75% 0.963144 \n",
+ "max 1.000000 \n",
+ "\n",
+ " original_glszm_GrayLevelVariance \\\n",
+ "count 400.000000 \n",
+ "mean 0.062633 \n",
+ "std 0.061783 \n",
+ "min 0.000000 \n",
+ "25% 0.018428 \n",
+ "50% 0.041588 \n",
+ "75% 0.082645 \n",
+ "max 0.250000 \n",
+ "\n",
+ " original_glszm_HighGrayLevelZoneEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 1.260478 \n",
+ "std 0.387635 \n",
+ "min 1.000000 \n",
+ "25% 1.056342 \n",
+ "50% 1.130435 \n",
+ "75% 1.272727 \n",
+ "max 3.400000 \n",
+ "\n",
+ " original_glszm_LargeAreaEmphasis \\\n",
+ "count 4.000000e+02 \n",
+ "mean 1.038107e+08 \n",
+ "std 1.048229e+09 \n",
+ "min 5.717762e+04 \n",
+ "25% 1.311764e+06 \n",
+ "50% 3.760290e+06 \n",
+ "75% 1.012511e+07 \n",
+ "max 1.467713e+10 \n",
+ "\n",
+ " original_glszm_LargeAreaHighGrayLevelEmphasis \\\n",
+ "count 4.000000e+02 \n",
+ "mean 3.000160e+08 \n",
+ "std 3.174131e+09 \n",
+ "min 2.280370e+05 \n",
+ "25% 5.031858e+06 \n",
+ "50% 1.446362e+07 \n",
+ "75% 3.861245e+07 \n",
+ "max 5.870849e+10 \n",
+ "\n",
+ " original_glszm_LargeAreaLowGrayLevelEmphasis \\\n",
+ "count 4.000000e+02 \n",
+ "mean 5.475941e+07 \n",
+ "std 7.352483e+08 \n",
+ "min 1.446278e+04 \n",
+ "25% 3.567324e+05 \n",
+ "50% 9.685342e+05 \n",
+ "75% 2.688915e+06 \n",
+ "max 1.419410e+10 \n",
+ "\n",
+ " original_glszm_LowGrayLevelZoneEmphasis \\\n",
+ "count 400.000000 \n",
+ "mean 0.934880 \n",
+ "std 0.096909 \n",
+ "min 0.400000 \n",
+ "25% 0.931818 \n",
+ "50% 0.967391 \n",
+ "75% 0.985915 \n",
+ "max 1.000000 \n",
+ "\n",
+ " original_glszm_SizeZoneNonUniformity \\\n",
+ "count 400.000000 \n",
+ "mean 10.672010 \n",
+ "std 14.404000 \n",
+ "min 1.000000 \n",
+ "25% 2.087413 \n",
+ "50% 5.170909 \n",
+ "75% 12.702912 \n",
+ "max 117.476510 \n",
+ "\n",
+ " original_glszm_SizeZoneNonUniformityNormalized \\\n",
+ "count 400.000000 \n",
+ "mean 0.239151 \n",
+ "std 0.132594 \n",
+ "min 0.066991 \n",
+ "25% 0.160370 \n",
+ "50% 0.208256 \n",
+ "75% 0.277568 \n",
+ "max 1.000000 \n",
+ "\n",
+ " original_glszm_SmallAreaEmphasis \\\n",
+ "count 4.000000e+02 \n",
+ "mean 3.920331e-01 \n",
+ "std 1.617334e-01 \n",
+ "min 7.050000e-11 \n",
+ "25% 3.199015e-01 \n",
+ "50% 4.073021e-01 \n",
+ "75% 4.956921e-01 \n",
+ "max 8.571429e-01 \n",
+ "\n",
+ " original_glszm_SmallAreaHighGrayLevelEmphasis \\\n",
+ "count 4.000000e+02 \n",
+ "mean 3.957637e-01 \n",
+ "std 1.666319e-01 \n",
+ "min 7.050000e-11 \n",
+ "25% 3.199017e-01 \n",
+ "50% 4.095627e-01 \n",
+ "75% 5.000049e-01 \n",
+ "max 8.773779e-01 \n",
+ "\n",
+ " original_glszm_SmallAreaLowGrayLevelEmphasis \\\n",
+ "count 4.000000e+02 \n",
+ "mean 3.911005e-01 \n",
+ "std 1.615922e-01 \n",
+ "min 7.050000e-11 \n",
+ "25% 3.184398e-01 \n",
+ "50% 4.054695e-01 \n",
+ "75% 4.956920e-01 \n",
+ "max 8.571429e-01 \n",
+ "\n",
+ " original_glszm_ZoneEntropy original_glszm_ZonePercentage \\\n",
+ "count 4.000000e+02 400.000000 \n",
+ "mean 2.722189e+00 0.003347 \n",
+ "std 7.648849e-01 0.002419 \n",
+ "min -3.200000e-16 0.000008 \n",
+ "25% 2.340783e+00 0.001389 \n",
+ "50% 2.814884e+00 0.002944 \n",
+ "75% 3.304411e+00 0.004798 \n",
+ "max 4.947427e+00 0.011301 \n",
+ "\n",
+ " original_glszm_ZoneVariance original_ngtdm_Busyness \\\n",
+ "count 4.000000e+02 400.000000 \n",
+ "mean 5.679717e+07 178.311246 \n",
+ "std 7.063846e+08 1045.453432 \n",
+ "min 0.000000e+00 0.000000 \n",
+ "25% 1.030473e+06 18.760570 \n",
+ "50% 3.277334e+06 67.929659 \n",
+ "75% 9.079686e+06 157.370294 \n",
+ "max 1.390001e+10 20764.693790 \n",
+ "\n",
+ " original_ngtdm_Coarseness original_ngtdm_Complexity \\\n",
+ "count 400.000000 400.000000 \n",
+ "mean 32500.032620 0.056935 \n",
+ "std 177545.921568 0.047179 \n",
+ "min 0.000248 0.000000 \n",
+ "25% 0.001826 0.018628 \n",
+ "50% 0.004383 0.047740 \n",
+ "75% 0.013769 0.085321 \n",
+ "max 1000000.000000 0.285100 \n",
+ "\n",
+ " original_ngtdm_Contrast original_ngtdm_Strength \n",
+ "count 400.000000 400.000000 \n",
+ "mean 0.005965 0.029322 \n",
+ "std 0.008379 0.115915 \n",
+ "min 0.000000 0.000000 \n",
+ "25% 0.000310 0.001464 \n",
+ "50% 0.002330 0.003276 \n",
+ "75% 0.007962 0.009479 \n",
+ "max 0.060742 1.145601 "
+ ]
+ },
+ "execution_count": 33,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "#Load the dataset\n",
+ "df = pd.read_csv('TrainDataset2024.csv',index_col=False)\n",
+ "df.info()\n",
+ "df.describe()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### DATA PRE-PROCESSING"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 34,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "data size before removing missing values: (400, 121)\n",
+ "data size after removing missing values: (398, 120)\n"
+ ]
+ }
+ ],
+ "source": [
+ "print (\"data size before removing missing values: \", df.shape)\n",
+ "missing_values_index = np.where(df.isin([999]) == True)\n",
+ "missing_values_index = np.array(missing_values_index).tolist()\n",
+ "missing_values_index = set(missing_values_index[0])\n",
+ "\n",
+ "drop_index = []\n",
+ "for index in missing_values_index:\n",
+ " missing_values_rows = df.iloc[index]\n",
+ " missing_values_rows = np.array(missing_values_rows).tolist()\n",
+ " if missing_values_rows.count(999) >= 4:\n",
+ " drop_index.append(index)\n",
+ "\n",
+ "df = df.drop(drop_index)\n",
+ "\n",
+ "# retain the original dataset with ID column to be used in the future\n",
+ "dataset_ID = df['ID']\n",
+ "df.drop('ID', axis=1, inplace=True)\n",
+ "print (\"data size after removing missing values: \", df.shape)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 35,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 1600x400 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "# Identify outliers using the 25th and 75th percentiles\n",
+ "Q1 = df.quantile(0.25)\n",
+ "Q3 = df.quantile(0.75)\n",
+ "IQR = Q3 - Q1\n",
+ "\n",
+ "# Define extreme outliers\n",
+ "extreme_outliers = ((df < (Q1 - 3 * IQR)) | (df > (Q3 + 3 * IQR)))\n",
+ "\n",
+ "# Filter columns with extreme outliers\n",
+ "extreme_outlier_columns = df.columns[extreme_outliers.any()]\n",
+ "\n",
+ "# Filter the DataFrame to include only columns with extreme outliers\n",
+ "df_extreme_outliers = df[extreme_outlier_columns]\n",
+ "\n",
+ "# Plot boxplot for columns with extreme outliers\n",
+ "plt.figure(figsize=(16, 4))\n",
+ "sns.boxplot(data=df_extreme_outliers)\n",
+ "plt.xticks(rotation=90) # Rotate x-axis labels for better visibility\n",
+ "plt.title(\"Box Plot for Extreme Outlier Detection (Columns with Extreme Outliers)\")\n",
+ "plt.xlabel(\"Features\")\n",
+ "plt.ylabel(\"Values\")\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Missing value exists in each column:\n",
+ " pCR (outcome) True\n",
+ "RelapseFreeSurvival (outcome) False\n",
+ "Age False\n",
+ "ER False\n",
+ "PgR False\n",
+ " ... \n",
+ "original_ngtdm_Busyness False\n",
+ "original_ngtdm_Coarseness False\n",
+ "original_ngtdm_Complexity False\n",
+ "original_ngtdm_Contrast False\n",
+ "original_ngtdm_Strength False\n",
+ "Length: 120, dtype: bool\n"
+ ]
+ }
+ ],
+ "source": [
+ "column_checks = df.isin([999]).any()\n",
+ "print(\"Missing value exists in each column:\\n\", column_checks)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Number of values equal to 999 in all columns before imputer is : 97\n",
+ "Number of values equal to 999 in all columns after imputer is : 0\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Count the number of values equal to 999 in all the columns before imputer\n",
+ "count_999 = (df.iloc[:, :] == 999).sum().sum()\n",
+ "print(f\"Number of values equal to 999 in all columns before imputer is : {count_999}\")\n",
+ "\n",
+ "# Replace 999 with NaN\n",
+ "new_df = df.replace(999, np.NaN)\n",
+ "column_names = new_df.columns\n",
+ "\n",
+ "# Perform iterative imputation\n",
+ "multivariate_imp = IterativeImputer(random_state=42)\n",
+ "multi_imputed_array = multivariate_imp.fit_transform(new_df)\n",
+ "\n",
+ "# Create a mask of the imputed values\n",
+ "imputed_mask = np.isnan(new_df.values)\n",
+ "\n",
+ "# Round only the imputed values\n",
+ "multi_imputed_array[imputed_mask] = np.round(multi_imputed_array[imputed_mask])\n",
+ "\n",
+ "# Convert to DataFrame\n",
+ "multi_imputed_df = pd.DataFrame(multi_imputed_array, columns=column_names)\n",
+ "\n",
+ "# Get the target and features dataframe\n",
+ "regression_target = multi_imputed_df['RelapseFreeSurvival (outcome)']\n",
+ "regression_features = multi_imputed_df.drop(['RelapseFreeSurvival (outcome)', 'pCR (outcome)'], axis=1)\n",
+ "\n",
+ "# Count the number of values equal to 999 in all the columns after imputer\n",
+ "count_999 = (multi_imputed_df.iloc[:, :] == 999).sum().sum()\n",
+ "print(f\"Number of values equal to 999 in all columns after imputer is : {count_999}\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Best parameters: {'max_depth': 20, 'max_features': 'log2', 'min_samples_leaf': 2, 'min_samples_split': 2, 'n_estimators': 100}\n",
+ "Best MAE: 23.03975180253857\n",
+ "Mean MAE with selected features and best parameters: 23.03975180253857\n",
+ "MAE on test set: 21.12190711281137\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Assuming regression_features and regression_target are already defined\n",
+ "\n",
+ "# Step 1: Handle Outliers\n",
+ "z_scores = np.abs(stats.zscore(regression_features))\n",
+ "filtered_entries = (z_scores < 3).all(axis=1)\n",
+ "regression_features_filtered = regression_features[filtered_entries]\n",
+ "regression_target_filtered = regression_target[filtered_entries]\n",
+ "\n",
+ "# Step 2: Feature Selection using RFE\n",
+ "rf = RandomForestRegressor(random_state=42)\n",
+ "rfe = RFE(estimator=rf, n_features_to_select=20)\n",
+ "rfe.fit(regression_features_filtered, regression_target_filtered)\n",
+ "selected_features_rfe = rfe.transform(regression_features_filtered)\n",
+ "\n",
+ "# Step 3: Feature Engineering - Polynomial Features\n",
+ "poly = PolynomialFeatures(degree=2, interaction_only=True)\n",
+ "regression_features_poly = poly.fit_transform(selected_features_rfe)\n",
+ "\n",
+ "# Step 4: Data Normalization\n",
+ "scaler = StandardScaler()\n",
+ "regression_features_scaled = scaler.fit_transform(regression_features_poly)\n",
+ "\n",
+ "# Step 5: Hyperparameter Tuning with GridSearchCV\n",
+ "param_grid = {\n",
+ " 'n_estimators': [100, 200, 300],\n",
+ " 'max_features': ['auto', 'sqrt', 'log2'],\n",
+ " 'max_depth': [10, 20, 30, None],\n",
+ " 'min_samples_split': [2, 5, 10],\n",
+ " 'min_samples_leaf': [1, 2, 4]\n",
+ "}\n",
+ "\n",
+ "grid_search = GridSearchCV(estimator=rf, param_grid=param_grid, cv=5, scoring='neg_mean_absolute_error', n_jobs=-1)\n",
+ "grid_search.fit(regression_features_scaled, regression_target_filtered)\n",
+ "\n",
+ "print(f\"Best parameters: {grid_search.best_params_}\")\n",
+ "print(f\"Best MAE: {-grid_search.best_score_}\")\n",
+ "\n",
+ "# Step 6: Train the final model with the best parameters\n",
+ "best_rf = grid_search.best_estimator_\n",
+ "best_rf.fit(regression_features_scaled, regression_target_filtered)\n",
+ "\n",
+ "# Step 7: Evaluate the model using cross-validation\n",
+ "scores = cross_val_score(best_rf, regression_features_scaled, regression_target_filtered, cv=5, scoring='neg_mean_absolute_error')\n",
+ "print(f\"Mean MAE with selected features and best parameters: {-scores.mean()}\")\n",
+ "\n",
+ "# Step 8: Train-test split to check MAE on test set\n",
+ "X_train, X_test, y_train, y_test = train_test_split(regression_features_scaled, regression_target_filtered, test_size=0.2, random_state=42)\n",
+ "best_rf.fit(X_train, y_train)\n",
+ "y_pred = best_rf.predict(X_test)\n",
+ "mae = mean_absolute_error(y_test, y_pred)\n",
+ "print(f\"MAE on test set: {mae}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Feature Selection "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 39,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "features_to_be_selected = 20\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "P-value less than <= 0.05 indicates significant dependency between values"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 40,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 640x480 with 2 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "f, p_val = f_regression(regression_features, regression_target)\n",
+ "f_reg_df = pd.DataFrame(np.array([f, p_val]).T, index=regression_features.columns, columns=['f-statistic', 'p-value'])\n",
+ "binary_stored_features = f_reg_df[f_reg_df['p-value'] <= 0.05].sort_values(by='f-statistic', ascending=False).head(\n",
+ " features_to_be_selected)\n",
+ "sns.heatmap(data=binary_stored_features, annot=True)\n",
+ "plt.title(f'Top {len(binary_stored_features)} features with p-value less than 0.05')\n",
+ "plt.show()\n",
+ "binary_stored_features = binary_stored_features.head(20)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Mutual info to find best features"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 41,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "iVBORw0KGgoAAAANSUhEUgAAA4sAAAGzCAYAAACGpYKKAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzdd1gUx//A8ffRO0gRLCBVBLugUTSCFXusxBIVwRKNoklQxAr2Gms0ahRIoqKxxUQRS8TEEksUkyixRcAkKvYCEYHb3x/+2C/HHQgIYpnX8+zzyOzs7Gf29s6bm9kZhSRJEoIgCIIgCIIgCIKQh1Z5ByAIgiAIgiAIgiC8ekRjURAEQRAEQRAEQVAjGouCIAiCIAiCIAiCGtFYFARBEARBEARBENSIxqIgCIIgCIIgCIKgRjQWBUEQBEEQBEEQBDWisSgIgiAIgiAIgiCoEY1FQRAEQRAEQRAEQY1oLAqCIAiCIAiCIAhqRGNREARBEF6S+fPn4+zsjLa2NvXq1SvvcIRXTGBgII6OjmV+npMnT+Lj44OxsTEKhYLExMQyP+fL4ujoSGBgYHmH8daKiIhAoVCUdxhCKRKNRUEQBOGlUygURdoSEhLKNI5r164RGRlJo0aNqFChAtbW1vj5+bF//36N+e/fv8/QoUOxsbHB2NiYFi1acPr06SKda+/evYwbN46mTZsSFRXFrFmzSrMqst27dxMREVEmZb9qAgMDUSgUmJmZ8d9//6ntv3TpknwvLViwoETnWLFiBdHR0S8Yaeny8/OjVq1aJTo2KyuLXr16cffuXRYtWsTXX39NtWrVSjnCsnX06FEiIiK4f/9+eYcii46OVvns0tHRoUqVKgQGBvLPP/+Ud3iCUGI65R2AIAiC8Pb5+uuvVf7+6quv2Ldvn1q6h4dHmcbx3XffMXfuXLp27crAgQPJzs7mq6++ok2bNqxbt45BgwbJeZVKJR07duTs2bOMHTsWa2trVqxYgZ+fH7/++itubm6FnuvHH39ES0uLtWvXoqenV2Z12r17N59//vlb02DU0dEhIyOD77//noCAAJV969evx8DAgCdPnpS4/BUrVmBtbf3G9FZduXKFlJQU1qxZw+DBg8s7nBI5evQokZGRBAYGYmFhobLvwoULaGmVX1/ItGnTcHJy4smTJ/zyyy9ER0dz+PBh/vjjDwwMDMotrpdl0qRJjB8/vrzDEEqRaCwKgiAIL90HH3yg8vcvv/zCvn371NLLWosWLUhNTcXa2lpO+/DDD6lXrx5TpkxRaSxu2bKFo0eP8u2339KzZ08AAgICqF69OlOnTmXDhg2FnistLQ1DQ8MybSiWpfT0dIyNjcs7DDX6+vo0bdqUjRs3qjUWN2zYQMeOHdm6dWs5RffqSUtLA1BrZL2IV+ne0NfXL9fzt2/fHm9vbwAGDx6MtbU1c+fOZefOnWr3Z1mSJIknT55gaGj40s4Jz3680dERzYs3iRiGKgiCILyS0tPT+fTTT7G3t0dfXx93d3cWLFiAJEkq+RQKBSNHjmT9+vW4u7tjYGCAl5cXP/3003PPUbNmTZWGIjz7stmhQwf+/vtvHj16JKdv2bIFW1tbunfvLqfZ2NgQEBDAd999R2ZmZoHnUSgUREVFkZ6eLg9Tyzu08ZtvvsHLywtDQ0MsLS3p3bs3165dUynj559/plevXjg4OKCvr4+9vT0ff/yxyvDLwMBAPv/8c/mcuRtAQkKCxqG9ycnJavEEBgZiYmLClStX6NChA6ampvTr1w941sO6ePFiatasiYGBAba2tgwbNox79+6plHvq1Cn8/f2xtrbG0NAQJycngoKCCrxGL6Jv377ExcWpDEs8efIkly5dom/fvmr5C3quKncoYXJyMvDs+bdz585x6NAh+Vr6+fkVqwx41oPdsWNHKleujL6+Pi4uLkyfPp2cnJwXqndeue+DHTt2UKtWLfT19alZsyZ79uyR8wQGBuLr6wtAr169VOoDz3q/3333XYyNjbGwsOC9994jKSlJ5Ty59T5//jx9+/alQoUKNGvWDHh2vTp16kRCQgLe3t4YGhpSu3Zt+Z7btm0btWvXlt+jZ86cUSn7t99+IzAwEGdnZwwMDLCzsyMoKIg7d+6onH/s2LEAODk5ya9L3tcsfy/wX3/9Ra9evbC0tMTIyIjGjRuza9culTy574/Nmzczc+ZMqlatioGBAa1ateLy5cvFezHyePfdd4FnPbp5/fnnn/Ts2RNLS0sMDAzw9vZm586dasf/9ttv+Pr6YmhoSNWqVZkxYwZRUVFq91jutY+Pj5ev/apVq4Bnw+fHjBkjf5a6uroyd+5clEqlyrliY2Px8vLC1NQUMzMzateuzZIlS+T9WVlZREZG4ubmhoGBAVZWVjRr1ox9+/bJeTS9L7Kzs5k+fTouLi7o6+vj6OjIhAkT1D4zc+tw+PBhGjVqhIGBAc7Oznz11VfFuOJCaRNNf0EQBOGVI0kSXbp04eDBgwQHB1OvXj3i4+MZO3Ys//zzD4sWLVLJf+jQITZt2kRISAj6+vqsWLGCdu3aceLEiRI923Xjxg2MjIwwMjKS086cOUODBg3Uhrg1atSI1atXc/HiRWrXrq2xvK+//prVq1dz4sQJvvzySwB8fHwAmDlzJpMnTyYgIIDBgwdz69Ytli1bRvPmzTlz5ozcA/Ttt9+SkZHB8OHDsbKy4sSJEyxbtoy///6bb7/9FoBhw4bx77//ahzSW1zZ2dn4+/vTrFkzFixYIF+LYcOGER0dzaBBgwgJCeHq1assX76cM2fOcOTIEXR1dUlLS6Nt27bY2Ngwfvx4LCwsSE5OZtu2bS8UU0G6d+/Ohx9+yLZt2+QG6YYNG6hRowYNGjQocbmLFy9m1KhRmJiYMHHiRABsbW2LXU50dDQmJiZ88sknmJiY8OOPPzJlyhQePnzI/PnzSxxffocPH2bbtm2MGDECU1NTli5dSo8ePUhNTcXKyophw4ZRpUoVZs2aRUhICA0bNpTrs3//ftq3b4+zszMRERH8999/LFu2jKZNm3L69Gm1iXd69eqFm5sbs2bNUvkB5/Lly/Tt25dhw4bxwQcfsGDBAjp37swXX3zBhAkTGDFiBACzZ88mICBAZdjovn37+Ouvvxg0aBB2dnacO3eO1atXc+7cOX755RcUCgXdu3fn4sWLbNy4kUWLFsk/9tjY2Gi8Jjdv3sTHx4eMjAxCQkKwsrIiJiaGLl26sGXLFrp166aSf86cOWhpaREaGsqDBw+YN28e/fr14/jx4yV6TXIbdBUqVJDTzp07R9OmTalSpQrjx4/H2NiYzZs307VrV7Zu3SrH9M8//9CiRQsUCgXh4eEYGxvz5ZdfFth7euHCBfr06cOwYcMYMmQI7u7uZGRk4Ovryz///MOwYcNwcHDg6NGjhIeHc/36dRYvXixf+z59+tCqVSvmzp0LQFJSEkeOHGH06NHAs4bg7NmzGTx4MI0aNeLhw4ecOnWK06dP06ZNmwKvweDBg4mJiaFnz558+umnHD9+nNmzZ5OUlMT27dtV8l6+fJmePXsSHBzMwIEDWbduHYGBgXh5eVGzZs0SvQbCC5IEQRAEoZx99NFHUt7/knbs2CEB0owZM1Ty9ezZU1IoFNLly5flNEACpFOnTslpKSkpkoGBgdStW7dix3Lp0iXJwMBA6t+/v0q6sbGxFBQUpJZ/165dEiDt2bOn0HIHDhwoGRsbq6QlJydL2tra0syZM1XSf//9d0lHR0clPSMjQ63M2bNnSwqFQkpJSZHT8l/LXAcPHpQA6eDBgyrpV69elQApKipKJVZAGj9+vEren3/+WQKk9evXq6Tv2bNHJX379u0SIJ08eVLDlSg9ea9pz549pVatWkmSJEk5OTmSnZ2dFBkZKddv/vz58nFTp07VeI2ioqIkQLp69aqcVrNmTcnX11ctb3HK0PTaDRs2TDIyMpKePHmiUp9q1ao9r9qSr6+vVLNmTZU0QNLT01N5b5w9e1YCpGXLlslpuffBt99+q3J8vXr1pIoVK0p37txROV5LS0saMGCAWr379OmjFle1atUkQDp69KicFh8fLwGSoaGhyn26atUqtftR03XauHGjBEg//fSTnDZ//ny1a5w3hoEDB8p/jxkzRgKkn3/+WU579OiR5OTkJDk6Oko5OTkq18XDw0PKzMyU8y5ZskQCpN9//13tXHnlvu779++Xbt26JV27dk3asmWLZGNjI+nr60vXrl2T87Zq1UqqXbu2ymuvVColHx8fyc3NTU4bNWqUpFAopDNnzshpd+7ckSwtLdXqn3vt838OTZ8+XTI2NpYuXryokj5+/HhJW1tbSk1NlSRJkkaPHi2ZmZlJ2dnZBdaxbt26UseOHQu9DvnfF4mJiRIgDR48WCVfaGioBEg//vijWh3yvtZpaWmSvr6+9OmnnxZ6XqHsiGGogiAIwitn9+7daGtrExISopL+6aefIkkScXFxKulNmjTBy8tL/tvBwYH33nuP+Pj4Yg31y8jIoFevXhgaGjJnzhyVff/995/GX/RzJ63QNBvn82zbtg2lUklAQAC3b9+WNzs7O9zc3Dh48KCcN++zR+np6dy+fRsfHx8kSVIbzldahg8frvL3t99+i7m5OW3atFGJ18vLCxMTEzne3N7QH374gaysrDKJLb++ffuSkJDAjRs3+PHHH7lx44bGIajlIe9r9+jRI27fvs27775LRkYGf/75Z6mdp3Xr1ri4uMh/16lTBzMzM/76669Cj7t+/TqJiYkEBgZiaWmpcnybNm3YvXu32jEffvihxrI8PT1p0qSJ/Pc777wDQMuWLXFwcFBLzxtb3uv05MkTbt++TePGjQGKPOtwfrt376ZRo0byUFkAExMThg4dSnJyMufPn1fJP2jQIJXninOHkT7vGuZq3bo1NjY22Nvb07NnT4yNjdm5cydVq1YF4O7du/z4448EBATI98Lt27e5c+cO/v7+XLp0SZ49dc+ePTRp0kRlmR1LS0t5SHh+Tk5O+Pv7q6R9++23vPvuu1SoUEHlPdu6dWtycnLk4foWFhakp6erDCnNz8LCgnPnznHp0qUiXQtAvnc++eQTlfRPP/0UQG04sKenp3zN4VmPsbu7e5Gvv1D6xDBUQRAE4ZWTkpJC5cqVMTU1VUnPnR01JSVFJV3TTKTVq1cnIyODW7duYWdn99xz5uTk0Lt3b86fP09cXByVK1dW2W9oaKjxucTcmTZLMpHEpUuXkCSpwJlUdXV15X+npqYyZcoUdu7cqfZ84IMHD4p97ufR0dGRv+DmjffBgwdUrFhR4zG5k6f4+vrSo0cPIiMjWbRoEX5+fnTt2pW+ffsWOgHJgwcPVBrdenp6Ko2XwuQ+W7lp0yYSExNp2LAhrq6uKs91lZdz584xadIkfvzxRx4+fKiyrzRfu7yNsVwVKlRQu1/yy30/ubu7q+3z8PAgPj5ebRIbJyenIsVgbm4OgL29vcb0vLHdvXuXyMhIYmNj5XspV0mvU0pKitwwzSvvZ0neoer5488dPvq8a5jr888/p3r16jx48IB169bx008/qdzzly9fRpIkJk+ezOTJkzWWkZaWRpUqVUhJSVFpeOdydXXVeJym1+TSpUv89ttvBQ7Tzb3OI0aMYPPmzbRv354qVarQtm1bAgICaNeunZx32rRpvPfee1SvXp1atWrRrl07+vfvT506dQq8HikpKWhpaanFbGdnh4WFhdpneUnvYaHsiMaiIAiCIABDhgzhhx9+YP369bRs2VJtf6VKlbh+/bpaem5a/sZlUSiVShQKBXFxcWhra6vtNzExAZ41ZNu0acPdu3cJCwujRo0aGBsb888//xAYGKg2UYUmBS2UXVDPq76+vtrzmUqlkooVK7J+/XqNx+R+IVUoFGzZsoVffvmF77//nvj4eIKCgli4cCG//PKLXK/8Ro8eTUxMjPy3r69vkdfa1NfXp3v37sTExPDXX38VunRIca/Fi5Rx//59fH19MTMzY9q0abi4uGBgYMDp06cJCwsr0mtXVJruIUBtUqjSUNCPIwXFUJTYAgICOHr0KGPHjqVevXqYmJigVCpp165dqV6nwrzoNWzUqJE8G2rXrl1p1qwZffv25cKFC3J9AEJDQ9V6AXMV1Bh8Hk2viVKppE2bNowbN07jMdWrVwegYsWKJCYmEh8fT1xcHHFxcURFRTFgwAD5Pdm8eXOuXLnCd999x969e/nyyy9ZtGgRX3zxxXOXYSno/ZLfy7yHhaIRjUVBEAThlVOtWjX279/Po0ePVHoXc4fs5V9EXNOwqIsXL2JkZFTgL+p5jR07lqioKBYvXkyfPn005qlXrx4///wzSqVSpRF1/PhxjIyM5C9dxeHi4oIkSTg5ORV6/O+//87FixeJiYlhwIABcrqmIWMFfSnL7SHJv5B5/l/2nxfv/v37adq0aZF6Uhs3bkzjxo2ZOXMmGzZsoF+/fsTGxhb4xXLcuHEqy6fknRSkKPr27cu6devQ0tKid+/eBebLey3yLiGh6VoU5XoWVkZCQgJ37txh27ZtNG/eXE6/evXqc+vzsuS+ny5cuKC2788//8Ta2rrMl8a4d+8eBw4cIDIykilTpsjpmt7bRW14wLO6FVSv3P1lRVtbm9mzZ9OiRQuWL1/O+PHjcXZ2Bp6NGmjdunWhx1erVk3jTKzFmZ3VxcWFx48fP/dc8Kwnv3PnznTu3BmlUsmIESNYtWoVkydPlhuwlpaWDBo0iEGDBvH48WOaN29OREREge/patWqoVQquXTpksq6uTdv3uT+/ftlev2F0iGeWRQEQRBeOR06dCAnJ4fly5erpC9atAiFQkH79u1V0o8dO6byTNO1a9f47rvvaNu2bYG/VOeaP38+CxYsYMKECfKsf5r07NmTmzdvqszoefv2bb799ls6d+5covXdunfvjra2NpGRkWq/nEuSJC8ZkFuHvHkkSVKZ1j5X7pf6/I3CatWqoa2trbakyIoVK4ocb0BAADk5OUyfPl1tX3Z2tnzOe/fuqdUn97mrwpYY8fT0pHXr1vKW9znUomjRogXTp09n+fLlhQ49zn2uL++1SE9PV+nVzGVsbKx2LYtThqbX7unTp8W67mWtUqVK1KtXj5iYGJW6/vHHH+zdu5cOHTqUeQyarhMgz9aZV0H3uCYdOnTgxIkTHDt2TE5LT09n9erVODo64unpWfKgi8DPz49GjRqxePFinjx5QsWKFfHz82PVqlUaRyrcunVL/re/vz/Hjh0jMTFRTrt7926BPfuaBAQEcOzYMeLj49X23b9/n+zsbACV5UkAtLS05OGlue/Z/HlMTExwdXUt9D2de+/kfx0/++wzADp27FjkugjlQ/QsCoIgCK+czp0706JFCyZOnEhycjJ169Zl7969fPfdd4wZM0ZlEg+AWrVq4e/vr7J0BkBkZGSh59m+fTvjxo3Dzc0NDw8PvvnmG5X9bdq0kZcW6NmzJ40bN2bQoEGcP38ea2trVqxYQU5OznPPUxAXFxdmzJhBeHg4ycnJdO3aFVNTU65evcr27dsZOnQooaGh1KhRAxcXF0JDQ/nnn38wMzNj69atGp/jyW1ghYSE4O/vj7a2Nr1798bc3JxevXqxbNkyFAoFLi4u/PDDD2rPhhXG19eXYcOGMXv2bBITE2nbti26urpcunSJb7/9liVLltCzZ09iYmJYsWIF3bp1w8XFhUePHrFmzRrMzMzKtOGhpaXFpEmTnpuvbdu2ODg4EBwczNixY9HW1mbdunXY2NiQmpqqktfLy4uVK1cyY8YMXF1dqVixIi1btixyGT4+PlSoUIGBAwcSEhKCQqHg66+/fuWG1c2fP5/27dvTpEkTgoOD5aUzzM3NCx3SW1rMzMxo3rw58+bNIysriypVqrB3716NPbC59/jEiRPp3bs3urq6dO7cWWPv5/jx49m4cSPt27cnJCQES0tLYmJiuHr1Klu3blUbal0Wxo4dS69evYiOjubDDz/k888/p1mzZtSuXZshQ4bg7OzMzZs3OXbsGH///Tdnz54FnvW0f/PNN7Rp04ZRo0bJS2c4ODhw9+7dIvWwjh07lp07d9KpUyd5CYr09HR+//13tmzZQnJyMtbW1gwePJi7d+/SsmVLqlatSkpKCsuWLaNevXpyj6Cnpyd+fn54eXlhaWnJqVOn2LJlCyNHjizw/HXr1mXgwIGsXr1aHpJ94sQJYmJi6Nq1Ky1atCidiyyUnZc+/6ogCIIg5KNpuYdHjx5JH3/8sVS5cmVJV1dXcnNzk+bPny8plUqVfID00UcfSd98843k5uYm6evrS/Xr11dbIkKT3GneC9ryl3H37l0pODhYsrKykoyMjCRfX98iLw+haemMXFu3bpWaNWsmGRsbS8bGxlKNGjWkjz76SLpw4YKc5/z581Lr1q0lExMTydraWhoyZIi8NELeZS+ys7OlUaNGSTY2NpJCoVC5rrdu3ZJ69OghGRkZSRUqVJCGDRsm/fHHHxqXzigoVkmSpNWrV0teXl6SoaGhZGpqKtWuXVsaN26c9O+//0qSJEmnT5+W+vTpIzk4OEj6+vpSxYoVpU6dOqksb1IanhenJEkal86QJEn69ddfpXfeeUfS09OTHBwcpM8++0zjshc3btyQOnbsKJmamkqAyjIaRS3jyJEjUuPGjSVDQ0OpcuXK0rhx4+QlJfLeYy+6dMZHH32kljf/UhIFLZ0hSZK0f/9+qWnTppKhoaFkZmYmde7cWTp//rxKntz3zK1btzSeS9PSCppi0/S6/P3331K3bt0kCwsLydzcXOrVq5f077//SoA0depUleOnT58uValSRdLS0lK53vnrK0mSdOXKFalnz56ShYWFZGBgIDVq1Ej64YcfVPIUdF00LS2jSe7rrunzICcnR3JxcZFcXFzkpSmuXLkiDRgwQLKzs5N0dXWlKlWqSJ06dZK2bNmicuyZM2ekd999V9LX15eqVq0qzZ49W1q6dKkESDdu3JDzFXTtJenZZ2l4eLjk6uoq6enpSdbW1pKPj4+0YMEC6enTp5IkSdKWLVuktm3bShUrVpTv52HDhknXr1+Xy5kxY4bUqFEjycLCQjI0NJRq1KghzZw5Uy5DkjQvKZOVlSVFRkZKTk5Okq6urmRvby+Fh4erLB1SWB18fX01Ll8jvBwKSXrFftoSBEEQhGJQKBR89NFHakNWBUEQ3kRjxoxh1apVPH78+LnD7AXhRYlnFgVBEARBEAThFZR//dY7d+7w9ddf06xZM9FQFF4K8cyiIAiCIAiCILyCmjRpgp+fHx4eHty8eZO1a9fy8OHDAtdoFITSJhqLgiAIgiAIgvAK6tChA1u2bGH16tUoFAoaNGjA2rVrVZZhEYSyJJ5ZFARBEARBEARBENSIZxYFQRAEQRAEQRAENaKxKAiCIAiCIAiCIKgRjUVBEARBEARBEARBjZjgRhAEQSgXWbf/Ku8QBEEQhNeErrVzmZ+jtP5fehmxviyisSgIgiAIgiAIgqDMKe8IXjmisSgIgiAIgiAIgiApyzuCV454ZlF4Y0RERFCvXr1iHePn58eYMWPKPY7ClEWMrzpHR0cWL15c3mG8VMnJySgUChITE1+onMDAQLp27Vponvz3VP7rrVAo2LFjxwvFIQiCIAjC6080FoU3RmhoKAcOHCjWMdu2bWP69OllFNGbITAwEIVCwYcffqi276OPPkKhUBAYGFiq5zx58iRDhw4t1TJLS26jLnezsrKibdu2nDlzprxDK7Ln3ffXr1+nffv2QOk1YgXhbbVx6/e07TGQBi260GfIGH4/f6HAvJf/SmHMhBm07TGQWk3b8/Wm7Wp51ny1ifeDQ2jUujvNO/YmZPw0rqb8XZZVEIS3h1JZOtsbRDQWhdeeJElkZ2djYmKClZVVsY61tLTE1NS0jCJ7c9jb2xMbG8t///0npz158oQNGzbg4OBQ6uezsbHByMio1MstTfv37+f69evEx8fz+PFj2rdvz/379zXmzcrKernBPcfz7ns7Ozv09fVfYkSC8GaK23+IectWMzyoH9+uW4a7qxPDPpnEnXv3Neb/L/MJVSvbMWb4IKytKmjMcyrxd/p078yG1YtYvXgWWdnZDP14Ihn/PSnDmgjC20GSlKWyvUlEY1F4JWVmZhISEkLFihUxMDCgWbNmnDx5EoCEhAQUCgVxcXF4eXmhr6/P4cOH1YZ/ZmdnExISgoWFBVZWVoSFhTFw4ECVIXqahuPNmjWLoKAgTE1NcXBwYPXq1SqxhYWFUb16dYyMjHB2dmby5MklbgwUJUZN1yYsLAx7e3v09fVxdXVl7dq1KtcmPj6e+vXrY2hoSMuWLUlLSyMuLg4PDw/MzMzo27cvGRkZRY6zQYMG2Nvbs23bNjlt27ZtODg4UL9+fZW8e/bsoVmzZnKdOnXqxJUrV+T9X331FSYmJly6dElOGzFiBDVq1JBj0jQsctWqVXTq1AkjIyM8PDw4duwYly9fxs/PD2NjY3x8fFTOo2k45pgxY/Dz85P/9vPzY9SoUYwZM4YKFSpga2vLmjVrSE9PZ9CgQZiamuLq6kpcXJzaNbGyssLOzg5vb28WLFjAzZs3OX78uNwTt2nTJnx9fTEwMGD9+vUolUqmTZtG1apV0dfXp169euzZs0et3D///BMfHx8MDAyoVasWhw4dkvfl5OQQHByMk5MThoaGuLu7s2TJEo2vWWRkJDY2NpiZmfHhhx/y9OlTlXoXNrQ57zBUJycnAOrXr49CocDPz4+ffvoJXV1dbty4oXZ933333QLLFYS3zVebttOzc3u6dWyLi1M1powdhYG+Ptt/2Ksxf20Pd0JHDqZDaz/0dHU15ln12Qy6dmyDq3M1arg5M3PiJ1y/mcb5C5c05hcEQXgRorEovJLGjRvH1q1biYmJ4fTp07i6uuLv78/du3flPOPHj2fOnDkkJSVRp04dtTLmzp3L+vXriYqK4siRIzx8+LBIz2EtXLgQb29vzpw5w4gRIxg+fDgXLvxv2JCpqSnR0dGcP3+eJUuWsGbNGhYtWlSiepYkxgEDBrBx40aWLl1KUlISq1atwsTERCVPREQEy5cv5+jRo1y7do2AgAAWL17Mhg0b2LVrF3v37mXZsmXFijUoKIioqCj573Xr1jFo0CC1fOnp6XzyySecOnWKAwcOoKWlRbdu3VD+/7CMAQMG0KFDB/r160d2dja7du3iyy+/ZP369YX2Jk6fPp0BAwaQmJhIjRo16Nu3L8OGDSM8PJxTp04hSRIjR44sVp0AYmJisLa25sSJE4waNYrhw4fTq1cvfHx8OH36NG3btqV///6FNq4NDQ0BVBpk48ePZ/To0SQlJeHv78+SJUtYuHAhCxYs4LfffsPf358uXbqoNJoBxo4dy6effsqZM2do0qQJnTt35s6dOwAolUqqVq3Kt99+y/nz55kyZQoTJkxg8+bNKmUcOHCApKQkEhIS2LhxI9u2bSMyMrLY1wbgxIkTwP96Urdt20bz5s1xdnbm66+/lvNlZWWxfv16goKCSnQeQXjTZGVlcf7CJRo3rCenaWlp0di7Hmf/SCq18zxOf/bZZG4mRskIwgsTw1DViMai8MpJT09n5cqVzJ8/n/bt2+Pp6cmaNWswNDSUe9AApk2bRps2bXBxccHS0lKtnGXLlhEeHk63bt2oUaMGy5cvx8LC4rnn79ChAyNGjMDV1ZWwsDCsra05ePCgvH/SpEn4+Pjg6OhI586dCQ0NVfuyXlTFjfHixYts3ryZdevW0a1bN5ydnWnVqhXvv/++Sr4ZM2bQtGlT6tevT3BwMIcOHWLlypXUr1+fd999l549e6rUqSg++OADDh8+TEpKCikpKRw5coQPPvhALV+PHj3o3r07rq6u1KtXj3Xr1vH7779z/vx5Oc+qVau4fv06ISEhBAcHExERgZeXV6HnHzRoEAEBAVSvXp2wsDCSk5Pp168f/v7+eHh4MHr0aBISEopVJ4C6desyadIk3NzcCA8Px8DAAGtra4YMGYKbmxtTpkzhzp07/PbbbxqPv3//PtOnT8fExIRGjRrJ6WPGjKF79+44OTlRqVIlFixYQFhYGL1798bd3Z25c+dSr149tYl8Ro4cSY8ePfDw8GDlypWYm5vL972uri6RkZF4e3vj5OREv379GDRokNr9p6enx7p166hZsyYdO3Zk2rRpLF26VG6wF4eNjQ3wv57U3PdacHCwyo8H33//PU+ePCEgIEBjOZmZmTx8+FBly8zMLHY8gvC6uHf/ITk5SqwsVYeTWllW4Pbde6VyDqVSyZwlq6hfxxM3Z8dSKVMQ3mqSsnS2N4hoLAqvnCtXrpCVlUXTpk3lNF1dXRo1akRS0v9+jfX29i6wjAcPHnDz5k2VL+/a2trPbZAAKr2UCoUCOzs70tLS5LRNmzbRtGlT7OzsMDExYdKkSaSmpha5fi8SY2JiItra2vj6+ha5Dra2tvKQ2bxpeetUFDY2NnTs2JHo6GiioqLo2LEj1tbWavkuXbpEnz59cHZ2xszMDEdHRwCVa1ShQgXWrl3LypUrcXFxYfz48c89f/46AdSuXVsl7cmTJzx8+LBY9cpbrra2NlZWVmrlAmrXy8fHBxMTEypUqMDZs2fZtGmTnBdU78+HDx/y77//qtzTAE2bNlW5pwGaNGki/1tHRwdvb2+VPJ9//jleXl7Y2NhgYmLC6tWr1e6/unXrqvTSNmnShMePH3Pt2rXnX5AiCgwM5PLly/zyyy8AREdHExAQgLGxscb8s2fPxtzcXGWbu+SLUotHEN5GMxZ+zuW/kpkf+fzPUEEQhJIQ6ywKr62CvpS+KN18z4koFAq5R+bYsWP069ePyMhI/P39MTc3JzY2loULF5ZJLPnlDnd8nrx1UCgUhdapOIKCguShnp9//rnGPJ07d6ZatWqsWbOGypUro1QqqVWrlsoQTYCffvoJbW1trl+/Tnp6+nMnGspfp4LScuulpaWFJEkqZWh6tlTTtSms3FybNm3C09MTKysrjb3BZXF/xsbGEhoaysKFC2nSpAmmpqbMnz+f48ePl/q5nqdixYp07tyZqKgonJyciIuLK7RnNzw8nE8++UQlTevRP2UcpSCUnwoWZmhra3EnXy/inbv3sLbUPHlNccxcuIJDR08Q8/l87CravHB5giAAypzyjuCVI3oWhVeOi4sLenp6HDlyRE7Lysri5MmTeHp6FqkMc3NzbG1t5Ulx4NnkIKdPn36h2I4ePUq1atWYOHEi3t7euLm5kZKSUqKyShJj7dq1USqVKpOevEzt2rXj6dOnZGVl4e/vr7b/zp07XLhwgUmTJtGqVSs8PDy4d099uNXRo0eZO3cu33//PSYmJiV61vB5bGxsuH79ukpaaS7/YG9vj4uLS5GGNpuZmVG5cmWVexrgyJEjavd0bk8dPJsA6ddff8XDw0PO7+Pjw4gRI6hfvz6urq4qk/rkOnv2rMrMtb/88gsmJibY29sXp4rAsyGt8OzezG/w4MFs2rSJ1atX4+LiotZzmpe+vj5mZmYqm5hxVXiT6erq4unuxvFTiXKaUqnk+K+J1K3lUeJyJUli5sIVHPjpKOuWzqFqZbtSiFYQBEAMQ9VA9CwKrxxjY2OGDx/O2LFjsbS0xMHBgXnz5pGRkUFwcDBnz54tUjmjRo1i9uzZuLq6UqNGDZYtW8a9e/fknqKScHNzIzU1ldjYWBo2bMiuXbvYvl19HayiKm6Mjo6ODBw4kKCgIJYuXUrdunVJSUkhLS2twGfFSpO2trY8JFJbW1ttf4UKFbCysmL16tVUqlSJ1NRUtSGmjx49on///oSEhNC+fXuqVq1Kw4YN6dy5Mz179iy1WFu2bMn8+fP56quvaNKkCd988w1//PGH2uytL8vYsWOZOnUqLi4u1KtXj6ioKBITE1m/fr1Kvs8//xw3Nzc8PDxYtGgR9+7dkyeNcXNz46uvviI+Ph4nJye+/vprTp48Kc9Ymuvp06cEBwczadIkkpOTmTp1KiNHjkRLq/i/D1asWBFDQ0P27NlD1apVMTAwwNzcHAB/f3/MzMyYMWMG06ZNK+GVEYQ314D3uzFx5kJq1nCjlqc732zewX9PMunasQ0A4dMXUNHaio+HP5ssLCsriytXU///39ncvHWHPy9ewcjIEIeqlYFnQ09370tg6ZwpGBsZcvvOs4nfTEyMMRA/wAiCUMpEY1F4Jc2ZMwelUkn//v159OgR3t7exMfHU6FC0YfuhIWFcePGDQYMGIC2tjZDhw7F399fYyOnqLp06cLHH3/MyJEjyczMpGPHjkyePJmIiIgSlVeSGFeuXMmECRMYMWIEd+7cwcHBgQkTJpSwRsVnZmZW4D4tLS1iY2MJCQmhVq1auLu7s3TpUpXlKkaPHo2xsTGzZs0CnvWWzpo1i2HDhtGkSROqVKlSKnH6+/szefJkxo0bx5MnTwgKCmLAgAH8/vvvpVJ+cYWEhPDgwQM+/fRT0tLS8PT0ZOfOnbi5uankmzNnDnPmzCExMRFXV1d27twpPxs6bNgwzpw5w/vvv49CoaBPnz6MGDFCbWmPVq1a4ebmRvPmzcnMzKRPnz4lvkd1dHRYunQp06ZNY8qUKbz77rvycFMtLS0CAwOZNWsWAwYMKFH5gvAma9/al3v3H7D8y2+4ffcuNdxc+GLhdHkY6vWbaWjl+XEw7fZdeg7630iL6I1bid64Fe/6tYlePg+ATdt3ATBoZJjKuWZM+ERuhAqCUEJv2EympUEh5X+oRxDeUEqlEg8PDwICApg+fXp5h6PR6xCjIOQVHBzMrVu32LlzZ7GPzbr9VxlEJAiCILyJdK2dn5/pBWVe+eX5mYpA36VxqZTzKhA9i8IbKyUlhb179+Lr60tmZibLly/n6tWr9O3bt7xDk70OMQqCJg8ePOD3339nw4YNJWooCoIgCMIrR/QsqhGNReGNpaWlRXR0NKGhoUiSRK1atdi/f788WcjLYGJiUuC+uLg4HB0dyzXG1NTUQicNOn/+PA4ODi8lFuH18t5773HixAk+/PBD2rQRQ98EQRAE4U0khqEKQhm6fPlygfuqVKlS5KUwykp2djbJyckF7nd0dERHR/ymJJQNMQxVEARBKKqXMgz14uFSKUe/erNSKedVIL4FCkIZcnV1Le8QCqWjo/PKxyi8uXKSjjw/kyAIgiAAuu+WfWNRrLOoTqyzKAiCIAiCIAiCIKgRPYuCIAiCIAiCIAiSmOAmP9GzKAhvgIiICOrVq1esY/z8/BgzZky5x1GYsoixLCUkJKBQKLh//355hyIIgiAIQnEplaWzvUFEz6IgvAFCQ0MZNWpUsY7Ztm0burq6ZRTRmyEwMJD79++zY8eOIuX38fHh+vXrmJubv/A5FHkW6s5r48aN9O7du8jlC4JQvmJ/PEVM/DFuP3hMdXtbxvfxp7ZzFY15L/9zixXfHSIp5Tr/3nnA2Pfb8EGbd1Ty/Hoxheg9v5CUcp1bDx6z6KNetKzv/jKqIgjCW0j0LArCa0ySJLKzszExMcHKyqpYx1paWmJqalpGkb2d9PT0sLOzK7ChV1xRUVFcv35dZevatWuplF2QrKysMi1fEN4me06cY8HmfQzr/C6xUwbjbm/L8MUbufMwXWP+J0+zqGpjQUiPlliba1566b/MLNztKxLer11Zhi4IbydJWTrbG0Q0FgXhFZOZmUlISAgVK1bEwMCAZs2acfLkSeB/wxzj4uLw8vJCX1+fw4cPqw3/zM7OJiQkBAsLC6ysrAgLC2PgwIEqDY38QzwdHR2ZNWsWQUFBmJqa4uDgwOrVq1ViCwsLo3r16hgZGeHs7MzkyZNL3LgoSoyark1YWBj29vbo6+vj6urK2rVrVa5NfHw89evXx9DQkJYtW5KWlkZcXBweHh6YmZnRt29fMjIyShRzYa9N3hhyh6FGR0djYWFBfHw8Hh4emJiY0K5dO65fvw48G7YbExPDd999h0KhQKFQkJCQIJdnYWGBnZ2dymZgYFCksnN9+eWXeHh4YGBgQI0aNVixYoW8Lzk5GYVCwaZNm/D19cXAwID169c/97X56quvsLKyIjMzU+VcXbt2pX///iW6toLwJvp633G6v1ufrs3q4VLZhkkfdMBAT5cdhxM15q/lVJlPerWmfaOa6Oloa8zTrLYrI7u1oFWDGmUYuSC8pcQwVDWisSgIr5hx48axdetWYmJiOH36NK6urvj7+3P37l05z/jx45kzZw5JSUnUqVNHrYy5c+eyfv16oqKiOHLkCA8fPizSUMqFCxfi7e3NmTNnGDFiBMOHD+fChQvyflNTU6Kjozl//jxLlixhzZo1LFq0qET1LEmMAwYMYOPGjSxdupSkpCRWrVqFiYnqr+8REREsX76co0ePcu3aNQICAli8eDEbNmxg165d7N27l2XLlpUo5qK8NvllZGSwYMECvv76a3766SdSU1MJDQ0Fng0fDggIkBt5169fx8fHp8jxFFY2wPr165kyZQozZ84kKSmJWbNmMXnyZGJiYlTKGT9+PKNHjyYpKQl/f//nvja9evUiJyeHnTt3ymlpaWns2rWLoKCgIscvCG+yrOwcklKu09jTSU7T0lLQ2MOR3/76pxwjEwRBKDrxzKIgvELS09NZuXIl0dHRtG/fHoA1a9awb98+1q5dS8OGDQGYNm0abdq0KbCcZcuWER4eTrdu3QBYvnw5u3fvfu75O3TowIgRI4BnvYiLFi3i4MGDuLs/ex5m0qRJcl5HR0dCQ0OJjY1l3Lhxxa5rcWO8ePEimzdvZt++fbRu3RoAZ2f1NZdmzJhB06ZNAQgODiY8PJwrV67IeXv27MnBgwcJCwsrVrzPe23Gjh2r8bisrCy++OILXFxcABg5ciTTpk0DwMTEBENDQzIzM7Gzs1M7tk+fPmhrq/YunD9/HgcHh+eWDTB16lQWLlxI9+7dAXBycuL8+fOsWrWKgQMHyvnGjBkj54HnvzaGhob07duXqKgoevXqBcA333yDg4MDfn5+Gq9DZmamWk+k9DQLfT3x3KzwZrr3OIMcpYSVmbFKupWZCVdv3CmnqARBKIwkiXUW8xONRUF4hVy5coWsrCy5sQOgq6tLo0aNSEpKkhuL3t7eBZbx4MEDbt68SaNGjeQ0bW1tvLy8UD5naETeXkqFQoGdnR1paWly2qZNm1i6dClXrlzh8ePHZGdnY2ZmVux6liTGxMREtLW18fX1LXIdbG1t5SGzedNOnDhR7Jif99oUxMjISG7MAVSqVEnlmhZm0aJFcsM4V+XKlYtUdnp6OleuXCE4OJghQ4bIebKzs9Um4Ml7PxX1tRkyZAgNGzbkn3/+oUqVKkRHRxMYGFjg85qzZ88mMjJSJW1iYFcmBXXXmF8QBEEQXro37HnD0iAai4LwGjI2Nn5+phLIPzuqQqGQGwjHjh2jX79+REZG4u/vj7m5ObGxsSxcuLBMYsnP0NCwSPny1kGhUBRap5dB0/klSSrSsXZ2dri6upao7MePHwPPej/feUd1NsX8vZUluZ/q169P3bp1+eqrr2jbti3nzp1j165dBeYPDw/nk08+UUmTTm4p9nkF4XVRwcQIbS2F2mQ2dx4+LnDyGkEQytkb9rxhaRDPLArCK8TFxQU9PT2OHDkip2VlZXHy5Ek8PT2LVIa5uTm2trYqE6/k5ORw+vTpF4rt6NGjVKtWjYkTJ+Lt7Y2bmxspKSklKqskMdauXRulUsmhQ4dKdM4XVRqvjSZ6enrk5JT+sBdbW1sqV67MX3/9haurq8rm5ORU4HHFeW0GDx5MdHQ0UVFRtG7dGnt7+wLL1dfXx8zMTGUTQ1CFN5mujjYe1SpxPOmqnKZUShz/M5k6BSydIQiC8KoRPYuC8AoxNjZm+PDhjB07FktLSxwcHJg3bx4ZGRkEBwdz9uzZIpUzatQoZs+ejaurKzVq1GDZsmXcu3fvhZZ0cHNzIzU1ldjYWBo2bMiuXbvYvn17icsrboyOjo4MHDiQoKAgli5dSt26dUlJSSEtLY2AgIASx1FUz3ttSsrR0ZH4+HguXLiAlZUV5ubmco/h/fv3uXHjhkp+U1PTIvcERkZGEhISgrm5Oe3atSMzM5NTp05x7949tV6+vIr62vTt25fQ0FDWrFnDV199VcyaC8Kbr3+bd5i8bic1q1WillMVvtl/nP8ys+jatC4AE9d+R0ULU0b3aAk8mxTnyr+35H+n3X/En6k3MNLXw8HWEoCMJ09JTfvfpFr/3LrPn6k3MDc2pJJV0dd4FQRBAzEMVY1oLArCK2bOnDkolUr69+/Po0eP8Pb2Jj4+ngoVKhS5jLCwMG7cuMGAAQPQ1tZm6NCh+Pv7qw0/LI4uXbrw8ccfM3LkSDIzM+nYsSOTJ08mIiKiROWVJMaVK1cyYcIERowYwZ07d3BwcGDChAklrNHzKZVKdHT+9zFZGq9NfkOGDCEhIQFvb28eP37MwYMH5UliBg0apJZ/9uzZjB8/vkhlDx48GCMjI+bPn8/YsWMxNjamdu3aKkumaFLU18bc3JwePXqwa9euMl//URBeR+0a1eTe4wxWfHeI2w/Tcbe3ZcWYPlj9/zDUG3ceoJXnR5i0+494f9qX8t8x8b8QE/8L3tUdWDtuAADnkv9l8IJv5DwLNu8DoItPHaYHdXkZ1RKEN5dSTHCTn0Iq6sMzgiC8tpRKJR4eHgQEBDB9+vTyDkejVzHGdu3a4erqyvLly8s7lHJV2GvTqlUratasydKlS4td7pOfvy6tEAVBEIQ3nMG7Zb+O75OTW0ulHIOGPUqlnFeB6FkUhDdQSkoKe/fuxdfXl8zMTJYvX87Vq1fp27dveYcme5VjvHfvHkeOHCEhIYEPP/ywvMN56Yry2ty7d4+EhAQSEhJYsWJFOUYrCIIgCKVEDENVIxqLgvAG0tLSIjo6mtDQUCRJolatWuzfvx8PD4+XFoOJScGz/cXFxeHo6FiuMaamphY4MU16ejoKhYLw8HDee++9lxLPq6Qo90/9+vW5d+8ec+fOldfhFARBEITXmpgNVY0YhioIQpm4fPlygfuqVKlS5KUwykp2djbJyckF7nd0dFR5XlEofWIYqiAIglBUL2UY6i+bSqUcg8bvl0o5rwLxTUgQhDJR2PqArwIdHZ1XPsY3Xc7h/eUdgiAIgvC6eAmNRTEMVZ1oLAqCIAiCIAiCIIhhqGq0yjsAQRAEQRAEQRAE4dUjehYFQRAEQRAEQRBEz6Ia0bMoCK+ZiIgI6tWrV6xj/Pz8nrsQ+8uIozBlEWNZSkhIQKFQcP/+/fIORRAEQRCEUiBJOaWyvUlEz6IgvGZCQ0MZNWpUsY7Ztm0burq6ZRTRmyEwMJD79++zY8eOIuX38fHh+vXrmJubv/A5FAqFxvwbN26kd+/eL1S2IAivHp0GrdB9pz0KE3OUadd4uvcblNf/0phXYV0FvXe7oWXniJaFDZn715N9cu9LjlgQ3hKiZ1GNaCwKwmtCkiRycnIwMTEpdA1DTSwtLcsoqreXnp4ednZ2pVZeVFQU7dq1U0mzsLAotfJzZWVliR8OBKEcaXs0Qq9VH57uiSHn3yvoNvTH4P1QMlaHQcYjtfwKXT2U92+R/edJ9Fr3LYeIBUF4m4lhqIJQjjIzMwkJCaFixYoYGBjQrFkzTp48CfxvmGNcXBxeXl7o6+tz+PBhteGf2dnZhISEYGFhgZWVFWFhYQwcOJCuXbvKefIP8XR0dGTWrFkEBQVhamqKg4MDq1evVoktLCyM6tWrY2RkhLOzM5MnTyYrK6tE9SxKjJquTVhYGPb29ujr6+Pq6sratWtVrk18fDz169fH0NCQli1bkpaWRlxcHB4eHpiZmdG3b18yMjJKFHNhr03eGHKHoUZHR2NhYUF8fDweHh6YmJjQrl07rl+/DjwbthsTE8N3332HQqFAoVCQkJAgl2dhYYGdnZ3KZmBg8EJlJycno1Ao2LRpE76+vhgYGLB+/XqUSiXTpk2jatWq6OvrU69ePfbs2SPHkntcbGwsPj4+GBgYUKtWLQ4dOgQ8++HC1dWVBQsWqFyzxMREFApFoWtsCsLbTrdRO7LPHiL795+R7vzL0z3RSNlP0a3TXGN+5fWrZB3cRE7Sccgu2WewIAhFJClLZ3uDiMaiIJSjcePGsXXrVmJiYjh9+jSurq74+/tz9+5dOc/48eOZM2cOSUlJ1KlTR62MuXPnsn79eqKiojhy5AgPHz4s0lDEhQsX4u3tzZkzZxgxYgTDhw/nwoUL8n5TU1Oio6M5f/48S5YsYc2aNSxatKhE9SxJjAMGDGDjxo0sXbqUpKQkVq1apdajGhERwfLlyzl69CjXrl0jICCAxYsXs2HDBnbt2sXevXtZtmxZiWIuymuTX0ZGBgsWLODrr7/mp59+IjU1ldDQUODZ8OGAgAC5kXf9+nV8fHyKHM+LlD1+/HhGjx5NUlIS/v7+LFmyhIULF7JgwQJ+++03/P396dKlC5cuXVI559ixY/n00085c+YMTZo0oXPnzty5cweFQkFQUBBRUVEq+aOiomjevLlYv1IQCqKljZadIzlXz+VJlMhJPodWFfG+EYRyp1SWzvYGEY1FQSgn6enprFy5kvnz59O+fXs8PT1Zs2YNhoaGcg8awLRp02jTpg0uLi4ah5MuW7aM8PBwunXrRo0aNVi+fHmRhi926NCBESNG4OrqSlhYGNbW1hw8eFDeP2nSJHx8fHB0dKRz586EhoayefPmEtW1uDFevHiRzZs3s27dOrp164azszOtWrXi/fffV8k3Y8YMmjZtSv369QkODubQoUOsXLmS+vXr8+6779KzZ0+VOhVVUV+b/LKysvjiiy/w9vamQYMGjBw5kgMHDgBgYmKCoaEh+vr6cs+hnp6efGyfPn3kIca5W2pqaqmUPWbMGLp3746TkxOVKlViwYIFhIWF0bt3b9zd3Zk7dy716tVj8eLFKvUZOXIkPXr0wMPDg5UrV2Jubi7XPzAwkAsXLnDixAk5vg0bNhAUFKTx2mRmZvLw4UOVLTP7zZoEQBCeR2FkikJLGynjgUq6lP4AhUnRn38WBEF4WURjURDKyZUrV8jKyqJp06Zymq6uLo0aNSIpKUlO8/b2LrCMBw8ecPPmTRo1aiSnaWtr4+Xl9dzz5+2lVCgU2NnZkZaWJqdt2rSJpk2bYmdnh4mJCZMmTVJpvBRVSWJMTExEW1sbX1/fItfB1tZWHjKbNy1vnYqqqK9NfkZGRri4uMh/V6pUqcjnX7RoEYmJiSpb5cqVS6XsvPfQw4cP+ffff1XqBtC0aVO1ujVp0kT+t46ODt7e3nKeypUr07FjR9atWwfA999/T2ZmJr169dIYw+zZszE3N1fZFiT8XqT4BUEQBOGlEMNQ1YjGoiC84oyNjcuk3PyTnCgUCpT/P3Ti2LFj9OvXjw4dOvDDDz9w5swZJk6cyNOnT8sklvwMDQ2LlC9vHRQKRaF1ehk0nV+SpCIda2dnh6urq8qmo/O/OchepOyyuocGDx5MbGws//33H1FRUbz//vsYGRlpzBseHs6DBw9UtlC/2mUSlyC8qqSMR0jKHBRGqr2ICmNzpMcPCjhKEISXRgxDVSMai4JQTlxcXNDT0+PIkSNyWlZWFidPnsTT07NIZZibm2Nra6sy8UpOTg6nT59+odiOHj1KtWrVmDhxIt7e3ri5uZGSklKiskoSY+3atVEqlfKEKi9babw2mujp6ZGTUzZDL4tatpmZGZUrV1apG8CRI0fU6vbLL7/I/87OzubXX3/Fw8NDTuvQoQPGxsasXLmSPXv2FDgEFUBfXx8zMzOVTV9Hu6jVE4Q3gzIH5Y1ktB3zvtcUaFfzRPmPmBhKEIRXj1g6QxDKibGxMcOHD2fs2LFYWlri4ODAvHnzyMjIIDg4mLNnzxapnFGjRjF79mxcXV2pUaMGy5Yt4969ewWu3VcUbm5upKamEhsbS8OGDdm1axfbt28vcXnFjdHR0ZGBAwcSFBTE0qVLqVu3LikpKaSlpREQEFDiOIrqea9NSTk6OhIfH8+FCxewsrLC3Nxc7jG8f/8+N27cUMlvampa5F5BTWUXZOzYsUydOhUXFxfq1atHVFQUiYmJrF+/XiXf559/jpubGx4eHixatIh79+6pNAi1tbUJDAwkPDwcNzc3lWGrgiBolnViD/qdhqC8cZWcf/9Ct6E/Cl19sn77GQC9TkORHt0j69C3zw7Q0kbLusqzf2vroDCpgFZFB6SsJ0j3ij/MXhCEQrxhQ0hLg2gsCkI5mjNnDkqlkv79+/Po0SO8vb2Jj4+nQoUKRS4jLCyMGzduMGDAALS1tRk6dCj+/v5oa5e816ZLly58/PHHjBw5kszMTDp27MjkyZOJiIgoUXkliXHlypVMmDCBESNGcOfOHRwcHJgwYUIJa/R8SqVSZdhnabw2+Q0ZMoSEhAS8vb15/PgxBw8exM/PD4BBgwap5Z89ezbjx48vcdmOjo4a84aEhPDgwQM+/fRT0tLS8PT0ZOfOnbi5uankmzNnDnPmzCExMRFXV1d27tyJtbW1Sp7g4GBmzZqlMX5BENTlJJ3gqZEZuu92R8/YHGVaKk82L4CMhwBomVmizPOFVWFaAcPg6fLfeo07QOMO5KQk8WTDnJcevyC80d6wIaSlQSEV9aEXQRBeC0qlEg8PDwICApg+ffrzDygHr2KM7dq1w9XVleXLl5d3KOUuOTkZJycnzpw5o7KmpyY///wzrVq14tq1a9ja2hbrPOmzB75AlIIgCMLbxDg8pszP8V/c0lIpx7B9SKmU8yoQPYuC8JpLSUlh7969+Pr6kpmZyfLly7l69Sp9+/Yt79Bkr3KM9+7d48iRIyQkJPDhhx+WdzivjczMTG7dukVERAS9evUqdkNREARBEF45omdRjWgsCsJrTktLi+joaEJDQ5EkiVq1arF//36ViUjKmomJSYH74uLicHR0LNcYU1NTC5yYJj09HYVCQXh4OO+9995LiedNsHHjRoKDg6lXrx5fffVVeYcjCIIgCC9OPLOoRgxDFQThhV2+XPAsflWqVCnyUhhlJTs7m+Tk5AL3Ozo6qjyvKLwcYhiqIAiCUFQvZRjqzgWlUo5hl9BiH/P5558zf/58bty4Qd26dVm2bJnKGtV5nTt3jilTpvDrr7+SkpLCokWLGDNmjEqen376ifnz5/Prr79y/fp1tm/fTteuXYsdl/h2JAjCC3N1dS3vEAqlo6Pzysf4NspJvvH8TIIgCILwhtu0aROffPIJX3zxBe+88w6LFy/G39+fCxcuULFiRbX8GRkZODs706tXLz7++GONZaanp1O3bl2CgoLo3r17iWMTjUVBEARBEARBEIRyGob62WefMWTIEHlm8S+++IJdu3axbt06jbOiN2zYkIYNGwIUOGt6+/btad++/QvHJhqLgiAIgiAIgiAIpTTBTWZmJpmZmSpp+vr66Ovrq+V9+vQpv/76K+Hh4XKalpYWrVu35tixY6USz4vQKu8ABEEouoiIiOcuZZCfn5+f2jj28oijMGURoyAIgiAIQnmYPXs25ubmKtvs2bM15r19+zY5OTlqs4rb2tpy40b5P64hGouC8BoJDQ3lwIEDxTpm27Ztr8xahq+qW7duMXz4cBwcHNDX18fOzg5/f3+OHDlS5ucODAxEoVCobe3atStyGQkJCSgUCu7fv192gQqCUGp0/TpjMjMG0+XfYzx+CVqO7gXm1apUDcNhkzGZGYPZqnj0WnV7iZEKwltGUpbKFh4ezoMHD1S2vD2HrxMxDFUQXgOSJJGTk4OJiUmhy1RoYmlpWUZRvTl69OjB06dPiYmJwdnZmZs3b3LgwAHu3LnzUs7frl07oqKiVNI0DVV5UU+fPkVPT6/UyxUEoeh0vH0x6DmUJxuWkXP1T/RadcM4ZCaPpwYjPXqgfoCePsrb18n69ScMAoa9/IAF4W1SSsNQCxpyqom1tTXa2trcvHlTJf3mzZvY2dmVSjwvQvQsCkI5yczMJCQkhIoVK2JgYECzZs04efIk8L+eori4OLy8vNDX1+fw4cNqwz+zs7MJCQnBwsICKysrwsLCGDhwoMrUyPmHeDo6OjJr1iyCgoIwNTXFwcGB1atXq8QWFhZG9erVMTIywtnZmcmTJ5OVlVWiehYlRk3XJiwsDHt7e/T19XF1dWXt2rUq1yY+Pp769etjaGhIy5YtSUtLIy4uDg8PD8zMzOjbty8ZGRnPje/+/fv8/PPPzJ07lxYtWlCtWjUaNWpEeHg4Xbp0ASA5ORmFQkFiYqLKcQqFgoSEhBeOK7c3M+9WoUIFeb9CoeDLL7+kW7duGBkZ4ebmxs6dO+XYWrRoAUCFChVQKBQEBgYCz177kSNHMmbMGKytrfH39wfg0KFDNGrUCH19fSpVqsT48ePJzs6Wz5d73MiRIzE3N8fa2prJkyeTu9LStGnTqFWrltq1rFevHpMnT37uNReEt5l+6+5kHd5D1tG9KK+n8mT9UqSnmej6+GvMr0y5SObWL8k+dQhK+DksCMKrS09PDy8vL5WRY0qlkgMHDtCkSZNyjOwZ0VgUhHIybtw4tm7dSkxMDKdPn8bV1RV/f3/u3r0r5xk/fjxz5swhKSmJOnXqqJUxd+5c1q9fT1RUFEeOHOHhw4fs2LHjuedeuHAh3t7enDlzhhEjRjB8+HAuXLgg7zc1NSU6Oprz58+zZMkS1qxZw6JFi0pUz5LEOGDAADZu3MjSpUtJSkpi1apVaj2qERERLF++nKNHj3Lt2jUCAgJYvHgxGzZsYNeuXezdu5dly5Y9N77c3todO3aoPYxeEqUVV36RkZEEBATw22+/0aFDB/r168fdu3ext7dn69atAFy4cIHr16+zZMkS+biYmBj09PQ4cuQIX3zxBf/88w8dOnSgYcOGnD17lpUrV7J27VpmzJihcr6YmBh0dHQ4ceIES5Ys4bPPPuPLL78EICgoiKSkJPnHDYAzZ87w22+/yTO5CYKggbYOWg5uZCed/l+aJJH95xm0nT3LLy5BEJ5RKktnK6ZPPvmENWvWEBMTQ1JSEsOHDyc9PV3+P3XAgAEqw1ifPn1KYmIiiYmJPH36lH/++YfExESVda8fP34s5wG4evUqiYmJpKamFis2MQxVEMpBeno6K1euJDo6Wp7WeM2aNezbt4+1a9fK0yFPmzaNNm3aFFjOsmXLCA8Pp1u3Z8+wLF++nN27dz/3/B06dGDEiBHAs17ERYsWcfDgQdzdnz03M2nSJDmvo6MjoaGhxMbGMm7cuGLXtbgxXrx4kc2bN7Nv3z5at24NgLOzs1q+GTNm0LRpUwCCg4MJDw/nypUrct6ePXty8OBBwsLCCo1PR0eH6OhohgwZwhdffEGDBg3w9fWld+/eGhvoz1OSuH744Qe1xvCECROYMGGC/HdgYCB9+vQBYNasWSxdupQTJ07Qrl07eahxxYoVsbCwUCnHzc2NefPmyX9PnDgRe3t7li9fjkKhoEaNGvz777+EhYUxZcoUtLSe/YZob2/PokWLUCgUuLu78/vvv7No0SKGDBlC1apV8ff3JyoqSr5Xo6Ki8PX11fhageaZ4TJzlOhri98shbeHwsQMhbY20qP7KunSw3to29mXT1CCIPzP/4+gednef/99bt26xZQpU7hx4wb16tVjz5498qQ3qamp8v/PAP/++y/169eX/16wYAELFizA19dXHvF06tQpeeQRPGuQAgwcOJDo6Ogixyb+lxaEcnDlyhWysrLkRgWArq4ujRo1IikpSU7z9vYusIwHDx5w8+ZNGjVqJKdpa2vj5eX13PPnbQQpFArs7OxIS0uT0zZt2kTTpk2xs7PDxMSESZMmFfuXqJLGmJiYiLa2Nr6+vkWug62trTxkNm9a3joVpkePHvz777/s3LmTdu3akZCQQIMGDYr1YfoicbVo0UL+9S93+/DDDwss19jYGDMzsyLVL/+1TkpKokmTJigUCjmtadOmPH78mL///ltOa9y4sUqeJk2acOnSJXJycgAYMmQIGzdu5MmTJzx9+pQNGzYQFBRUYByaZob77Mxfz41fEARBEN4GI0eOJCUlhczMTI4fP84777wj70tISFD5TuLo6IgkSWpbbkMRnj1SoilPcb/biMaiILzCjI2Ny6RcXV1dlb8VCgXK/x82cezYMfr160eHDh344YcfOHPmDBMnTuTp06dlEkt+hoaGRcqXtw4KhaLQOhWFgYEBbdq0YfLkyRw9epTAwECmTp0KIP+aJ+X5xbGgZzhLEpexsTGurq4qW/6JiUpav7K6hzp37oy+vj7bt2/n+++/Jysri549exaYX9PMcJ/U19wLKQhvKunxQ6ScHBSmFirpCrMKKB/cK5+gBEH4n3IahvoqE41FQSgHLi4u8nNkubKysjh58iSenkV7bsXc3BxbW1uV58ZycnI4ffp0IUc939GjR6lWrRoTJ07E29sbNzc3UlJSSlRWSWKsXbs2SqWSQ4cOleicpcXT05P09HQAbGxsALh+/bq8P+9kN+Utd4bT3F6/wnh4eHDs2DGVhu+RI0cwNTWlatWqctrx48dVjvvll19wc3NDW1sbeDZ8d+DAgURFRREVFUXv3r0Lbejr6+tjZmamsokhqMJbJycbZeoldDz+N3wMhQKdGvXI+et8+cUlCMIzorGoRjyzKAjlwNjYmOHDhzN27FgsLS1xcHBg3rx5ZGRkEBwczNmzZ4tUzqhRo5g9ezaurq7UqFGDZcuWce/ePZXhg8Xl5uZGamoqsbGxNGzYkF27drF9+/YSl1fcGB0dHRk4cCBBQUEsXbqUunXrkpKSQlpaGgEBASWOoyB37tyhV69eBAUFUadOHUxNTTl16hTz5s3jvffeA571djZu3Jg5c+bg5OREWlqaynOdLyozM1Nt4V0dHR2sra2LdHy1atVQKBT88MMPdOjQAUNDwwKXWBkxYgSLFy9m1KhRjBw5kgsXLjB16lQ++eQTlechUlNT+eSTTxg2bBinT59m2bJlLFy4UKWswYMH4+HhAfBS1qQUhDdB5v5tGAaGkpN8kZzkC+i16oZCz4Cso3sBMAgci3T/Npk7/n85HW0dtCo5PPu3ji4KCyu0qjojZT5BuvVvOdVCEN5Q0pvV0CsNorEoCOVkzpw5KJVK+vfvz6NHj/D29iY+Pl5lyYTnCQsL48aNGwwYMABtbW2GDh2Kv7+/3PtTEl26dOHjjz9m5MiRZGZm0rFjRyZPnkxERESJyitJjCtXrmTChAmMGDGCO3fu4ODgoDLZS2kyMTHhnXfeYdGiRfKzpPb29gwZMkTlnOvWrSM4OBgvLy/c3d2ZN28ebdu2LZUY9uzZQ6VKlVTS3N3d+fPPP4t0fJUqVYiMjGT8+PEMGjSIAQMGFPhMQpUqVdi9ezdjx46lbt26WFpaEhwcrNb4HTBgAP/99x+NGjVCW1ub0aNHM3ToUJU8bm5u+Pj4cPfuXZVnKwRBKFj2qUM8MTFHv8uAZ8NP//6LjKUT5UlvtCxtUOb5wqqwsMJk8kr5b/22vdBv24vsC2fJ+Kz4k44JgiAUh0KSymnaH0EQSp1SqcTDw4OAgACmT59e3uFo9DrE+Lbz8/OjXr16LF68uNB8kiTh5ubGiBEj5FnWiuPhMM3rygmCIAhCfmar4sv8HP99Ff78TEVgOGB2qZTzKhA9i4LwGktJSWHv3r34+vqSmZnJ8uXLuXr1Kn379i3v0GSvQ4xC8d26dYvY2Fhu3Lgh1lYUBEEQ3gyiD02NaCwKwmtMS0uL6OhoQkNDkSSJWrVqsX//fvk5spehoGfjAOLi4nB0dCzXGFNTUwudNOj8+fM4ODi8lFjeJBUrVsTa2prVq1cXa+i0IAiCIAivD9FYFITXmL29fblPLFLYrKBVqlTB0NCwXGOsXLlyoTFWrlz55QXzmsi7TlNBxBMMgiAIwhvnDZvJtDSIxqIgCC/E1dW1vEMolI6Ozisf49tqxR6b8g5BEARBeE2MfxknEY1FNWKRK0EQBEEQBEEQBEGN6FkUBEEQBEEQBEEQ6yyqEY1FQRAEQRAEQRDeepJSPI+fn2gsCsJrICIigh07dhQ6UUt+RV0rr6zjKExZxCgIglCeGgxozTtDO2JsY05aUir7pn7F9bN/FZjfvUMjmn/aE/Oq1txNvknCnFj+OnhW3q9rpI/f+Pdxa+uNYQUTHly7xamoeBLX/yjnqdunBTXf88G2liP6poYsqj2UzIcZZVpPQXgjiWcW1YhnFgXhNRAaGsqBAweKdcy2bdvEovfPcevWLYYPH46DgwP6+vrY2dnh7+//UmZvLc9zC4JQNmp0eoeWk/pxeMl2ojpNIi0plfe/DsPIykxj/ipebry37CPObj5EVMdJXNr7Kz1Wf4x19apynlaT++HsW5cfxqzky1bjOLl2D22nDcS1dQM5j66hHn8d+o1jn+8s8zoKgvB2ET2LgvAKkySJnJwcTExMCl3PUBNLS8syiurN0aNHD54+fUpMTAzOzs7cvHmTAwcOcOfOnTf63M/z9OlT9PT0yjsMQXjtNBrcnrOxB/n9258A2DMhCpeW9agT4MsvK79Xy+89yJ+/Dv3GiVW7APh54RYcm9XCa2Ab4idGAc8alL9v/ZnUX5IAOLvxIPX7taRSPWcu7z8NwKl18QA4NH55a+wKwhtJPLOoRvQsCsJLlpmZSUhICBUrVsTAwIBmzZpx8uRJ4Nn6dgqFgri4OLy8vNDX1+fw4cNERERQr149uYzs7GxCQkKwsLDAysqKsLAwBg4cSNeuXeU8fn5+jBkzRv7b0dGRWbNmERQUhKmpKQ4ODqxevVoltrCwMKpXr46RkRHOzs5MnjyZrKysEtWzKDFqujZhYWHY29ujr6+Pq6sra9euVbk28fHx1K9fH0NDQ1q2bElaWhpxcXF4eHhgZmZG3759ych4/vCr+/fv8/PPPzN37lxatGhBtWrVaNSoEeHh4XTp0gWA5ORkFAqFyrDb+/fvo1Ao5LUISxJXUc4NcOnSJZo3b46BgQGenp7s27cPhULBjh07VM59//59+ZjExEQUCgXJyckA3Llzhz59+lClShWMjIyoXbs2GzduVLkWfn5+jBw5kjFjxmBtbY2/vz8Af/zxB+3bt8fExARbW1v69+/P7du35eO2bNlC7dq1MTQ0xMrKitatW5Oenv7cay8IbyItXW3sajuRfPjc/xIlieTD56jSQPPyPZUbuJJ8+A+VtKs//aaS/59fL+HWugEmthUAcGjiQQUnO5J/+r30KyEIbzulVDrbG0Q0FgXhJRs3bhxbt24lJiaG06dP4+rqir+/P3fv3pXzjB8/njlz5pCUlESdOnXUypg7dy7r168nKiqKI0eO8PDhQ7kBUZiFCxfi7e3NmTNnGDFiBMOHD+fChQvyflNTU6Kjozl//jxLlixhzZo1LFq0qET1LEmMAwYMYOPGjSxdupSkpCRWrVql1qMaERHB8uXLOXr0KNeuXSMgIIDFixezYcMGdu3axd69e1m2bNlz48vtrd2xYweZmZklqmNJ4yrKuZVKJd27d0dPT4/jx4/zxRdfEBYWVuy4njx5gpeXF7t27eKPP/5g6NCh9O/fnxMnTqjki4mJQU9PjyNHjvDFF19w//59WrZsSf369Tl16hR79uzh5s2bBAQEAHD9+nX69OlDUFAQSUlJJCQk0L17dyTpzfpPUhCKyqiCKVo62qTffqCSnn77AcY25hqPMbGxIP32w3z5H2JsYyH/vW/qV9y+9A8jTyxj7OVoAmLGsW9yDNdOXEAQBKGsiWGogvASpaens3LlSqKjo2nfvj0Aa9asYd++faxdu5aGDRsCMG3aNNq0aVNgOcuWLSM8PJxu3boBsHz5cnbv3v3c83fo0IERI0YAz3oRFy1axMGDB3F3dwdg0qRJcl5HR0dCQ0OJjY1l3Lhxxa5rcWO8ePEimzdvZt++fbRu3RoAZ2dntXwzZsygadOmAAQHBxMeHs6VK1fkvD179uTgwYPPbVjp6OgQHR3NkCFD+OKLL2jQoAG+vr707t1bYwP9eYoTV1HOvX//fv7880/i4+OpXLkyALNmzZLvm6KqUqUKoaGh8t+jRo0iPj6ezZs306hRIzndzc2NefPmqdSnfv36zJo1S05bt24d9vb2XLx4kcePH5OdnU337t2pVq0aALVr1y4wjszMTLWGcbaUg45Cu1j1EYS3jVdgWyrXd2VL0EIe/HMb+3dq0Gb6QB7dvEfKkXPPL0AQhKITE9yoET2LgvASXblyhaysLLlRAaCrq0ujRo1ISkqS07y9vQss48GDB9y8eVPli762tjZeXl7PPX/eRpBCocDOzo60tDQ5bdOmTTRt2hQ7OztMTEyYNGkSqampRa7fi8SYmJiItrY2vr6+Ra6Dra2tPGQ2b1reOhWmR48e/Pvvv+zcuZN27dqRkJBAgwYNiI6OLtLxLxLX886dlJSEvb293FAEaNKkSbHjysnJYfr06dSuXRtLS0tMTEyIj49Xe13zvzZnz57l4MGDci+oiYkJNWrUAJ7dx3Xr1qVVq1bUrl2bXr16sWbNGu7du1dgHLNnz8bc3FxlS3ggvugKb46Me49QZudgbK3ai2hsbU76rQcaj3l86z7G1mb58puRfus+ADr6uviODeDHGeu5fOAMt/68xumYffz5w3HeGdqxTOohCG81pbJ0tjeIaCwKwivI2Ni4TMrV1dVV+VuhUKD8/w+1Y8eO0a9fPzp06MAPP/zAmTNnmDhxIk+fPi2TWPIzNDQsUr68dVAoFIXWqSgMDAxo06YNkydP5ujRowQGBjJ16lQAtLSefUTmHVpZ0DOcJYmrsHMXRVHimz9/PkuWLCEsLIyDBw+SmJiIv7+/2uua/557/PgxnTt3JjExUWXLfY5SW1ubffv2ERcXh6enJ8uWLcPd3Z2rV69qjDU8PJwHDx6obH7mNYtcV0F41Smzcrjx+1Ucm+a5rxUKqjWtyT+nL2s85t/Tl1XzA47v1pLza+nqoK2ng5Tvs0OZo0ShpSjdCgiCIGggGouC8BK5uLjIz4XlysrK4uTJk3h6ehapDHNzc2xtbeVJceBZ79Hp06dfKLajR49SrVo1Jk6ciLe3N25ubqSkpJSorJLEWLt2bZRKJYcOHSrROUuLp6enPEmLjY0N8Oz5vFyltcbk887t4eHBtWvXVM79yy+/qOQvSnxHjhzhvffe44MPPqBu3bo4Oztz8eLF58bSoEEDzp07h6OjI66uripbbsNSoVDQtGlTIiMjOXPmDHp6emzfvl1jefr6+piZmalsYgiq8KY58WUcdXv7UavHu1i5VsZ/5iD0jPT57dtnn2udPhuG77gAOf+pqHicfOvQaEh7LF0q0WxMdyrVdubXmH0APH38H6nHkmgxoQ8OjT0wt7ehds93qdWjGRfjT8nlGNuYU9HTAQtHWwBs3O2p6OmAgXnZ/PAoCG8sSSqd7Q0inlkUhJfI2NiY4cOHM3bsWCwtLXFwcGDevHlkZGQQHBzM2bNnn18Iz547mz17Nq6urtSoUYNly5Zx7949FIqS/9Ls5uZGamoqsbGxNGzYkF27dhX4xb8sYnR0dGTgwIEEBQWxdOlS6tatS0pKCmlpafKkKqXpzp079OrVi6CgIOrUqYOpqSmnTp1i3rx5vPfee8Cz3s7GjRszZ84cnJycSEtLU3musyzP3bp1a6pXr87AgQOZP38+Dx8+ZOLEiSrluLq6Ym9vT0REBDNnzuTixYssXLhQJY+bmxtbtmzh6NGjVKhQgc8++4ybN28+98eJjz76iDVr1tCnTx/GjRuHpaUlly9fJjY2li+//JJTp05x4MAB2rZtS8WKFTl+/Di3bt3Cw0NM3S+8vf784ThGVma8+0kPjG3MSTufwqYB88j4/0lszCpbI+WZKfGfXy+xM2QFzUN70XxsAPeSb7B16CJuX/xbzvPdqOX4jnufzkuGY2BhwsO/b/PT/G85883/1t6t368VzT7uLv/9wZbJAOz6dBW/b/m5rKstCG+ON2wIaWkQjUVBeMnmzJmDUqmkf//+PHr0CG9vb+Lj46lQoUKRywgLC+PGjRsMGDAAbW1thg4dir+/P9raJe+p6dKlCx9//DEjR44kMzOTjh07MnnyZCIiIkpUXkliXLlyJRMmTGDEiBHcuXMHBwcHJkyYUMIaFc7ExIR33nmHRYsWyc+S2tvbM2TIEJVzrlu3juDgYLy8vHB3d2fevHm0bdu2zM+tpaXF9u3bCQ4OplGjRjg6OrJ06VLatWsnl6Orq8vGjRsZPnw4derUoWHDhsyYMYNevXrJeSZNmsRff/2Fv78/RkZGDB06lK5du/LggeZnqHJVrlyZI0eOEBYWRtu2bcnMzKRatWq0a9cOLS0tzMzM+Omnn1i8eDEPHz6kWrVqLFy4sNgT8AjCm+Z0zD5O/3/PYH4bes9US7uw+wQXdp/QkPuZ9FsP2D12dYH7AQ4v3sbhxduKF6ggCEIRKCQxz7kgvPaUSiUeHh4EBAQwffr08g5Ho9chxteBQqFg+/btha5X+bqYU+2D8g5BEARBeE2MT/mmzM+RsWBwqZRjFPplqZTzKhA9i4LwGkpJSWHv3r34+vqSmZnJ8uXLuXr1Kn379i3v0GSvQ4yCIAiCIAgySQxDzU80FgXhNaSlpUV0dDShoaFIkkStWrXYv3//S31ezMTEpMB9cXFxODo6lmuMqamphT6Xd/78eRwcHF5KLIIgCIIgvAaUYsBlfqKxKAivIXt7e5UZVctDYbOCVqlSBUNDw3KNsXLlyoXGmHf9wteJeHJAEARBEISXRTQWBUEoEVdX1/IOoVA6OjqvfIxvu38VmtesFARBEITykH9NU0E0FgVBEARBEARBEMQwVA20yjsAQRAEQRAEQRAE4dUjGouFiIiIoF69esU6xs/PjzFjxpR7HIUpixhfluTkZBQKRaHPogkvX2BgoMpSDpIkMXToUCwtLcvl9UpISEChUHD//v2Xet5XRf73ycu4HqX9OSUIgiAIL52kLJ3tDSKGoRYiNDSUUaNGFeuYbdu2oaurW0YRvfmuXr3KxIkTSUhI4O7du1hbW+Pl5cXcuXOpUaMG9vb2XL9+HWtr61I5n6OjIykpKQXuT05Oplq1aqVyrqJQKBTo6+tz4cIFlfN27doVCwsLoqOjS+1cERER7NixQ60hl5ycjJOTE2fOnCnyl/8lS5aoTLyyZ88eoqOjSUhIwNnZudRer6Ly8fHh+vXrmJubAxAdHc2YMWOK3ViKiIggMjKSYcOG8cUXX8jpiYmJ1K9fn6tXr+Lo6FiKkZeN/NdDEISy827/trQc1hkzGwv+SUphy9QoUs9eKTB/vQ6N6fhpAJZVbbh19QY756znfEKivH9p8iaNx+2Y9Q0/rv4e18aehMRO1ZhnQZcJpP5W8LkFQchHDENVIxqLGkiSRE5ODiYmJoUuD6CJpaVlGUX15svKyqJNmza4u7uzbds2KlWqxN9//01cXJz8JV9bWxs7O7tSO+fJkyfJyclRSbt//z6tWrXCy8urXJZWUCgUTJkyhZiYmJd+7pLK3wi5cuUKlSpVwsfHp8Rl5r4PdXSK/zGlp6dXaveJgYEBa9eu5dNPP8XNza1UygR4+vQpenp6pVZeYUrzegiCULD6nZrQbdIANk36kpQzl/AN6sCIryYwo+XHPL7zUC2/U4PqDFwawvfzNnLuwGm83mvK4NVjmd9pPNcvXgNgYsOhKsd4+tWnz9xhnI07DsDVXy+o5en4yftUb1pLNBQFQXhhb80w1MzMTEJCQqhYsSIGBgY0a9aMkydPAv8bohUXF4eXlxf6+vocPnxYbVhVdnY2ISEhWFhYYGVlRVhYGAMHDlQZfpd/iKejoyOzZs0iKCgIU1NTHBwcWL16tUpsYWFhVK9eHSMjI5ydnZk8eTJZWSWbJbAoMea3YsUK3NzcMDAwwNbWlp49ewL/G8qWf/Pz8wOe9dZYWFjwww8/4O7ujpGRET179iQjI4OYmBgcHR2pUKECISEhag0yTc6dO8eVK1dYsWIFjRs3plq1ajRt2pQZM2bQuHFjlZhye8MCAwM1xpiQkAA8e91DQ0OpUqUKxsbGvPPOO/I+ABsbG+zs7OStYsWKjBkzBnNzc9avX49CoQDg3r17DBgwgAoVKmBkZET79u25dOmSXE7utYiPj8fDwwMTExPatWvH9evXVer45Zdf4uHhgYGBATVq1GDFihVq12HkyJF88803/PHHHwVeq8LuZ/jfPX3gwAG8vb0xMjLCx8eHCxcuPPd1yK8odcs7DDUwMJBRo0aRmpqKQqGQe96KGnP+96Gfnx+jRo1izJgxVKhQAVtbW9asWUN6ejqDBg3C1NQUV1dX4uLi1Mq6f/8+CQkJDBo0iAcPHsj3R0REBNOmTaNWrVpq9a1Xrx6TJ0+W/3Z3d6dFixZMnDix0Ot06NAhGjVqhL6+PpUqVWL8+PFkZ2fL+/38/Bg5ciRjxozB2toaf39/Oc74+Hjq16+PoaEhLVu2JC0tjbi4ODw8PDAzM6Nv375kZGTIZe3Zs4dmzZrJ7/NOnTpx5UrBXwrzD0P18/PT+L5JTk4Gnv1gMnjwYGxsbDAzM6Nly5acPXtWpcw5c+Zga2uLqakpwcHBPHnypNDrIwhvgxaDO3I09gDHv03gxuV/2DzxS57+95TGAS005vcNak/SoUR+XP09N6/8w+7PNvP3uau8O9BfzvPo1gOVrXYbby4dO8eda2kA5GTlqOxPv/eY2m28Of5twsuosiC8WZTK0tneIG9NY3HcuHFs3bqVmJgYTp8+jaurK/7+/ty9e1fOM378eObMmUNSUhJ16tRRK2Pu3LmsX7+eqKgojhw5wsOHD9mxY8dzz71w4UK8vb05c+YMI0aMYPjw4Spf2k1NTYmOjub8+fMsWbKENWvWsGjRohLVs7gxnjp1ipCQEKZNm8aFCxfYs2cPzZs3B5CHfOZuZ86cwcrKSt4PkJGRwdKlS4mNjWXPnj0kJCTQrVs3du/eze7du/n6669ZtWoVW7ZseW7sNjY2aGlpsWXLliI1LuHZ8Me8MY4ePZqKFStSo0YN4FnD69ixY8TGxvLbb7/Rq1cv2rVrp9LQy2v8+PEcP36c7777DlNTUzk9MDCQU6dOsXPnTo4dO4YkSXTo0EGlUZ+RkcGCBQv4+uuv+emnn0hNTSU0NFTev379eqZMmcLMmTNJSkpi1qxZTJ48Wa0HsWnTpnTq1Inx48cXWO+i3M8AEydOZOHChZw6dQodHR2CgoKKdF3ze17d8lqyZAnTpk2jatWqXL9+XW4QFjVmTe/DmJgYrK2tOXHiBKNGjWL48OH06tULHx8fTp8+Tdu2benfv79KgyqXj48PixcvxszMTL5PQkNDCQoKIikpSaXBeubMGX777TcGDRqkUsacOXPYunUrp06d0ljnf/75hw4dOtCwYUPOnj3LypUrWbt2LTNmzFDJFxMTg56eHkeOHFEZ1hoREcHy5cs5evQo165dIyAggMWLF7NhwwZ27drF3r17WbZsmZw/PT2dTz75hFOnTnHgwAG0tLTo1q0byiL+B7Vt2zaV90337t1xd3fH1tYWgF69eskN1l9//ZUGDRrQqlUr+bXavHkzERERzJo1i1OnTlGpUiWNP3wIwttEW1cb+1rOXDjyu5wmSRIXjvyOUwPNoxIc61fn4hHVHwaTfjqLU4PqGvObWptTs0V9ftl0sMA4arf2wriCqWgsCkJJKKXS2d4gb8Uw1PT0dFauXEl0dDTt27cHYM2aNezbt4+1a9fSsGFDAKZNm0abNm0KLGfZsmWEh4fTrVs3AJYvX87u3bufe/4OHTowYsQI4Fkv4qJFizh48CDu7u4ATJo0Sc7r6OhIaGgosbGxjBs3rth1LW6MqampGBsb06lTJ0xNTalWrRr169cHVId8PnnyhK5du9KkSRMiIiLk47Oysli5ciUuLi4A9OzZk6+//pqbN29iYmKCp6cnLVq04ODBg7z//vuFxl6lShWWLl3KuHHjiIyMxNvbmxYtWtCvXz+cnZ01HmNubi4Pgdy2bRurVq1i//792NnZkZqaSlRUFKmpqfIC7KGhoezZs4eoqChmzZqlUtbGjRv57LPP2LVrl8pww0uXLrFz506OHDkiD6tcv3499vb27Nixg169esnX4osvvpCvxciRI5k2bZpcztSpU1m4cCHdu3cHwMnJifPnz7Nq1SoGDhyoEsvs2bOpU6cOP//8M++++67Kvufdz2PHjpXzzpw5E19fX+BZI6xjx448efIEAwODQl+L/J5Xt7zMzc0xNTVVuX+KE7Om92HdunXl90l4eDhz5szB2tqaIUOGADBlyhRWrlzJb7/9JvdC59LT08Pc3ByFQqEyFNPExAR/f3+ioqLkz4CoqCh8fX3V7rcGDRoQEBBAWFgYBw4cUKvzihUrsLe3Z/ny5SgUCmrUqMG///5LWFgYU6ZMQUvr2e9ybm5uzJs3Tz4ut3d2xowZNG3aFIDg4GDCw8O5cuWKHEfPnj05ePAgYWFhAPTo0UPl/OvWrcPGxobz589r7C3NL+9w+UWLFvHjjz9y/PhxDA0NOXz4MCdOnCAtLQ19fX0AFixYwI4dO9iyZQtDhw5l8eLFBAcHExwcLMe/f//+QnsXMzMzyczMVEnLkXLQVmg/N15BeB0YVzBDW0ebR7cfqKQ/uvUAW5fKGo8xs7Hg4e37avlNrTU/X9yohy9P0p9wNv5EgXE0fr8lST+d5f6NuwXmEQRBKKq3omfxypUrZGVlyV/GAHR1dWnUqBFJSUlymre3d4FlPHjwgJs3b9KoUSM5TVtbGy8vr+eeP28vZe4X1rS0NDlt06ZNNG3aFDs7O0xMTJg0aRKpqalFrt+LxNimTRuqVauGs7Mz/fv3Z/369Rp7Z4KCgnj06BEbNmyQv/gCGBkZyQ0IAFtbWxwdHVWe9bS1tVWpb2E++ugjbty4wfr162nSpAnffvstNWvWZN++fYUed+bMGfr378/y5cvl1/n3338nJyeH6tWry8+fmpiYcOjQIbUhe6dPnyY4OJg5c+bg7++vsi8pKQkdHR3eeecdOc3Kygp3d3eV+yf/tahUqZJc7/T0dK5cuUJwcLBKLDNmzNA4fNDT05MBAwZo7F0s6v0MqvdepUqVAIr8WuRVWN2Kojgxa3of5q2HtrY2VlZW1K5dW07L7RErbt2GDBnCxo0befLkCU+fPmXDhg0F9r7OmDGDn3/+mb1796rtS0pKokmTJvKwZXjWQ/z48WP+/vtvOa2g92Le+tna2spD0vOm5a3bpUuX6NOnD87OzpiZmclDfYv7uREXF8f48ePZtGkT1as/68k4e/Ysjx8/xsrKSuVevXr1qnyvJiUlqbwfAJo0aVLouWbPni3/uJO7nXqQVOgxgiCoahzgx6kdh8nO1PyoioWdJR7N6/LLph9fcmSC8IYQs6GqeSt6FovK2Ni4TMrNPzuqQqGQh4sdO3aMfv36ERkZib+/P+bm5sTGxrJw4cIyiSU/U1NTTp8+TUJCAnv37mXKlClERERw8uRJLCwsgGdfkuPj4zlx4oTK0MyC6lZYfYsaU+fOnencuTMzZszA39+fGTNmFNjre+PGDbp06cLgwYPlng6Ax48fo62tza+//oq2tmrvRd7G7K1bt+jWrRs9evQocGhlUWiqd+4MoY8fPwae9abl/5KdP7ZckZGRVK9evUhDnYsSU25DJve1MDMz48GDB2rH5D7XlnfSmsLqVto0vQ+fd5/lr1tRde7cGX19fbZv346enh5ZWVnyM7v5ubi4MGTIEMaPH8/atWuLdZ5cBX3G5K/L895DnTt3plq1aqxZs4bKlSujVCqpVasWT58+LXIs58+fp3fv3syZM4e2bdvK6Y8fP6ZSpUoqz/bmyv1MKInw8HA++eQT1bTaJRsWLQivovR7D8nJzlHrFTS1MefRrfsaj3l46z5m1hbq+W+rfzY7N6yBrUsVokYuKTCGd3r5kX7vEb/v/7XY8QuCwBs3hLQ0vBU9iy4uLvJzQrmysrI4efIknp6eRSrD3NwcW1tbleebcnJyOH369AvFdvToUapVq8bEiRPx9vbGzc2t0KUcyiJGHR0dWrduzbx58/jtt99ITk7mxx+f/Sq5detWpk2bxubNm1V6ll6W3CF96enpGvc/efKE9957jxo1avDZZ5+p7Ktfvz45OTmkpaXh6uqqsuUOR8xtHFSsWJE1a9ZoPIeHhwfZ2dkcP35cTrtz5w4XLlwo8v1ja2tL5cqV+euvv9RicXJy0niMvb09I0eOZMKECSrPcJbG/QzPJm75+++/uXnzpkr66dOnMTAwKNWZYEsr5pLS09PT+Bysjo4OAwcOJCoqiqioKHr37o2hoWGB5UyZMoWLFy8SGxurku7h4SE/y5rryJEjmJqaUrVq1dKrCP+79yZNmkSrVq3w8PDg3r17xSrj9u3bdO7cmR49evDxxx+r7GvQoAE3btxAR0dH7V7NXQLFw8ND5f0A8MsvvxR6Tn19fczMzFQ2MQRVeJPkZOVw7Y+/qO7zv1EPCoUCd59aXD2t+Tn55DMXqe6jOnS8RrPaXD19US1vk/dbkPrbFf5NKvg7wju9/Dix7SeU2UV77l8QBFWSUlkq25vkrehZNDY2Zvjw4YwdOxZLS0scHByYN28eGRkZBAcHq83yV5BRo0Yxe/ZsXF1dqVGjBsuWLePevXsqQ8+Ky83NjdTUVGJjY2nYsCG7du1i+/btJS6vuDH+8MMP/PXXXzRv3pwKFSqwe/dulEol7u7u/PHHHwwYMICwsDBq1qzJjRs3gGdfvMtiiZDExESmTp1K//798fT0RE9Pj0OHDrFu3Tr5Wa38hg0bxrVr1zhw4AC3bt2S0y0tLalevTr9+vVjwIABLFy4kPr163Pr1i0OHDhAnTp16NixI2PGjOHs2bPs379f4xp8lpaWuLm58d577zFkyBBWrVqFqakp48ePp0qVKrz33ntFrl9kZCQhISGYm5vTrl07MjMzOXXqFPfu3VPrcckVHh7OmjVruHr1qvzM5/Pu56Ly9/fH3d2dPn36MGPGDOzs7Dh9+jSTJk1i9OjRBfZ4lkRpxVxSjo6OPH78mAMHDlC3bl2MjIwwMjICYPDgwXh4eACoNGY1sbW15ZNPPmH+/Pkq6SNGjGDx4sWMGjWKkSNHcuHCBaZOnconn3yiMmy7NFSoUAErKytWr15NpUqVSE1NLXQyJE169OiBkZERERER8vsank0y1bp1a5o0aULXrl2ZN28e1atX599//2XXrl1069YNb29vRo8eTWBgIN7e3jRt2pT169dz7ty5Ap8tFoS3xcEvd/HBwhFc+/0KKYlX8AvugJ6RvjzZzAcLP+LBzbt8P28jAIfWxRGyaSotBnfi3MHTeHX2wb62C7Hhqj9eGpgYUq9DY3bM/LrAc1f3qYW1gy3HxBBUQRBK0VvRWIRnsxkqlUr69+/Po0eP8Pb2Jj4+ngoVKhS5jLCwMG7cuMGAAQPQ1tZm6NCh+Pv7v9CX6i5duvDxxx8zcuRIMjMz6dixI5MnT1aZRKY4ihujhYUF27ZtIyIigidPnuDm5sbGjRupWbMm0dHRZGRkMGPGDJVZHX19fTUOUXtRVatWxdHRkcjISHmJjNy/8/d+5Dp06BDXr19X6506ePAgfn5+REVFMWPGDD799FP++ecfrK2tady4MZ06dQKQZ3DMneAkv7zljB49mk6dOvH06VOaN2/O7t271YYLFmbw4MEYGRkxf/58xo4di7GxMbVr11ZZaiU/S0tLwsLCmDBhgkp6adzPOjo67N27lwkTJtCnTx9u3bqFk5MTo0ePLrDx+iJKI+aS8vHx4cMPP+T999/nzp07TJ06VX6Pubm54ePjw927d9WGCGsSGhrKypUrVSZzqVKlCrt372bs2LHUrVsXS0tLgoODVSavKi1aWlrExsYSEhJCrVq1cHd3Z+nSpfKSNkXx008/AVCtWjWV9KtXr+Lo6Mju3buZOHEigwYN4tatW9jZ2dG8eXP52dD333+fK1euMG7cOJ48eUKPHj0YPnw48fHxpVZPQXgdnfnhGCaWZnT4OAAzGwv+Tkpm5cDZ8rDSClWskPI8z3T19EViRi+j46fv03lsb9KSb/Dl0PnyGou5GnT2QaFQ8OvOgn/Qavx+C/46dYG0K/+WTeUE4W0ghqGqUUhl9eDRW0CpVOLh4UFAQADTp08v73A0eh1iFITyJEkSbm5ujBgxokwayULBQhwLnyFZEARBEHItTd5U5ud4PLZbqZRjMr/kowRfNW9Nz2JpSElJYe/evfj6+pKZmcny5cu5evUqffv2Le/QZK9DjILwqrh16xaxsbHcuHFDbW1FQRAEQRCEt51oLBaDlpYW0dHRhIaGIkkStWrVYv/+/fLzTi9D3lk884uLi8PR0bHcYyzIzz//LK+xp0nujKGC8LJUrFgRa2trVq9e/VKGwwqCIAiC8Ap7w5a9KA2isVgM9vb2z50Ao6wlJiYWuK9KlSoYGhqWe4wF8fb2LjR+QXjZxCh8QRAEQRBk4plFNaKx+JpxdXUt7xBKzNDQ8LWOXxCE0pWJ+AVXEARBEF5lorEoCIIgCIIgCMJbTxI9i2pEY1EQBEEQBEEQBEE0FtWU7mrRgiAIgiAIgiAIwhvhpTQWIyIiqFevXrGO8fPzK3Sx8pcVR2GKEqOjoyOLFy8utXO+SgIDA+natav8d1m8Zq+C0r5vXrbi3oPJyckoFAoxGVERJCQkoFAouH//fnmH8lJieVPf44JQmvz6+zPz8Ocsv7Ce8Ttm4Vi38Gf1G3RoTOSBxSy/sJ4pexZSy6++yv5Vyd9q3NoO7aKSr1aLBozfMYtlf67ns7NRDF89ttTrJghvPKWydLY3yEtpLIaGhnLgwIFiHbNt2zaxiHwR5OTkMGfOHGrUqIGhoSGWlpa88847fPnll+UdGn5+figUChQKBfr6+lSpUoXOnTuzbdu28g7ttVdYgy7/F/qTJ08ydOjQUo9BkiTWrFlDkyZNMDMzw8TEhJo1azJ69GguX75c6ufT5FX7MSa3waZpu3HjRnmH98LE57IgFM67kw89Jw1k15JvmdkxjL/PpxDy1URMrcw05nduUJ3BS8dwZNOPzOgwjsS9Jxi+ehyVq9vLecY2HKKyxYz9HKVSyem4X+Q89du9Q9CiURz99iDT24cyv8dkTnx3uMzrKwhvHKVUOtsbpEwbi5IkkZ2djYmJCVZWVsU61tLSElNT0zKK7M0RGRnJokWLmD59OufPn+fgwYMMHTr0lejpABgyZAjXr1/nypUrbN26FU9PT3r37l0mjRdBMxsbG4yMjEq1TEmS6Nu3LyEhIXTo0IG9e/dy/vx51q5di4GBATNmzCjw2KdPn5ZqLK+iCxcucP36dZWtYsWK5R3WCxOfy4JQuNaDO3E49gBHv03g+uW/WT9xNU//e4pPQEuN+VsFdeTcoUT2rt7JjSv/sPOzTaSe+wu/ge3kPA9v3VfZ6rZpyMVj57h9LQ0ALW0t3p86iK2zvuan9ftIu3qd65f/5tddx15KnQXhjSIai2qK3VjMzMwkJCSEihUrYmBgQLNmzTh58iTwv1/V4+Li8PLyQl9fn8OHD6sN48vOziYkJAQLCwusrKwICwtj4MCBhQ5pdHR0ZNasWQQFBWFqaoqDgwOrV69WiS0sLIzq1atjZGSEs7MzkydPJisrq7hVLHKM+aWlpdG5c2cMDQ1xcnJi/fr1ankUCgWrVq2iU6dOGBkZ4eHhwbFjx7h8+TJ+fn4YGxvj4+PDlStXihTnzp07GTFiBL169cLJyYm6desSHBxMaGionMfPz49Ro0YxZswYKlSogK2tLWvWrCE9PZ1BgwZhamqKq6srcXFx8jE5OTkEBwfj5OSEoaEh7u7uLFmypOgX8P8ZGRlhZ2dH1apVady4MXPnzmXVqlWsWbOG/fv3y/muXbtGQEAAFhYWWFpa8t5775GcnCzvzx3yGhkZiY2NDWZmZnz44YcqDQ+lUsns2bPlmOvWrcuWLVvk/bn354EDB/D29sbIyAgfHx8uXLigEvOcOXOwtbXF1NSU4OBgnjx5olavL7/8Eg8PDwwMDKhRowYrVqyQ9+X2+m3bto0WLVpgZGRE3bp1OXZM9T/uI0eO4Ofnh5GRERUqVMDf35979+4VqS7Fkb/37c8//6RZs2YYGBjg6enJ/v37USgU7NixQ+W4v/76q8D4N23aRGxsLJs2bWLy5Mk0btwYBwcH+TWOioqS8+a+djNnzqRy5cq4u7sD8PXXX+Pt7Y2pqSl2dnb07duXtLRnX34kScLV1ZUFCxaoxJSYmIhCoShyz+V3331HgwYNMDAwwNnZmcjISLKzswHo27cv77//vkr+rKwsrK2t+eqrr4CSvw4VK1bEzs5OZdPS0lK5HrNmzcLW1hYLCwumTZtGdnY2Y8eOxdLSkqpVq6pcw9x7KjY2Fh8fHwwMDKhVqxaHDh1SO/evv/5a4P195coV3nvvPWxtbTExMaFhw4Yq70OAFStW4ObmhoGBAba2tvTs2VPel/9zubC8gvC20dbVwaGWM0lHfpPTJEnizyO/4dygusZjnOtX5888+QHO/3S2wPym1ubUbtGAw5t+lNMcajlToZIVkqRk4q55zDuxmlHRE1R6JwVBEEqq2I3FcePGsXXrVmJiYjh9+jSurq74+/tz9+5dOc/48eOZM2cOSUlJ1KlTR62MuXPnsn79eqKiojhy5AgPHz5U+6KqycKFC/H29ubMmTOMGDGC4cOHq3wRMjU1JTo6mvPnz7NkyRLWrFnDokWLilvFEscYGBjItWvXOHjwIFu2bGHFihXyl9+8pk+fzoABA0hMTKRGjRr07duXYcOGER4ezqlTp5AkiZEjRxYpTjs7O3788Udu3bpVaL6YmBisra05ceIEo0aNYvjw4fTq1QsfHx9Onz5N27Zt6d+/PxkZGcCzL8lVq1bl22+/5fz580yZMoUJEyawefPmIsVVmIEDB1KhQgV5OGpWVhb+/v6Ympry888/c+TIEUxMTGjXrp1KY/DAgQMkJSWRkJDAxo0b2bZtG5GRkfL+2bNn89VXX/HFF19w7tw5Pv74Yz744AO1L9QTJ05k4cKFnDp1Ch0dHYKCguR9mzdvJiIiglmzZnHq1CkqVaqk0hAEWL9+PVOmTGHmzJkkJSUxa9YsJk+eTExMjNp5QkNDSUxMpHr16vTp00duqCQmJtKqVSs8PT05duwYhw8fpnPnzuTk5BSrLsWVk5ND165dMTIy4vjx46xevZqJEydqzFtY/Bs3bsTd3Z0uXbpoPFahUKj8feDAAS5cuMC+ffv44YcfgGev+/Tp0zl79iw7duwgOTmZwMBA+figoCCVBhNAVFQUzZs3L9J6nT///DMDBgxg9OjRnD9/nlWrVhEdHc3MmTMB6NevH99//z2PHz+Wj4mPjycjI4Nu3boBZfc6/Pjjj/z777/89NNPfPbZZ0ydOpVOnTpRoUIFjh8/zocffsiwYcP4+++/VY4bO3Ysn376KWfOnKFJkyZ07tyZO3fuqOQp7P5+/PgxHTp04MCBA5w5c4Z27drRuXNnUlNTATh16hQhISFMmzaNCxcusGfPHpo3b66xDsXJKwhvA5MKpmjraPPo9gOV9Ie3HmBuY6HxGDMbCx6q5b+PubXm/E16+PIk/Qln4o/LadYOz0YtdBodwO5lW1keNIeMB+l8GhuBkblJySskCG8hSZJKZSuJzz//HEdHRwwMDHjnnXc4ceJEgXnPnTtHjx49cHR0RKFQFPhITnHKLEixGovp6emsXLmS+fPn0759ezw9PVmzZg2GhoasXbtWzjdt2jTatGmDi4sLlpaWauUsW7aM8PBwunXrRo0aNVi+fDkWFhbPPX+HDh0YMWIErq6uhIWFYW1tzcGDB+X9kyZNwsfHB0dHRzp37kxoaGiJGzfFjfHixYvExcWxZs0aGjdujJeXF2vXruW///5Tyzto0CACAgKoXr06YWFhJCcn069fP/z9/fHw8GD06NEkJCQUKc7PPvuMW7duYWdnR506dfjwww9Veghz1a1bl0mTJuHm5kZ4eDgGBgZYW1szZMgQ3NzcmDJlCnfu3OG33579wqmrq0tkZCTe3t44OTnRr18/Bg0aVCqNRS0tLapXry73HG7atAmlUsmXX35J7dq18fDwICoqitTUVJXroKenx7p166hZsyYdO3Zk2rRpLF26FKVSSWZmJrNmzWLdunX4+/vj7OxMYGAgH3zwAatWrVI5/8yZM/H19cXT05Px48dz9OhRufdw8eLFBAcHExwcjLu7OzNmzMDT01Pl+KlTp7Jw4UK6d++Ok5MT3bt35+OPP1Y7T2hoKB07dqR69epERkaSkpIi94jNmzcPb29vVqxYQd26dalZsyYjR47E2tq6WHXx8fHBxMREZfv5558LvPb79u3jypUrfPXVV9StW5dmzZrJjaf8Cov/4sWLcg9hrjFjxsgxVK1aVWWfsbExX375JTVr1qRmzZoABAUF0b59e5ydnWncuDFLly4lLi5ObrwFBgZy4cIF+YMtKyuLDRs2qDR+ChMZGcn48eMZOHAgzs7OtGnThunTp8vX0N/fH2NjY7Zv3y4fs2HDBrp06YKpqWmxXof8qlatqvKa5NY5l6WlJUuXLsXd3Z2goCDc3d3JyMhgwoQJ8ntUT0+Pw4dVnzkaOXIkPXr0wMPDg5UrV2Jubq7y2QuF399169Zl2LBh1KpVCzc3N6ZPn46Liws7d+4EIDU1FWNjYzp16kS1atWoX78+ISEhGutYnLzwbFTKw4cPVbYcKafQ6ygIgqqmAS05seNnsjP/N2pKoXj2VS7u822c2XOc1D/+Imbs50gSeHVsXF6hCsLrqZyGoW7atIlPPvmEqVOncvr0aerWrYu/v7/GTieAjIwMnJ2dmTNnDnZ2dqVSZkGK1Vi8cuUKWVlZNG3aVE7T1dWlUaNGJCUlyWne3t4FlvHgwQNu3rxJo0aN5DRtbW28vLyee/68vZQKhQI7OzuVCm/atImmTZtiZ2eHiYkJkyZNkn8xL46SxJiUlISOjo5Knho1amhsYOath62tLQC1a9dWSXvy5AkPHz58bqyenp788ccf/PLLLwQFBclDYQcPHlzgObW1tbGyslI7J6ByPT///HO8vLywsbHBxMSE1atXl+h6aiJJktz7dPbsWS5fvoypqan85drS0pInT56oDMetW7euyrN3TZo04fHjx1y7do3Lly+TkZFBmzZtVL6kf/XVV2pDevNei0qVKqnUOykpiXfeeUclf5MmTeR/p6enc+XKFYKDg1XOM2PGjGKdJ7dnUZPi1GXTpk0kJiaqbIW9/y5cuIC9vb3KB0ve+7yo8WsyceJEEhMTmTJlikpvHTy7v/X09FTSfv31Vzp37oyDgwOmpqb4+voCyPdY5cqV6dixI+vWrQPg+++/JzMzk169ehUYQ15nz55l2rRpKtcw9xnajIwMdHR0CAgIkIeLp6en891339GvXz+geK9Dfj///LPKa7J7926V/TVr1pSHpcKz91/e92PuezT/9c57L+ro6ODt7a3y2QuFv26PHz8mNDQUDw8PLCwsMDExISkpSb7mbdq0oVq1ajg7O9O/f3/Wr18vjzbIrzh54Vkvrbm5ucp25sGfBeYXhNfN43uPyMnOwdTaXCXdzMacB7fuazzm4a37mKnlt+DBbfX8rg1rYOdShcObVCcMfHDr2eML/17630iE7KfZ3L52E8vKNiWoiSAIL0rTD6SZmZkF5v/ss88YMmQIgwYNwtPTky+++AIjIyP5O1B+DRs2ZP78+fTu3Rt9ff1SKbMgOsXKXUTGxsZlUSy6uroqfysUCpT/Pz3tsWPH6NevH5GRkfj7+2Nubk5sbCwLFy4sk1heRN565DaYNKUpizj1rpaWFg0bNqRhw4aMGTOGb775hv79+zNx4kScnJzUys89R2HnjI2NJTQ0lIULF9KkSRNMTU2ZP38+x48f50Xl5ORw6dIlGjZsCDz7Auvl5aXxGU8bm6L9R5fbONm1axdVqlRR2Zf/TfQi1zr3PGvWrFFrVGpraxf5PIaGhs89R1HqYm9vrzYks7Cyi6Ow+N3c3NSe9bSxscHGxkbjRC75PxPS09Px9/fH39+f9evXY2NjQ2pqKv7+/ipDjwcPHkz//v1ZtGgRUVFRvP/++0WerOfx48dERkbSvXt3tX0GBgbAs6Govr6+pKWlsW/fPgwN/4+9+46K4nobOP5dQHoTRLABIiDYFazYS7BhiRELKlhirFiCIlEUNAr2KFhRAY2KSSwxqFiwRMEuYEMUFDC/2HuJSHv/4HXiuggLQU3wfs6Zc9yZO3eeO7Ose/c2LTp27CidD8o9h3dVrVq1wJ4Ihf09vtmn7PvyfXm/+9y8vLzYv38/CxYswNraGi0tLb766ivpnuvp6XHu3DkOHz7Mvn37mD59On5+fpw+fVqhPEVJC+Dj48PEiRPl9k2s7VHk8gnCv1V2ZhbpF69j36w2Cfvy5nKQyWTYNavNofVR+Z5zPe4qds1qE73u7x+U7JvX4fq5qwppnfq0I+18Cn8kpsntT79wncyM15hZVSTlTN4PMCpqqhhXMuHh/woeoiIIwjtKaHKagIAAuaFSkNczzc/PTyHt69evOXv2LD4+PtI+FRUV2rdvrzDfhbJKMs8itSxWq1YNdXV1YmJipH2ZmZmcPn1aoave+xgYGGBqaipNigN5lYdz584VJRQFsbGxWFhYMHXqVBwdHbGxsSEtLa3wE0soRjs7O7Kysjh79qy0Lykp6ZPMSvrmWbx48aLYecTExNCsWTNGjRpF/fr1sba2VnrSncKEh4fz6NEjevXqBUCDBg24du0a5cuXx9raWm4zMPj7F9eEhAS5br0nTpxAV1eXKlWqUKNGDTQ0NEhPT1fIo0oV5Qf529vbK1SIT5z4e3pyU1NTKlasyPXr1xWu86Zirow6deq8dzmZkipLfqpXr87Nmze5c+eOtO/t97my+vXrR1JSEr/++mux4rhy5QoPHjwgMDCQFi1aYGdnl2+rZefOndHR0WHFihVERUUp3QUV8t5XSUlJCvfQ2tpaatVr1qwZVapUYcuWLWzcuJHevXtLla0P+RyK6+334pvPG3t7e6XPj4mJwcPDg549e1K7dm3MzMzkJpKCvBbL9u3bM2/ePM6fP09qaioHDx7MN7+ipNXQ0EBfX19uU5Wp5ptWEP6rDqyJpHm/djTp1QqzapXoP/tr1LU1iP05b8iMx8Ix9JjcX0ofvW4XNVvVo/2wrphWq0jX8b2xqF2Nw+HylUtNXS0cOjdRaFUEePX8L37fuB+XCa7Yt6iDqVVF3L7/GkDMiCoIRZSbk1sim4+PD0+ePJHb3q64ve3+/ftkZ2dLvfzeMDU1LfayWyWZZ5FaFnV0dBg5cqQ0Y5+5uTnz5s3j5cuXDB06lISEBKXyGTt2LAEBAVhbW2NnZ0dQUBCPHj1SmBSjKGxsbEhPTyciIoKGDRuya9cuubFIRVXUGKtXr07Hjh355ptvWLFiBWpqaowfP77EWnne56uvvsLJyYlmzZphZmbGjRs38PHxwdbWFjs7u2Lna2Njw/r169m7dy9Vq1Zlw4YNnD59ukgVIsjrU3379m2ysrL4448/2L59O4sXL2bkyJG0adMGyGvdmT9/Pt27d2fmzJlUrlyZtLQ0tm3bxuTJk6Xxb69fv2bo0KFMmzaN1NRUZsyYwZgxY1BRUUFPTw8vLy8mTJhATk4OzZs358mTJ8TExKCvr4+7u7tS8Y4bNw4PDw8cHR1xcnJi48aNXLp0CSsrKymNv78/np6eGBgY0LFjRzIyMjhz5gyPHj1SaDl5Hx8fH2rXrs2oUaMYMWIE6urqHDp0iN69e1OuXLkSKUt+3owldnd3Z968eTx79oxp06YBipPSFKRv375s27aNvn374uPjg7OzM6ampqSlpbFlyxaFVtZ3mZubo66uTlBQECNGjODixYv5rt+nqqqKh4cHPj4+2NjYyHXDfON///ufwnqTFhYWTJ8+na5du2Jubs5XX32FiooKCQkJXLx4UW5pj/79+7Ny5UquXr0qNwb6n7yn7t69qzCLrrGxsULrYVEtW7YMGxsb7O3tWbx4MY8ePSpSBdrGxoZt27bh4uKCTCbD19dXrvUyMjKS69ev07JlS8qWLcvu3bvJyclRGJ9a1LSC8Lk4ExmLrpE+3Sb0Qd/EkD8SU1nqPlua9MaoUjm5yS+un7vKmnFL6P5tP3pM6s/d1FusGD6PP6/elMu3oYsTMpmMUztjyM8vczaQnZXNkEVjKaOpzo34ZBb19+fl0+L/aCwIQvFpaGgU2gvpv6LI3VADAwPJyclh4MCBPHv2DEdHR/bu3UvZsmWVzsPb25vbt28zaNAgVFVVGT58OM7OzoV+wSxIt27dmDBhAmPGjCEjI4MuXbrg6+ubb3Pvh4oxNDSUYcOG0apVK0xNTfn+++/x9fUtZomU4+zszObNmwkICODJkyeYmZnRtm1b/Pz8UFMrfi/jb775hri4OPr06YNMJqNfv36MGjUq38lzChISEkJISAjq6uoYGxvj4ODAli1bpNkmIW95jd9//x1vb2++/PJLnj17RqVKlWjXrh36+n8vZNyuXTtsbGxo2bIlGRkZ9OvXT+75zpo1CxMTEwICArh+/TqGhoY0aNCA7777Tul4+/TpQ0pKCpMnT+bVq1f06tWLkSNHsnfvXinNsGHD0NbWZv78+UyaNAkdHR1q164tt6RAYWxtbdm3bx/fffcdjRo1QktLi8aNG9OvX78SK0t+VFVV2bFjB8OGDaNhw4ZYWVkxf/58XFxcpK6ZypDJZGzZsoWQkBBCQ0OZN28emZmZVK5cmXbt2rFo0aICzzcxMSEsLIzvvvuOpUuX0qBBAxYsWJDv7KpDhw5lzpw5DB48ON+8FixYoLDExoYNGxgwYACRkZHMnDmTuXPnUqZMGezs7BTG87q5uTF79mwsLCzkxmND8Z9DfhWm48eP06TJP5tsIjAwkMDAQOLj47G2tmbnzp2UK1dO6fMXLVrEkCFDaNasGeXKlcPb21tubLShoSHbtm3Dz8+PV69eYWNjw+bNmxUm6ClqWkH4nBxeH8Xh93Q7XdTXT2Hfud0nOLf7hGLitxzdfICjmw+893hOVjZb52xg65wNRYpVEIR3fII1EsuVK4eqqqpcry+AO3fuvHfymo+Zpyy3uPO7lqCcnBzs7e1xdXXNt3Xh3+C/EGNp5uHhwePHj5VaYkUompiYGJo3b05ycjLVqlX71OEoOHr0KO3atePmzZsK3Sk+F6mpqVStWpW4uDi5NWv/676xVG6yIkEQBEFYlfrzB7/Gk4H5Tz5YVAYb8h9q9D6NGzemUaNGBAUFAXn1DnNzc8aMGcOUKVMKPNfS0pLx48crNFr8kzzf9kEmuClMWloa+/bto1WrVmRkZBAcHMyNGzfo379/4Sd/JP+FGAWhOLZv346uri42NjYkJyczbtw4nJyc/nUVxYyMDO7du4efnx+9e/f+bCuKgiAIgiCUbhMnTsTd3R1HR0caNWrEDz/8wIsXL6ReVYMGDaJSpUoEBAQAeUOzLl++LP37zZAcXV1daeLDwvJU1iepLKqoqBAWFoaXlxe5ubnUqlWLAwcOFGmihn9KV/f9C9Xu2bMHS0vLTx4j5E2x/76JelatWiVN8y8Iynr27Bne3t6kp6dTrlw52rdv/6+cNXjz5s0MHTqUevXqsX79+k8djiAIgiAIpVzuJ+iGCnnDoO7du8f06dO5ffs29erVIyoqSvqhPD09XW7JrT///JP69etLr98MyWnVqpW0RnlheSrrX9EN9VN4s7h4fipVqvTBJ6ZRVlpaGpmZmfkeMzU1RU9P7yNHJAiCUDJEN1RBEARBWR+jG+rjfm1KJB/DzYcKT/Qf8UlaFv8N3l2b7t/KwsLiU4cgCILwQbzMzf7UIQiCIAjC34q+vHGpV6R1FgVBEARBEARBEITPw2fbsigIgiAIgiAIgvDGpxqz+G8mWhYF4QPx8/Mr8jIHrVu3LtJ6jR8qjoIoE2NqaioymYz4+PgSu64gCIIgCMIHlVNCWykiWhYF4QPx8vJi7NixRTpn27ZtlClT5gNFVLp4eHgQHh4OgJqaGpUrV6Z3797MnDkTTU3NErvOmzUO3zAyMsLBwYG5c+fKzUT2b+Tn58eOHTtEpV0QPqL2gzrSeXgPDEwMuZmYyvoZa7ie8P5J9Rp1bkqvb/tRrnJ57qTeYkvgBhIOnZOOb0jblu95m+eEs3vVrwAsOrYSkyrl5Y5vCdxA5IrtJVAiQRA+Z6KyKAglLDc3l+zsbHR1dQtcoiU/RkZGHyiqj+f169cf7VodO3YkNDSUzMxMzp49i7u7OzKZjLlz55b4tQ4cOEDNmjX5448/8PT0pFOnTly5cgVDQ8Mi5/X69WvU1dVLPEZBED6txl2d6D9tMKFTV5ESf5WOQ7oyecN0JrcZy9MHTxTS2zhUZ1TQRH6a9yPx0Wdo2r0l41d749tlEn9cTQdgjOMQuXPqtG7AsHmjOL37hNz+XxZu5vDm/dLrV8//+gAlFITSTXRDVSS6oQqCEjIyMvD09KR8+fJoamrSvHlzTp8+DcDhw4eRyWTs2bMHBwcHNDQ0OHbsmEL3z6ysLDw9PTE0NMTY2Bhvb2/c3d3p0aOHlObdLp6WlpbMmTOHIUOGoKenh7m5OatXr5aLzdvbG1tbW7S1tbGyssLX1/e9y60URpkY32VpacmsWbMYNGgQ+vr6DB8+XCHNm3u0d+9e6tevj5aWFm3btuXu3bvs2bMHe3t79PX16d+/Py9fvlQ6Xg0NDczMzKhSpQo9evSgffv27N//95clS0tLfvjhB7lz6tWrh5+fn/RaJpOxZs0aevbsiba2NjY2NuzcuVPhWsbGxpiZmeHo6MiCBQu4c+cOJ0+eBODYsWO0aNECLS0tqlSpgqenJy9evCj0HsXExNC6dWu0tbUpW7Yszs7OPHr0CICcnBwCAgKoWrUqWlpa1K1bl19++UXhnkZHR+Po6Ii2tjbNmjUjKSkJgLCwMPz9/UlISEAmkyGTyQgLCwNg0aJF1K5dGx0dHapUqcKoUaN4/vy5XHlDQkKoUqUK2tra9OzZk0WLFilUjH/99VcaNGiApqYmVlZW+Pv7k5WVpcSTE4TSqdMwFw5H7Ofozwf589ofhH63ioy/Mmjp2jbf9F8M7sr5I3HsXvUrfyb/j60LN5N68Qbt3TtJaZ7ceyy3OXRoSOLxi9y7eUcur1fP/5JLl/FXxgctqyCUSqIbqgJRWRQEJUyePJmtW7cSHh7OuXPnsLa2xtnZmYcPH0pppkyZQmBgIImJidSpU0chj7lz57Jx40ZCQ0OJiYnh6dOn7Nixo9BrL1y4EEdHR+Li4hg1ahQjR46UKgQAenp6hIWFcfnyZZYsWUJISAiLFy8uVjmLG+OCBQuoW7cucXFx+Pr6vjedn58fwcHBxMbGcvPmTVxdXfnhhx/YtGkTu3btYt++fQQFBRUr9osXLxIbG1usFjt/f39cXV05f/48nTt3xs3NTe7ZvuvNOqyvX78mJSWFjh070qtXL86fP8+WLVs4duwYY8aMkTvn3XsUHx9Pu3btqFGjBsePH+fYsWO4uLiQnZ23nERAQADr169n5cqVXLp0iQkTJjBgwACOHDkil+/UqVNZuHAhZ86cQU1NjSFD8loh+vTpw7fffkvNmjW5desWt27dok+fPgCoqKiwdOlSLl26RHh4OAcPHmTy5MlSnjExMYwYMYJx48YRHx9Phw4dmD17ttx1jx49yqBBgxg3bhyXL19m1apVhIWFKaQThM+Fahk1LGtX49Kx89K+3NxcLh07j3WD6vmeY93AVi49wIXf47B5T3r9cgbUbevAkS3RCse6juzJ8vhwZu1eQOdvuqOiKr7iCYLwz4luqIJQiBcvXrBixQrCwsLo1Cnv196QkBD279/P2rVradiwIQAzZ86kQ4cO780nKCgIHx8fevbsCUBwcDC7d+8u9PqdO3dm1KhRQF4r4uLFizl06BDVq+d9mZg2bZqU1tLSEi8vLyIiIuS+/CuruDG2bduWb7/9Vnqdmpqab7rvv/8eJycnAIYOHYqPjw8pKSlYWVkB8NVXX3Ho0CG8vb2VijcyMhJdXV2ysrLIyMhARUWF4OBgpc59m4eHB/369QNgzpw5LF26lFOnTtGxY0eFtI8fP2bWrFno6urSqFEjpk6dipubm9QibGNjw9KlS2nVqhUrVqyQxk++e4/69++Po6Mjy5cvl/bVrFkTyGvJnjNnDgcOHKBp06YAWFlZcezYMVatWkWrVq2kc2bPni29njJlCl26dOHVq1doaWmhq6uLmpoaZmZmcmV4t/X6+++/Z8SIEVIsQUFBdOrUCS8vLwBsbW2JjY0lMjJSOs/f358pU6bg7u4uxTdr1iwmT57MjBkzFO5bRkYGGRnyLR3ZudmoylQV0grCf5FeWT1U1VR5cv+x3P6n9x9TsVqlfM8xNDFUSP/k/hMMTAzzTd+iVxtevfiLM1HyXVD3he0i9eJ1Xjx+jo1DdVy9B2BYviybZoUVszSC8HnKLWWtgiVBVBYFoRApKSlkZmZKlRyAMmXK0KhRIxITE6XKoqOj43vzePLkCXfu3KFRo0bSPlVVVRwcHMjJKfiT6e1WSplMhpmZGXfv3pX2bdmyhaVLl5KSksLz58/JyspCX1+/yOX8JzEWVPa3vV0WU1NTqevs2/tOnTqldMxt2rRhxYoVvHjxgsWLF6OmpkavXr2UPj+/uHR0dNDX15e7xwDNmjVDRUWFFy9eYGVlxZYtWzA1NSUhIYHz58+zceNGKW1ubi45OTncuHEDe3t7QPEexcfH07t373zjSU5O5uXLlwo/Prx+/VphUp23Y69QoQIAd+/exdzc/L3lPXDgAAEBAVy5coWnT5+SlZXFq1evePnyJdra2iQlJUk/GLzRqFEjucpiQkICMTExci2J2dnZcvm8LSAgAH9/f7l9tfXtqGto/944BUGQ19K1LbE7jpKZIT/UIGrNb9K/b15JIyszi8FzRvDT3B/Jei26hguC0kRlUYGoLApCCdHR0fkg+b47O6pMJpMqb8ePH8fNzQ1/f3+cnZ0xMDAgIiKChQsXfpBY3kfZsr9dFplMVmDZlL2utbU1AOvWraNu3bqsXbuWoUOHAnndLXNz5Qer5zeeU5k4tmzZQo0aNTA2NpYbu/f8+XO++eYbPD09FfJ9u8L27j1605U1P2/GD+7atYtKleRbJDQ0NN4bu0wmAyjwHqamptK1a1dGjhzJ7NmzMTIy4tixYwwdOpTXr18rVPIKitHf358vv/xS4Vh+s9H6+PgwceJEuX0jag1U6lqC8F/w7NEzsrOyMShnKLdfv5whj+89zvecx/ceK6Q3KGfAk3zS2za0p6J1ZZaNWVRoLClx11Aro0a5yuW5ff1PJUsgCIKgSHRoF4RCVKtWDXV1dWJiYqR9mZmZnD59mho1aiiVh4GBAaamptKkOJDXCnPu3LkCzipcbGwsFhYWTJ06FUdHR2xsbEhLSytWXh8qxo9FRUWF7777jmnTpvHXX3mzAJqYmHDr1i0pzdOnT7lx40ax8q9SpQrVqlVTmOSlQYMGXL58GWtra4WtoPGTderUITpacdwRQI0aNdDQ0CA9PV0hzypVqigds7q6ujQG8o2zZ8+Sk5PDwoULadKkCba2tvz5p/yXyerVq8u9DwCF1w0aNCApKSnfcquoKP7XoqGhgb6+vtwmuqAKpUl2ZhapF1Ko4STfG6SmUx2SzyXle07yuavUdKott69Wi7pcyyd96z7tuH4+mfTE1EJjsahZlZzsbJ7eV5yBVRCE98vNKZmtNBGVRUEohI6ODiNHjmTSpElERUVx+fJlvv76a16+fCm1YClj7NixBAQE8Ouvv5KUlMS4ceN49OiR1BpUHDY2NqSnpxMREUFKSgpLly5l+/bir6v1IWL8mHr37o2qqirLli0D8sYJbtiwgaNHj3LhwgXc3d1RVS3ZCoq3tzexsbGMGTOG+Ph4rl27xq+//qowwc27fHx8OH36NKNGjeL8+fNcuXKFFStWcP/+ffT09PDy8mLChAmEh4eTkpLCuXPnCAoKktaWVIalpSU3btwgPj6e+/fvk5GRgbW1NZmZmQQFBXH9+nU2bNjAypUr5c4bO3Ysu3fvZtGiRVy7do1Vq1axZ88euffB9OnTWb9+Pf7+/ly6dInExEQiIiLkxtAKwudmz5rfaN23Pc17taaidSU8Zn+DhrYGv/98EIBvFnniOtlNSr8vNJLarerT6etuVKhWiZ7j+1C1djUOhO+Ry1dTV4tGXZpxJOKAwjWtG9jiPKQr5vaWmFQxpVmPlrj5DiZm+++8fPpCIb0gCAUQs6EqEJVFQVBCYGAgvXr1YuDAgTRo0IDk5GT27t1L2bJllc7D29ubfv36MWjQIJo2bYquri7Ozs7/aAH5bt26MWHCBMaMGUO9evWIjY0tcDbSTxHjx6SmpsaYMWOYN28eL168wMfHh1atWtG1a1e6dOlCjx49qFatWoles06dOhw5coSrV6/SokUL6tevz/Tp06lYsWKB59na2rJv3z4SEhJo1KgRTZs25ddff0VNLW90wKxZs/D19SUgIAB7e3s6duzIrl27qFq1qtKx9erVi44dO9KmTRtMTEzYvHkzdevWZdGiRcydO5datWqxceNGAgIC5M5zcnJi5cqVLFq0iLp16xIVFcWECRPk3gfOzs5ERkayb98+GjZsSJMmTVi8eDEWFhZFuHuCULqcjIxh85xwek3sx/e7F2FRw5L5g2ZJLXzGFcthWP7v/zeunU1ihedi2vTrwOw9i2jUuSk/DJ8rrbH4RlOX5iCTcXznMYVrZr7OoolLc77bMovAAz/QbUwvotb+xjqfFR+2sIJQComWRUWy3HcH9AiC8FHk5ORgb2+Pq6srs2bN+tTh5Ou/EKPwcXz99ddcuXKFo0ePllieAy0UxzsKgiAIQn42pG374Ne416FV4YmUYLL/SOGJ/iPEBDeC8JGkpaWxb98+WrVqRUZGBsHBwdy4cYP+/ft/6tAk/4UYhY9jwYIFdOjQAR0dHfbs2UN4eLjcMh+CIAiCUNqUtlbBkiAqi4LwkaioqBAWFoaXlxe5ubnUqlWLAwcOSEsrfAy6urrvPbZnzx4sLS0/eYwA6enpBU4edPny5QKXhhD+uVOnTjFv3jyePXuGlZUVS5cuZdiwYZ86LEEQBEH4YERlUZHohioIn5Hk5OT3HqtUqVKByzl8TFlZWaSmpr73uKWlpTS2T/jvEt1QBUEQBGV9jG6od9qUTDdU00OiG6ogCP9Bb9Yk/LdTU1P7z8QqFN8rsgtPJAiCIAgfS+5/Y/b3j0lUFgVBEARBEARB+OyJbqiKxNIZgiAIgiAIgiAIggJRWRSEfPj5+VGvXr0indO6dWvGjx//yeP4kPn823yIe/4hpaamIpPJiI+P/9Sh/GMymYwdO3Z86jAEQRAEocTk5shKZCtNRGVREPLh5eVFdHR0kc7Ztm2bWIvwH/Lw8EAmkzFixAiFY6NHj0Ymk+Hh4SHt+xT3fPPmzaiqqjJ69Ogin1ulShVu3bpFrVq1lEr/b6iQldYfGgThQ3Ee1Jllx1azMeln5uyYj3VdmwLTN+ncjB+il7Ex6WcW7l1C/TYOcsd/Tvs1363bNz0V8lJTV2P+7sX8nPYrljWqlmi5BOFzkJtTMltpIiqLgvCW3NxcsrKy0NXVxdjYuEjnGhkZoaen94Ei+3xUqVKFiIgI/vrrL2nfq1ev2LRpk8JyGR/jnr9+/Vru9dq1a5k8eTKbN2/m1atXRcpLVVUVMzMzMZOrIJRSzbo2x33aEH5esgXvrhNJS7zB1A1+6Bsb5Jve1sGO8UFeHPzpAJO7TODUvpNMXu1DFdu/P+u+dnSX25Z5LSUnJ4cTu2MV8hvo48HDuw8/WPkEQfj8iMqiUOplZGTg6elJ+fLl0dTUpHnz5pw+fRqAw4cPI5PJ2LNnDw4ODmhoaHDs2DGF1pSsrCw8PT0xNDTE2NgYb29v3N3d6dGjh5Tm3S6RlpaWzJkzhyFDhqCnp4e5uTmrV6+Wi83b2xtbW1u0tbWxsrLC19eXzMzMYpXz8OHDNGrUCB0dHQwNDXFyciItLU0uzYYNG7C0tMTAwIC+ffvy7Nkz6VhUVBTNmzeXyti1a1dSUlKk42+6UEZERNCsWTM0NTWpVasWR47ITw998eJFOnXqhK6uLqampgwcOJD79+8rXY4GDRpQpUoVtm37e4rsbdu2YW5uTv369eXSFueeX7hwgbZt26KlpYWxsTHDhw/n+fPn0nEPDw969OjB7NmzqVixItWrV5eO3bhxg9jYWKZMmYKtra1cjABDhgyhTp06ZGRkAHkVzfr16zNo0CC5e/imG+qjR49wc3PDxMQELS0tbGxsCA0NVfperVmzBnt7ezQ1NbGzs2P58uXSsTfX2rZtG23atEFbW5u6dety/PhxuTxCQkKoUqUK2tra9OzZk0WLFmFoaAhAWFgY/v7+JCQkIJPJkMlkhIWFSefev3+fnj17oq2tjY2NDTt37lQ6dkEojboO6050xD4O/xzNH9dusvq7Fbz+K4O2ru3zTd9lsAvxR86xc9V2/pf8B1sWbuL6xet0dO8ipXl877Hc1rBDIy4dv8Ddm3fk8qrXugF1WtZjw+ywD1lEQSjVcnNlJbKVJqKyKJR6kydPZuvWrYSHh3Pu3Dmsra1xdnbm4cO/f32dMmUKgYGBJCYmUqdOHYU85s6dy8aNGwkNDSUmJoanT58q1T1w4cKFODo6EhcXx6hRoxg5ciRJSUnScT09PcLCwrh8+TJLliwhJCSExYsXF7mMWVlZ9OjRg1atWnH+/HmOHz/O8OHDkcn+/sBKSUlhx44dREZGEhkZyZEjRwgMDJSOv3jxgokTJ3LmzBmio6NRUVGhZ8+e5OTI96eYNGkS3377LXFxcTRt2hQXFxcePHgAwOPHj2nbti3169fnzJkzREVFcefOHVxdXYtUniFDhshVmtatW8fgwYOVOrege/7ixQucnZ0pW7Ysp0+f5ueff+bAgQOMGTNGLo/o6GiSkpLYv38/kZGR0v7Q0FC6dOmCgYEBAwYMYO3atXLnLV26lBcvXjBlyhQApk6dyuPHjwkODs43Vl9fXy5fvsyePXtITExkxYoVlCtXTqlybty4kenTpzN79mwSExOZM2cOvr6+hIeHy6WbOnUqXl5exMfHY2trS79+/cjKygIgJiaGESNGMG7cOOLj4+nQoQOzZ8+Wzu3Tpw/ffvstNWvW5NatW9y6dYs+ffpIx/39/XF1deX8+fN07twZNzc3ub8rQficqJVRw6p2Nc4fS5D25ebmcv5YArYNqud7jm2D6nLpARJ+j3tveoNyBjRo68jBLQcU9o8IHE3Q+B/I+CvjH5ZEED5fohuqItEXSijVXrx4wYoVKwgLC6NTp05AXkvK/v37Wbt2LQ0bNgRg5syZdOjQ4b35BAUF4ePjQ8+eeWNEgoOD2b17d6HX79y5M6NGjQLyWhEXL17MoUOHpNaqadOmSWktLS3x8vIiIiKCyZMnF6mcT58+5cmTJ3Tt2pVq1aoBYG9vL5cmJyeHsLAwqdvmwIEDiY6OlioHvXr1kku/bt06TExMuHz5stwYuzFjxkhpV6xYQVRUlNQ1Mzg4mPr16zNnzhy5fKpUqcLVq1extbVVqjwDBgzAx8dHahmNiYkhIiKCw4cPF3puQfd806ZNvHr1ivXr16OjowPkPUsXFxfmzp2LqakpADo6OqxZswZ1dXWF+xcUFARA3759+fbbb7lx4wZVq+aNDdLV1eXHH3+kVatW6Onp8cMPP3Do0CH09fXzjTU9PZ369evj6OgI5L0HlDVjxgwWLlzIl1/mLWxftWpVLl++zKpVq3B3d5fSeXl50aVLXiuFv78/NWvWJDk5GTs7O4KCgujUqRNeXl4A2NraEhsbK1WQtbS00NXVRU1NDTMzM4UYPDw86NevHwBz5sxh6dKlnDp1io4dOypdDkEoLfTK6qOqpsqT+4/l9j+5/5hK1Srne46hiaFC+sf3H2NoUjbf9K16teXVi784GSXfQ2D0wnHs2xjF9QvJmFQuX+wyCMLnrrRNTlMSRMuiUKqlpKSQmZmJk5OTtK9MmTI0atSIxMREad+bL+v5efLkCXfu3KFRo0bSPlVVVRwcHN57zhtvt1LKZDLMzMy4e/eutG/Lli04OTlhZmaGrq4u06ZNIz09XenyvWFkZISHhwfOzs64uLiwZMkSbt26JZfG0tJSbnxfhQoV5GK5du0a/fr1w8rKCn19fani8m48TZs2lf6tpqaGo6OjdC8TEhI4dOgQurq60mZnZwcg16W1MCYmJnTp0oWwsDCpNU/ZFreC7nliYiJ169aVKooATk5O5OTkyLX41q5dW66iCLB//35evHhB586dAShXrhwdOnRg3bp1cumaNm2Kl5cXs2bN4ttvv6V58+bvjXXkyJFERERQr149Jk+eTGys4hik/Lx48YKUlBSGDh0qd6+///57hfv89v2oUKECgHQ/kpKS5N7XgMLrgrydt46ODvr6+nLvqbdlZGTw9OlTuS07N1vpawmCAG1d23N0xxEyM/4ertDJoytaOlrsWLb1E0YmCEJpJSqLggBylYeSVKZMGbnXMplM6tZ5/Phx3Nzc6Ny5M5GRkcTFxTF16lSFCVWUFRoayvHjx2nWrBlbtmzB1taWEydOKBULgIuLCw8fPiQkJISTJ09y8uRJQHGCl4I8f/4cFxcX4uPj5bZr167RsmXLIpVnyJAhhIWFER4ezpAhQ5Q+r7ByKiO/98PatWt5+PAhWlpaqKmpoaamxu7duwkPD5fLPycnh5iYGFRVVUlOTi7wOp06dSItLY0JEybw559/0q5dO6mVryBvxliGhITI3eeLFy/KPXOQvx9vuiUX9X68T1HudUBAAAYGBnLblSfXSiQOQfg3ePboKdlZ2RiUM5Tbb1DOkMf3HuV7zuN7jxXSG74nvV3DGlSyrkx0xH65/bWa1ca2QXU2XfuFiJRtBB1ZCUDgbwsZvXBc8QskCJ+h3NyS2UoTUVkUSrVq1aqhrq5OTEyMtC8zM5PTp09To0YNpfIwMDDA1NRUmhQHIDs7m3Pnzv2j2GJjY7GwsGDq1Kk4OjpiY2OjMCFNUdWvXx8fHx9iY2OpVasWmzZtUuq8Bw8ekJSUxLRp02jXrh329vY8epT/l5u3KyNZWVmcPXtW6vLaoEEDLl26hKWlJdbW1nJbUSvkHTt25PXr12RmZuLs7Fykc9/H3t6ehIQEXrx4Ie2LiYlBRUVFbiKbdz148IBff/2ViIgIucpZXFwcjx49Yt++fVLa+fPnc+XKFY4cOUJUVFShE9aYmJjg7u7Ojz/+yA8//KAwIU9+TE1NqVixItevX1e4z2+6xCqjevXqcu9rQOG1uro62dn/vAXQx8eHJ0+eyG12BgUvKSAI/yVZmVlcv5BCbSf53g21nepw9VxSvudcPZcklx6gTot6+aZv16c9KeeTSUtMldsf6heCV8fxTOqUt83xmAnA4jHz2Tz/x39YKkH4vIh1FhWJMYtCqaajo8PIkSOZNGkSRkZGmJubM2/ePF6+fMnQoUNJSEgoPBNg7NixBAQEYG1tLY31evTokdwEMkVlY2NDeno6ERERNGzYkF27drF9+/Zi5XXjxg1Wr15Nt27dqFixIklJSVy7dk2ahbMwZcuWxdjYmNWrV1OhQgXS09OlSVretWzZMmxsbLC3t2fx4sU8evRIavkbPXo0ISEh9OvXj8mTJ2NkZERycjIRERGsWbMGVVVVpcukqqoqdW8tynkFcXNzY8aMGbi7u+Pn58e9e/cYO3YsAwcOlMYr5mfDhg0YGxvj6uqq8Mw7d+7M2rVr6dixI3FxcUyfPp1ffvkFJycnFi1axLhx42jVqhVWVlYK+U6fPh0HBwdq1qxJRkYGkZGRCmNNb9y4Ic2e+oaNjQ3+/v54enpiYGBAx44dycjI4MyZMzx69IiJEycqdT/Gjh1Ly5YtWbRoES4uLhw8eJA9e/bIldHS0lKKoXLlyujp6aGhoaFU/m/T0NBQOE9VVjLPVRD+LSLX/MroheNIOZ9McsI1ugxxQUNbk0M/501IM2bReB7efsCmeRsA2BX6G/5bZtP16+6cO3gGJ5cWVKtdjVVTlsnlq6WrRZMuTqz/XvHHp/t/ys82/epl3pI+d9Ju8/D2gw9RTEEQPiOisiiUeoGBgeTk5DBw4ECePXuGo6Mje/fupWzZ/CcQyI+3tze3b99m0KBBqKqqMnz4cJydnf9RJaZbt25MmDCBMWPGkJGRQZcuXfD19cXPz6/IeWlra3PlyhXCw8N58OABFSpUYPTo0XzzzTdKna+iokJERASenp7UqlWL6tWrs3TpUlq3bq2QNjAwkMDAQOLj47G2tmbnzp3SeMKKFSsSExODt7c3X3zxBRkZGVhYWNCxY0dUVIrekeF9E8MUl7a2Nnv37mXcuHE0bNgQbW1tevXqxaJFiwo8b926dfTs2TPfHwd69erFwIED+eOPPxgwYAAeHh64uLgAMHz4cHbt2sXAgQP5/fffFc5VV1fHx8eH1NRUtLS0aNGiBREREXJp8qv4HT16lGHDhqGtrc38+fOZNGkSOjo61K5dW24pkcI4OTmxcuVK/P39mTZtGs7OzkyYMEFu9tZevXpJy288fvyY0NBQPDw8lL6GIHxOYiOPoW+sT5+J/TE0KUvq5RvMHuTPk/tPAChXsRy5b3XVvnr2Cks8F9LPawD9Jw3kVuqfzBsewM2r8mPFnVxaIJPJiNmp+DkiCELJKW2tgiVBlptb2nrWCsKHl5OTg729Pa6ursyaNetTh/NRpKamUrVqVeLi4uTWoBRKl6+//porV65w9OjRD36t3hbdP/g1BEEQhNLh57RfP/g1btR9/8z4RVE1YX/hif4jRMuiICghLS2Nffv20apVKzIyMggODubGjRv079//U4cmCP/IggUL6NChAzo6OuzZs4fw8HCWL1/+qcMSBEEQBOFfQFQWBUEJKioqhIWF4eXlRW5uLrVq1eLAgQMK48s+JF1d3fce27NnDy1atPhosRRHenp6gZMKXb58GXNz848YkQBw6tQp5s2bx7Nnz7CysmLp0qUMGzbsU4clCIIgCB+d6IaqSHRDFYT/iIKWYahUqRJaWlofMZqiy8rKIjU19b3HLS0tUVMTv199TkQ3VEEQBEFZH6Mbakqtkpl9vdrFvSWSz7+B+GYmCP8R1tbWnzqEf0RNTe0/XwZBEARBEITPiagsCoIgCJ/EH1lPP3UIgiAIgiDJzSk8zedGVBYFQRAEQRAEQfjs5eSKMYvvEpVFQRAEQRAEQRA+e7misqig6KtkF4Ofn1+R12Vr3bp1kRaX/lBxFESZGC0tLfnhhx9K7JrCp/Fffo6HDx9GJpPx+PFjpc8p6b+V0szDw4MePXp86jCADx9LamoqMpmM+Pj4D3YNQRAEQRD+PT5KZdHLy4vo6OginbNt27bPZrHzfyIsLAxDQ8NPHUa+3nyxfLPp6elRs2ZNRo8ezbVr1z51eP9576vQvfuFvlmzZty6dQsDA4MSj+H27duMGzcOa2trNDU1MTU1xcnJiRUrVvDy5csSv967ilMR/tA8PDzk3vdvto4dO37q0P6xKlWqcOvWLWrVqvWpQxGE/4xe7j3YdmIzh1P2sua35dSoZ1dg+rZdWxFxJJzDKXv58cBamrZtLHf8+P8O5bu5jejzIYshCJ+F3BxZiWylyQfthpqbm0t2dja6uroFrhGXHyMjow8UlVCYzMxMypQpU2L5HThwgJo1a/Ly5UsuXLjAkiVLqFu3Lr/99hvt2rUrsesI+VNXV8fMzKzE871+/TpOTk4YGhoyZ84cateujYaGBhcuXGD16tVUqlSJbt265XtuSb/H/m06duxIaGio3D4NDY1PFE3JUVVV/SDvJUEordp1a4PnjJHMm7KYS3GJ9Bn2FYs3zqNvy0E8evBYIX1tx5r4L/NlZUAIxw4cx7lnO+aunYVHx+FcT0oFoEu9L+XOadqmMd8tnMSh3b9/hBIJQukmFhRUVOSWxYyMDDw9PSlfvjyampo0b96c06dPA3//yr9nzx4cHBzQ0NDg2LFjCi0gWVlZeHp6YmhoiLGxMd7e3ri7u8t1n3q3i6elpSVz5sxhyJAh6OnpYW5uzurVq+Vi8/b2xtbWFm1tbaysrPD19SUzM7OoRVQ6xnfdvXsXFxcXtLS0qFq1Khs3blRII5PJWLVqFV27dkVbWxt7e3uOHz9OcnIyrVu3RkdHh2bNmpGSklKsuN8VFRVF8+bNpXJ07dpVLu83rVBbtmyhVatWaGpqsnHjRqXKn5OTQ0BAAFWrVkVLS4u6devyyy+/KMRgbGyMmZkZVlZWdO/enQMHDtC4cWOGDh1Kdna2lO7XX3+lQYMGaGpqYmVlhb+/P1lZWXL3bsWKFXTq1AktLS2srKwUrnfz5k1cXV0xNDTEyMiI7t27y63t96ab3oIFC6hQoQLGxsaMHj1a7n2izHN8/Pgxw4YNw8TEBH19fdq2bUtCQoJ0/M17fsOGDVhaWmJgYEDfvn159uyZ3P2bN28e1tbWaGhoYG5uzuzZs5Uui7Lya30LCQmhSpUqaGtr07NnTxYtWpRvC3VB8Y8aNQo1NTXOnDmDq6sr9vb20jPetWsXLi4uUto3z65bt27o6Ogwe/ZssrOzGTp0qPT+qV69OkuWLJHO+f333ylTpgy3b9+Wi2n8+PG0aNFCqbJnZGTg5eVFpUqV0NHRoXHjxhw+fBiAp0+foqWlxZ49e+TO2b59O3p6elLLaHGeg4aGBmZmZnJb2bJl5e5HUT8H3rynVq1aJT07V1dXnjx5onD9gt7fGzZswNHRET09PczMzOjfvz93796Vjj969Ag3NzdMTEzQ0tLCxsZGqvi+22pdUFpBEKDf173ZuWkXu36KIvVaGvOmLCLjr1d07dsp3/SuQ3tx8vApNq7cQlpyOqvnh5J08RpfDe4ppXl475Hc1sLZiXOx8fyZfutjFUsQhM9IkSuLkydPZuvWrYSHh3Pu3Dmsra1xdnbm4cOHUpopU6YQGBhIYmIiderUUchj7ty5bNy4kdDQUGJiYnj69Ck7duwo9NoLFy7E0dGRuLg4Ro0axciRI0lKSpKO6+npERYWxuXLl1myZAkhISEsXry4qEUsdoweHh7cvHmTQ4cO8csvv7B8+XK5L2FvzJo1i0GDBhEfH4+dnR39+/fnm2++wcfHhzNnzpCbm8uYMWOKFfe7Xrx4wcSJEzlz5gzR0dGoqKjQs2dPcnLk5waeMmUK48aNIzExEWdnZ6XKHxAQwPr161m5ciWXLl1iwoQJDBgwgCNHjhQYk4qKCuPGjSMtLY2zZ88CcPToUQYNGsS4ceO4fPkyq1atIiwsTK7yBODr60uvXr1ISEjAzc2Nvn37kpiYCOS1Vjk7O6Onp8fRo0eJiYlBV1eXjh078vr1aymPQ4cOkZKSwqFDhwgPDycsLIywsDDpuDLPsXfv3ty9e5c9e/Zw9uxZGjRoQLt27eT+DlJSUtixYweRkZFERkZy5MgRAgMDpeM+Pj4EBgbi6+vL5cuX2bRpE6ampkUqS3HExMQwYsQIxo0bR3x8PB06dFC4z4XF/+DBA/bt28fo0aPR0dHJ9zoymXw3DD8/P3r27MmFCxcYMmQIOTk5VK5cmZ9//pnLly8zffp0vvvuO3766ScAWrZsiZWVFRs2bJDyyMzMZOPGjQwZMkSpso4ZM4bjx48TERHB+fPn6d27Nx07duTatWvo6+vTtWtXNm3aJHfOxo0b6dGjB9ra2h/0ORTncyA5OZmffvqJ3377jaioKOmz8G2Fvb8zMzOZNWsWCQkJ7Nixg9TUVDw8PKTjb96Pe/bsITExkRUrVlCuXLl8y1CUtILwuVEro0b1OracPnpW2pebm8vpY+eo5VAz33NqOdSQSw9w8vDp96YvW64sTu2a8Nvm3SUXuCB8xkQ3VEVF6ob64sULVqxYQVhYGJ065f0qFhISwv79+1m7di0NGzYEYObMmXTo0OG9+QQFBeHj40PPnnm/lAUHB7N7d+EfdJ07d5a+GHl7e7N48WIOHTpE9erVAZg2bZqU1tLSEi8vLyIiIpg8eXJRilmsGK9evcqePXs4deqUdB/Wrl2Lvb29QtrBgwfj6uoqlaNp06b4+vri7OwMwLhx4xg8eHCRY85Pr1695F6vW7cOExMTLl++LDfuaPz48Xz55d9dWworf0ZGBnPmzOHAgQM0bdoUACsrK44dO8aqVato1apVgXHZ2eWN2UhNTaVRo0b4+/szZcoU3N3dpbxmzZrF5MmTmTFjhnRe7969GTZsGJD3ZXv//v0EBQWxfPlytmzZQk5ODmvWrJEqKqGhoRgaGnL48GG++OILAMqWLUtwcDCqqqrY2dnRpUsXoqOj+frrr5V6jseOHePUqVPcvXtX6lq4YMECduzYwS+//MLw4cOBvJbDsLAw9PT0ABg4cCDR0dHMnj2bZ8+esWTJEoKDg6UyV6tWjebNmwMoXZYLFy4odPHOLaQPRVBQEJ06dcLLywsAW1tbYmNjiYyMlEtXUPzJycnk5uZKf3tvlCtXjlevXgEwevRo5s6dKx3r37+/wvva399f+nfVqlU5fvw4P/30k/T3MXToUEJDQ5k0aRIAv/32G69evZKOFyQ9PZ3Q0FDS09OpWLEikDd+OioqitDQUObMmYObmxsDBw7k5cuXaGtr8/TpU3bt2sX27dsB5Z/DuyIjIxWey3fffcd3330nvS7O58CrV69Yv349lSpVAvKeZZcuXVi4cKHUPbSg9zcgV9G2srJi6dKlNGzYkOfPn6Orq0t6ejr169fH0dERyPssLegeK5s2IyODjIwMuX05uTmoyD7K0HlB+OgMjQxQU1Pl4f1Hcvsf3nuERTXzfM8xNjHi4b130t9/hLFJ2XzTd+7tzMvnLzm8R3RBFYSSIJbOUFSkymJKSgqZmZk4OTlJ+8qUKUOjRo1ITEyUvly/+eKQnydPnnDnzh0aNWok7VNVVcXBwUGhtetdb7dSymQyzMzM5Fp8tmzZwtKlS0lJSeH58+dkZWWhr69flCIWO8bExETU1NRwcHCQ9tnZ2eXbte/tcrxpSapdu7bcvlevXvH06dNixf+2a9euMX36dE6ePMn9+/el+NPT0+Uqi28/M2XKn5yczMuXLxV+FHj9+jX169cvNK43FZo3X8ATEhKIiYmRa+HKzs7m1atX0hd5QKqYvtG0aVOpS1xCQgLJyclS5eaNV69eyXXnq1mzJqqqqtLrChUqcOHCBUC555iQkMDz588xNjaWu85ff/0ldx1LS0u5WCpUqCC9XxMTE8nIyHjvmE1ly1K9enV27twpl+Z///sfrVu3zjdfgKSkJOlHgDcaNWqkUFksKP73OXXqFDk5Obi5uSlUDPL7XFi2bBnr1q0jPT2dv/76i9evX8t1Wffw8GDatGmcOHGCJk2aEBYWhqur63tbM9924cIFsrOzsbW1ldufkZEhPbvOnTtTpkwZdu7cSd++fdm6dSv6+vq0b98eUP45vKtNmzasWLFCbt+747CL8zlgbm4uVRQh7/2fk5NDUlKSVFks6P0NcPbsWfz8/EhISODRo0dynwk1atRg5MiR9OrVi3PnzvHFF1/Qo0cPmjVrlm85i5I2ICBA7scBgEq6FlTRr5pvekEQCufStxN7tx/gdUbxhtwIgiAU5oNMcKPMF7nieHdCDJlMJn3ROX78OG5ubvj7++Ps7IyBgQEREREsXLjwg8TyT7xdjjeVpfz2FVZ5VoaLiwsWFhaEhIRQsWJFcnJyqFWrlkIXuqI+s+fPnwOwa9cuuS+voNxEHm+6jlatWlXKz9/fX6518w1NTU2lY3JwcMh3jKGJiYn074LeR8pep0KFCtLYt7e9Xaks6DpaWlqFXkOZsqirq2NtbS13XE2tZP6sC4rf2toamUwm1w0c8lqqIP/yvfsei4iIwMvLi4ULF9K0aVP09PSYP38+J0+elNKUL18eFxcXQkNDqVq1Knv27Mn3vufn+fPnqKqqcvbsWbnKEyC1+qmrq/PVV1+xadMm+vbty6ZNm+jTp490D5V9DvmV9d3n8q4P9TlQ0HN78eIFzs7OODs7s3HjRkxMTEhPT8fZ2Vn6TOjUqRNpaWns3r2b/fv3065dO0aPHs2CBQsUrlWUtD4+PkycOFFuXwc7F4V0glBaPH74hKysbIzKybcKGpmU5cG9h/me8+DeQ4zeaUU0KleWB++0NgLUbVQbC2tzpo2cWXJBC8JnTqyzqKhI/X+qVauGuro6MTEx0r7MzExOnz5NjRo1lMrDwMAAU1NTaVIcyGtBOnfuXFFCURAbG4uFhQVTp07F0dERGxsb0tLSipVXcWK0s7MjKytLGoMHeS04n3JK/wcPHpCUlMS0adNo164d9vb2PHqk+B/Ou5Qpf40aNdDQ0CA9PR1ra2u5rUqVKgXmn5OTw9KlS6latarUCtmgQQOSkpIU8rK2tkZF5e+36YkTJ+TyOnHihNRFtEGDBly7do3y5csr5KHsshHKPMcGDRpw+/Zt1NTUFK6j7HgtGxsbtLS03rukTEmU5X2qV68u92wBhdeFMTY2pkOHDgQHB/PixYtixRETE0OzZs0YNWoU9evXx9raOt/WumHDhrFlyxZWr15NtWrV5Ho2FKR+/fpkZ2dz9+5dhXv49oyebm5uREVFcenSJQ4ePIibm5t07EM+h+JIT0/nzz//lF6fOHECFRUVhe7A73PlyhUePHhAYGAgLVq0wM7OLt/WYhMTE9zd3fnxxx/54YcfFCYTK05aDQ0N9PX15TbRBVUozbIys0g6fxXH5g2kfTKZDMfmDbh49lK+51w8e1kuPUCjlg75pnfp15nEhCSSL5fMhHiCIOTNhloSW2lSpCYIHR0dRo4cyaRJkzAyMsLc3Jx58+bx8uVLhg4dKjcbZEHGjh1LQEAA1tbW2NnZERQUxKNHjxQmxCgKGxsb0tPTiYiIoGHDhnLjjoqjqDFWr16djh078s0337BixQrU1NQYP358oS1IJSE7O1thkWwNDQ2qV6+OsbExq1evpkKFCqSnpzNlyhSl8iys/Hp6enh5eTFhwgRycnJo3rw5T548ISYmBn19fWkcHuRVWm/fvs3Lly+5ePEiP/zwA6dOnWLXrl1Si8/06dPp2rUr5ubmfPXVV6ioqJCQkMDFixf5/vvvpbx+/vlnHB0dad68ORs3buTUqVOsXbsWyPvSP3/+fLp3787MmTOpXLkyaWlpbNu2jcmTJ1O5cuVCy63Mc2zfvj1NmzalR48ezJs3D1tbW/7880927dpFz549C+yG/Yampibe3t5MnjwZdXV1nJycuHfvHpcuXWLo0KElUpb3GTt2LC1btmTRokW4uLhw8OBB9uzZU+S/v+XLl+Pk5ISjoyN+fn7UqVMHFRUVTp8+zZUrV+S68ubHxsaG9evXs3fvXqpWrcqGDRs4ffq01Nr8hrOzM/r6+nz//ffMnJn/L+gXLlyQ6yoqk8moW7cubm5uDBo0iIULF1K/fn3u3btHdHQ0derUoUuXLkDeRDpmZma4ublRtWpVGjf+e02z4j6HjIwMhVlc1dTU/vHkL5qamri7u7NgwQKePn2Kp6cnrq6uSi9nYW5ujrq6OkFBQYwYMYKLFy8qrGc7ffp0HBwcqFmzJhkZGURGRuY79rqoaQXhc7Q55Gd8F0/hyvmrXIpLpO/XX6GppUnkligApi/x4d6te6wIXAPAT2u3svyXH+j3TW9iD5ygffe22NWpTuBk+V5S2rratO3aiqCZKxSuKQiCUJKK3F8tMDCQnJwcBg4cyLNnz3B0dGTv3r1y08IXxtvbm9u3bzNo0CBUVVUZPnw4zs7OCl3FiqJbt25MmDCBMWPGkJGRQZcuXfD19cXPz69Y+RUnxtDQUIYNG0arVq0wNTXl+++/x9fXt5glUt7z588VxglWq1aN5ORkIiIi8PT0pFatWlSvXp2lS5cWOJ7tDWXKP2vWLExMTAgICOD69esYGhrSoEEDuUk8AGn8l7a2NhYWFrRp04bVq1fLddNzdnYmMjKSmTNnMnfuXMqUKYOdnZ00mc0b/v7+REREMGrUKCpUqMDmzZulVm1tbW1+//13vL29+fLLL3n27BmVKlWiXbt2RRr7WdhzlMlk7N69m6lTpzJ48GDu3buHmZkZLVu2lMaeKcPX1xc1NTWmT5/On3/+SYUKFRgxYkSJliU/Tk5OrFy5En9/f6ZNm4azszMTJkwgODi4SPlUq1aNuLg45syZg4+PD3/88QcaGhrUqFEDLy8vhVk63/XNN98QFxdHnz59kMlk9OvXj1GjRiksZaGiooKHhwdz5sxh0KBB+ebVsmVLudeqqqpkZWURGhrK999/z7fffsv//vc/ypUrR5MmTejatauU9s21582bx/Tp0+XyKe5ziIqKokKFCnL7qlevzpUrVwq8J4Wxtrbmyy+/pHPnzjx8+JCuXbuyfPlypc83MTEhLCyM7777jqVLl9KgQQMWLFggtx6muro6Pj4+pKamoqWlRYsWLYiIiMg3v6KkFYTPUfTOQ5Q1MmCYlwfGJkZcu5TChAHePPr/SW9MK5aX62p+4cwlZoz5nuGThzDCexg3b/wP76G+0hqLb3To3haZTMa+HQc/ZnEEodQTE9wokuUWNnXiR5CTk4O9vT2urq4Kv3L/W/wXYvyQ/g3ll8lkbN++vcC1LoXi+frrr7ly5QpHjx791KHka+jQody7d09hMp/PiZ+fHzt27FDoRfBf1rRSm08dgiAIgvAfcfx/hz74NeLMu5dIPvXTfy2RfP4NPsmAkbS0NEJCQrh69SoXLlxg5MiR3Lhxg/79+3+KcPL1X4jxQ/rcy1/aLViwQJrpMygoiPDwcLmuw/8WT5484dixY2zatImxY8d+6nAEQRAEQSjFPuWYxWXLlmFpaYmmpiaNGzfm1KlTBab/+eefsbOzQ1NTk9q1ayss8Xfnzh08PDyoWLEi2tra0jrTRfVJKosqKiqEhYXRsGFDnJycuHDhAgcOHPioY110dXXfux09evRfESPkTYP/vjjzm6GxpPxbyi98GKdOnaJDhw7Url2blStXsnTpUoUuv/8G3bt354svvmDEiBEFrt0qCIIgCILwX7VlyxYmTpzIjBkzOHfuHHXr1sXZ2fm9S5bFxsbSr18/hg4dSlxcHD169KBHjx5cvHgRyFuirkePHly/fp1ff/2VuLg4LCwsaN++fZEnJvxXdEP9FJKTk997rFKlSh9lYhplpKWlkZmZ//pJpqamCuu/CYIg/FeIbqiCIAiCsj5GN9QzlXuUSD61U7YorDetoaHx3uXlGjduTMOGDaX5I3JycqhSpQpjx47Nd3LKPn368OLFC7k1sps0aUK9evVYuXIlV69epXr16ly8eJGaNWtKeZqZmTFnzpwiNRB8kHUW/wsKWwPt38LCwuJThyAIgvBB3H/99FOHIAiCIAiSklpnMSAgAH9/f7l9M2bMyHfizdevX3P27Fl8fHykfSoqKrRv357jx4/nm//x48cV1i52dnZmx44dAFJF9e21ylVUVNDQ0ODYsWNFqiyKRa4EQRAEQRAEQRBKiI+PD0+ePJHb3q4Mvu3+/ftkZ2crzKhvamqqsAzXG7dv3y4wvZ2dHebm5vj4+PDo0SNev37N3Llz+eOPP7h161aRyvLZtiwKgiAIgiAIgiC8UVJLZxTU5fRjKFOmDNu2bWPo0KEYGRmhqqpK+/bt6dSpE0UdgShaFgWhAH5+ftSrV69I57Ru3Zrx48d/8jg+ZD5C8X2I98en4OHhIZaxEQRBEEqV3BLaiqJcuXKoqqpy584duf137tzBzMws33PMzMwKTe/g4EB8fDyPHz/m1q1bREVF8eDBA6ysrIoUn6gsCkIBvLy8iI6OLtI527Zt+yzX4ixJn7oiIpPJpH7/7/rrr78wMjKiXLlyCoPXlVGU98envg8AqampyGSyUrW+oyB8SG5DenPo7G9cvBnLL1Hh1Klfs8D0Hbu1Jyp2KxdvxhJ5ZAut2jsppKlmY8nKDYs4l3KEhNRjbN23ngqV5L9E1nOszfptK0lIPUbc9SNs2hmChuana9kQBEE56urqODg4yH3fzMnJITo6mqZNm+Z7TtOmTRW+n+7fvz/f9AYGBpiYmHDt2jXOnDlD9+5FW0tSVBYFIR+5ublkZWWhq6uLsbFxkc41MjISs9SWYlu3bqVmzZrY2dm9t0JZEPH+EITSq3OPDnw3cyLBC1bTo50biZeusu6nYIzKlc03ff2GdVi8aja/bNxB97b9ObDnMMvDF2JjV01KY25Zmc2Ra7l+LZUBPYbj0rovyxaukfuxqp5jbdZtCebY4RP0ch7Elx0GsWHtT+Tm5HzwMgtCaZKTKyuRragmTpxISEgI4eHhJCYmMnLkSF68eMHgwYMBGDRokNyYx3HjxhEVFcXChQu5cuUKfn5+nDlzhjFjxkhpfv75Zw4fPiwtn9GhQwd69OjBF198UaTYRGVR+GxkZGTg6elJ+fLl0dTUpHnz5pw+fRqAw4cPI5PJ2LNnDw4ODtJsUe9228zKysLT0xNDQ0OMjY3x9vbG3d1drvXn3W6GlpaWzJkzhyFDhqCnp4e5uTmrV6+Wi83b2xtbW1u0tbWxsrLC19f3vUumFObw4cM0atQIHR0dDA0NcXJyIi0tTS7Nhg0bsLS0xMDAgL59+/Ls2TPpWFRUFM2bN5fK2LVrV1JSUqTjb1qaIiIiaNasGZqamtSqVYsjR47IXePixYt06tQJXV1dTE1NGThwIPfv3y9Wmd5VWN6FleH169eMGTOGChUqoKmpiYWFBQEBAUDe8wLo2bMnMplMev3G2rVrGTBgAAMGDGDt2rVyxw4fPoy6ujpHjx6V9s2bN4/y5ctL3UXefX8sX74cGxsbNDU1MTU15auvviqx+9C6dWs8PT2ZPHkyRkZGmJmZKczEduXKFZo3b46mpiY1atTgwIEDci2rVatWBaB+/frIZDJat24td/6CBQuoUKECxsbGjB49utjvW0EoDYaMGMCWH7ezdfNvJF+9wXSvOfz11yu+6p//L/nuw/tx9OBx1izbQMq1VH4IXMHl81cYONRVSjPhu1EcORDDvJlLuXwhifTUPzi493ce3n8kpZk661vWh0SwemkYyUnXuZGSxp5f9/P6tfh7FISiyM2VlchWVH369GHBggVMnz6devXqER8fT1RUlDSJTXp6utzENM2aNWPTpk2sXr2aunXr8ssvv7Bjxw5q1aolpbl16xYDBw7Ezs4OT09PBg4cyObNm4scm6gsCp+NyZMns3XrVsLDwzl37hzW1tY4Ozvz8OFDKc2UKVMIDAwkMTGROnXqKOQxd+5cNm7cSGhoKDExMTx9+lSp1qWFCxfi6OhIXFwco0aNYuTIkSQlJUnH9fT0CAsL4/LlyyxZsoSQkBAWL15c5DJmZWXRo0cPWrVqxfnz5zl+/DjDhw9HJvv7gyslJYUdO3YQGRlJZGQkR44cITAwUDr+4sULJk6cyJkzZ4iOjkZFRYWePXuS884v1JMmTeLbb78lLi6Opk2b4uLiwoMHDwB4/Pgxbdu2pX79+pw5c4aoqCju3LmDq6sr/5QyeRdWhqVLl7Jz505++uknkpKS2Lhxo1QpfPMDQmhoKLdu3ZJev7l3x48fx9XVFVdXV44ePSpXEX9TERw4cCBPnjwhLi4OX19f1qxZozBrGcCZM2fw9PRk5syZJCUlERUVRcuWLUvsPgCEh4ejo6PDyZMnmTdvHjNnzmT//v0AZGdn06NHD7S1tTl58iSrV69m6tSpcuefOnUKgAMHDnDr1i22bdsmHTt06BApKSkcOnSI8PBwwsLCCAsLUyp+QShtypRRo2ZdO2KPnJL25ebmEvv7Keo71s73nPqOdYj9/aTcvqOHjlPPMe//H5lMRusOzUlNSWfdT8GcuLyfX6LCad+ptZTeqFxZ6jnW5sH9h2zZtY7jl/ax8dfVODSuV+JlFAThwxkzZgxpaWlkZGRw8uRJGjduLB07fPiwwv+vvXv3JikpiYyMDC5evEjnzp3ljnt6enLz5k1ev35NWloas2bNQl1dvchxidlQhc/CixcvWLFiBWFhYXTq1AmAkJAQ9u/fz9q1a2nYsCEAM2fOpEOHDu/NJygoCB8fH3r27AlAcHAwu3fvLvT6nTt3ZtSoUUBeK+LixYs5dOgQ1atXB2DatGlSWktLS7y8vIiIiGDy5MlFKufTp0958uQJXbt2pVq1vG5M9vb2cmlycnIICwuTukIOHDiQ6OhoZs+eDUCvXr3k0q9btw4TExMuX74s94vVmDFjpLQrVqwgKiqKtWvXMnnyZIKDg6lfvz5z5syRy6dKlSpcvXoVW1vbIpXrbcrkXVgZ0tPTsbGxoXnz5shkMrn1TE1MTAAwNDRUGFi+bt06OnXqRNmyeV3KnJ2dCQ0NlWut+/7779m/fz/Dhw/n4sWLuLu7061bt3zLkp6ejo6ODl27dkVPTw8LCwvq169fYvcBoE6dOsyYMQMAGxsbgoODiY6OpkOHDuzfv5+UlBQOHz4slXX27NlyfwNv7oexsbHC/ShbtizBwcGoqqpiZ2dHly5diI6O5uuvv1aqDIJQmpQ1MkRNTY379x7I7X9w9wHVrC3zPadceWPu330ot+/+vYeYlM8b/mBsYoSurg7DPT1YHLCc+TOX0qJtM5aFzWdgz284FXsOc4tKAIydNJy5fj+QePEqPVy7sH7rCjq3dCXt+s2SL6wglFKi47Yi0bIofBZSUlLIzMzEyenviQPKlClDo0aNSExMlPY5Ojq+N48nT55w584dGjVqJO1TVVXFwcGh0Ou/3Uopk8kwMzPj7t270r4tW7bg5OSEmZkZurq6TJs2jfT0dKXL94aRkREeHh44Ozvj4uLCkiVLFNbTsbS0lBszV6FCBblYrl27Rr9+/bCyskJfX19qcXs3nrcHUaupqeHo6Cjdy4SEBA4dOoSurq602dnZAch1By0OZfIurAweHh7Ex8dTvXp1PD092bdvX6HXzc7OJjw8nAEDBkj7BgwYQFhYmFyrq7q6Ohs3bmTr1q28evWqwBbiDh06YGFhgZWVFQMHDmTjxo28fPmyxO4DoNBC/vbzTkpKokqVKnKVwLff34WpWbMmqqqq+eb9royMDJ4+fSq35eaK/5YFoSAq/98rJDrqCGGrNpF48Sqrl4ZxaN9R+rnn/SgmU8n7KhexfhtbN//G5QtJzPFdxPXktPd2fxUEIX+5yEpkK01EZVEQ3qKjo/NB8i1Tpozca5lMJlUwjh8/jpubG507dyYyMpK4uDimTp3K69evi3Wt0NBQjh8/TrNmzdiyZQu2tracOHFCqVgAXFxcePjwISEhIZw8eZKTJ/O6SBUlnufPn+Pi4kJ8fLzcdu3aNaW7Wf6TvAsrQ4MGDbhx4wazZs3ir7/+wtXVtdCxgnv37uV///sfffr0QU1NDTU1Nfr27UtaWprCjGSxsbEAPHz4UK6b87v09PQ4d+4cmzdvpkKFCkyfPp26devy+PHjErkPUPjz/ieKkndAQAAGBgZy28OX+S82LAj/RY8ePiYrK4tyJvKTohmXN+be3fzHa9+/+4By5Y3k9pUzMeLe3QdSnpmZWSRfvS6XJuXqDSpUzvuR596dvLyTk95Jc+0GFSvlP+2+IAj5y8ktma00EZVF4bNQrVo11NXViYmJkfZlZmZy+vRpatSooVQeBgYGmJqayo1hy87O5ty5c/8ottjYWCwsLJg6dSqOjo7Y2NgoTEhTVPXr18fHx4fY2Fhq1arFpk2blDrvwYMHJCUlMW3aNNq1a4e9vT2PHj3KN+3bFdCsrCzOnj0rdXlt0KABly5dwtLSEmtra7ntn1bIC8tb2TLo6+vTp08fQkJC2LJlC1u3bpUqdmXKlCE7O1su/dq1a+nbt69C5axv375yE92kpKQwYcIEQkJCaNy4Me7u7gVWztTU1Gjfvj3z5s3j/PnzpKamcvDgwX98H5RRvXp1bt68KbdW09vvb0Aa3/Du/SgqHx8fnjx5IrcZaYsvskLpkZmZxaWEKzRt2VDaJ5PJaNaiIXFnLuR7TtyZ8zRtId+a79SqMfFnzkt5Xoi7RNVqFnJpLKtZ8OfNvB9b/kj/k9u37mL1TlfXqtXM+d8f8j1LBEEQikqMWRQ+Czo6OowcOZJJkyZhZGSEubk58+bN4+XLlwwdOpSEhASl8hk7diwBAQFYW1tjZ2dHUFAQjx49kptApqhsbGxIT08nIiKChg0bsmvXLrZv316svG7cuMHq1avp1q0bFStWJCkpiWvXrjFo0CClzi9btizGxsasXr2aChUqkJ6ezpQpU/JNu2zZMmxsbLC3t2fx4sU8evSIIUOGADB69GhCQkLo16+fNBNncnIyERERrFmzRq7r4vs8efJEYW2/NzNuFpS3MmVYtGgRFSpUoH79+qioqPDzzz9jZmaGoaEhkNdVNzo6GicnJzQ0NMjKyuK3335j586dcuM2IW866549e/Lw4UMMDAwYMGAAzs7ODB48mI4dO1K7dm0WLlzIpEmTFMoYGRnJ9evXadmyJWXLlmX37t3k5ORIY1n/yX1Q5h536NCBatWq4e7uzrx583j27Jk0fvbNe7p8+fJoaWkRFRVF5cqV0dTUxMDAoNC836WhoYGGhvyabzKZ+L1SKF3WrfyReUH+XIxP5Py5i3h80x8tbS22bt4JwLxgf+7cvsfC74MBCF+9mY2/hjBk5AAO7z9Gl55fUKteDaZ9O1vKc82yDfwQEsDp43GciDlNy7bNaOvcggE9vpHSrF22Hs/JI7hy6SqXLybxZR8XrKwtGTvE++PeAEH4j8spZV1IS4KoLAqfjcDAQHJychg4cCDPnj3D0dGRvXv3SpOVKMPb25vbt28zaNAgVFVVGT58OM7Ozkp9MX+fbt26MWHCBMaMGUNGRgZdunTB19dXYYkDZWhra3PlyhXCw8N58OABFSpUYPTo0XzzzTeFnwyoqKgQERGBp6cntWrVonr16ixdulRhuQTIu5+BgYHEx8djbW3Nzp07KVeuHAAVK1YkJiYGb29vvvjiCzIyMrCwsKBjx46oqChXQTh8+LDCZC9Dhw5lzZo1Beb9ZlmPgsqgp6fHvHnzuHbtGqqqqjRs2JDdu3dLsS1cuFBa86hSpUqMHTsWHR0d2rVrpxBnu3bt0NLS4scff+Tx48ekpaURGRkJ5I3hW716Nf369eOLL76gbt26cucaGhqybds2/Pz8ePXqFTY2NmzevJmaNf9exLu490EZqqqq7Nixg2HDhtGwYUOsrKyYP38+Li4uaGpqAnktn0uXLmXmzJlMnz6dFi1acPjwYaXyF4TPze4d+zEyLss47xGYlDcm8eJVhvYZy4N7eb0WKlY2Izf37z5qcafPM3HEVCb4jOTbqaNJvZ7OKPdvuXbl73HH+3cfYsakOXwzbjC+c7y4kZLGmMGTOXsyXkoTtmoz6hoafDdrIgaGBly5dBWP3qNJT/3jo5VdEEqD0jbesCTIct/+1BIEoUhycnKwt7fH1dWVWbNmfepwPorU1FSqVq1KXFyc3BqUQukQExND8+bNSU5OlmbU/VBsTAqfHEoQBEEQAK7dO/vBrxFt2qdE8ml3Z0uJ5PNvIFoWBaEI0tLS2LdvH61atSIjI4Pg4GBu3LhB//79P3VoglAs27dvR1dXFxsbG5KTkxk3bhxOTk4fvKIoCIIgCP82Yo5uRaKyKAhFoKKiQlhYGF5eXuTm5lKrVi0OHDigsJbhh6Srq/veY3v27KFFixYfLZbiSE9PL3BSocuXL2Nubv4RI/q8PXv2DG9vb9LT0ylXrhzt27dn4cKFnzosQRAEQfjoRDdURaIbqiD8xyQnJ7/3WKVKldDS0vqI0RRdVlYWqamp7z1uaWmJmpr4HetzILqhCoIgCMr6GN1Q95n2LZF8vrgTUSL5/BuIb2SC8B9jbW39qUP4R9TU1P7zZRAEQRAEofQR3VAVicqiIAiCIAiCIAifPVFZVCQWuRIEQRAEQRAEQRAUiJZFQRAEQRAEQRA+e2KCG0WiZVH4IPz8/Iq8Bl/r1q0ZP378J4+jIMrEaGlpyQ8//FBi1xTyFxYWhqGh4acOo0TIZDJ27Nghvb5y5QpNmjRBU1Pzk6xl6eHhQY8ePT76dQVBEAThU8qRlcxWmojKovBBeHl5ER0dXaRztm3b9tksbP9PvX79mvnz59OgQQN0dHQwMDCgbt26TJs2jT///POjxPBuBedTCwsLQyaT0bFjR7n9jx8/RiaTcfjw4RK93vt+FCjODxS3bt2iU6dO0usZM2ago6NDUlJSkf+OSsKSJUsICwuTXn+IH3IEobRyG9KbQ2d/4+LNWH6JCqdO/ZoFpu/YrT1RsVu5eDOWyCNbaNXeSSFNNRtLVm5YxLmUIySkHmPrvvVUqGQml6aeY23Wb1tJQuox4q4fYdPOEDQ0NUq0bIJQ2uUgK5GtNBGVRaFE5ebmkpWVha6uLsbGxkU618jICD09vQ8UWemRkZFBhw4dmDNnDh4eHvz+++9cuHCBpUuXcv/+fYKCgt577uvXrz9ipB+fmpoaBw4c4NChQ586lCIxMzNDQ+PvL3UpKSk0b94cCwuLIv8dvfFPnrWBgUGpabUVhI+pc48OfDdzIsELVtOjnRuJl66y7qdgjMqVzTd9/YZ1WLxqNr9s3EH3tv05sOcwy8MXYmNXTUpjblmZzZFruX4tlQE9huPSui/LFq4hIyNDSlPPsTbrtgRz7PAJejkP4ssOg9iw9idyc8R0HYIg/DOisigUKiMjA09PT8qXL4+mpibNmzfn9OnTABw+fBiZTMaePXtwcHBAQ0ODY8eOKbSuZGVl4enpiaGhIcbGxnh7e+Pu7i7X1e3d1gtLS0vmzJnDkCFD0NPTw9zcnNWrV8vF5u3tja2tLdra2lhZWeHr60tmZmaxyqlMjO+6e/cuLi4uaGlpUbVqVTZu3KiQRiaTsWrVKrp27Yq2tjb29vYcP36c5ORkWrdujY6ODs2aNSMlJUWpOBcvXsyxY8c4ePAgnp6eODg4YG5uTqtWrVi5ciVz5syR0rZu3ZoxY8Ywfvx4ypUrh7OzMwCLFi2idu3a6OjoUKVKFUaNGsXz588BePHiBfr6+vzyyy9y192xYwc6Ojo8e/ZMqTjXrFmDvb09mpqa2NnZsXz5culYs2bN8Pb2lkt/7949ypQpw++//w7kve+8vLyoVKkSOjo6NG7cuNDWQR0dHYYMGcKUKVMKTHfhwgXatm2LlpYWxsbGDB8+XCo//N0Nc8GCBVSoUAFjY2NGjx5drPdW69at8fT0ZPLkyRgZGWFmZoafn59cmrdbaWUyGWfPnmXmzJnIZDIprbIxz549m4oVK1K9enVSU1ORyWT89NNPtGjRAi0tLRo2bMjVq1c5ffo0jo6O6Orq0qlTJ+7du6eQ15t/HzlyhCVLliCTyZDJZNy4cQNra2sWLFggV474+HhkMlmBa4EKQmk2ZMQAtvy4na2bfyP56g2me83hr79e8VX/7vmmdx/ej6MHj7Nm2QZSrqXyQ+AKLp+/wsChrlKaCd+N4siBGObNXMrlC0mkp/7Bwb2/8/D+IynN1Fnfsj4kgtVLw0hOus6NlDT2/Lqf16+L9/+hIHyucktoK01EZVEo1OTJk9m6dSvh4eGcO3cOa2trnJ2defjwoZRmypQpBAYGkpiYSJ06dRTymDt3Lhs3biQ0NJSYmBiePn2qVBfGhQsX4ujoSFxcHKNGjWLkyJEkJSVJx/X09AgLC+Py5cssWbKEkJAQFi9eXKxyFidGDw8Pbt68yaFDh/jll19Yvnw5d+/eVUg3a9YsBg0aRHx8PHZ2dvTv359vvvkGHx8fzpw5Q25uLmPGjFEqzs2bN9OhQwfq16+f73GZTL77Q3h4OOrq6sTExLBy5UoAVFRUWLp0KZcuXSI8PJyDBw8yefJkIK/C1bdvX0JDQ+XyCQ0N5auvvlKq9Xfjxo1Mnz6d2bNnk5iYyJw5c/D19SU8PBwANzc3IiIiyM39+yN1y5YtVKxYkRYtWgAwZswYjh8/TkREBOfPn6d379507NiRa9euFXhtPz8/Lly4oFDZfePFixc4OztTtmxZTp8+zc8//8yBAwcU7v+hQ4dISUnh0KFDhIeHExYWJtc1syjCw8PR0dHh5MmTzJs3j5kzZ7J///580966dYuaNWvy7bffcuvWLby8vJSOOTo6mqSkJPbv309kZKS0f8aMGUybNo1z586hpqZG//79mTx5MkuWLOHo0aMkJyczffr0fONZsmQJTZs25euvv+bWrVvcunULc3NzhgwZku97pGXLlmIdTeGzVKaMGjXr2hF75JS0Lzc3l9jfT1HfsXa+59R3rEPs7yfl9h09dJx6jnn/j8pkMlp3aE5qSjrrfgrmxOX9/BIVTvtOraX0RuXKUs+xNg/uP2TLrnUcv7SPjb+uxqFxvRIvoyCUdjkltJUmorIoFOjFixesWLGC+fPn06lTJ2rUqEFISAhaWlqsXbtWSjdz5kw6dOhAtWrVMDIyUsgnKCgIHx8fevbsiZ2dHcHBwUp1c+vcuTOjRo3C2toab29vypUrJ9fFcNq0aTRr1gxLS0tcXFzw8vLip59+KlZZixrj1atX2bNnDyEhITRp0gQHBwfWrl3LX3/9pZB28ODBuLq6Ymtri7e3N6mpqbi5ueHs7Iy9vT3jxo1Tekzd1atXqV69uty+nj17oquri66uLs2aNZM7ZmNjw7x586hevbp03vjx42nTpg2Wlpa0bduW77//Xu6+DRs2jL1793Lr1i0grwV19+7dDBkyRKkYZ8yYwcKFC/nyyy+pWrUqX375JRMmTGDVqlUAuLq68ueff3Ls2DHpnE2bNtGvXz9kMhnp6emEhoby888/06JFC6pVq4aXlxfNmzdXqKC8q2LFiowbN46pU6eSlZWlcHzTpk28evWK9evXU6tWLdq2bUtwcDAbNmzgzp07UrqyZcsSHByMnZ0dXbt2pUuXLsUeP1inTh1mzJiBjY0NgwYNwtHR8b15mZmZoaamhq6uLmZmZujq6iods46ODmvWrKFmzZrUrPn3OCkvLy+599rZs2fx9fXFycmJ+vXrM3To0Pd23TUwMEBdXR1tbW3MzMwwMzNDVVUVDw8PkpKSOHUq74txZmYmmzZteu97JCMjg6dPn8ptubml7b9U4XNW1sgQNTU17t97ILf/wd0HmJQvl+855cobc//uQ7l99+89xKR8XvdzYxMjdHV1GO7pwe/RsQx2Hc2+3YdYFjafRs0aAGBuUQmAsZOG89OP2xnadyyXzl9h/dYVWFhVKeliCoLwmRGVRaFAKSkpZGZm4uT094D7MmXK0KhRIxITE6V9jo6O783jyZMn3Llzh0aNGkn7VFVVcXBwKPT6b7dSymQyzMzM5FrutmzZgpOTk/Sletq0aaSnpytdvn8SY2JiImpqanJp7Ozs8q1gvl0OU1NTAGrXri2379WrVzx9+rTIsQMsX76c+Ph4hgwZwsuXL+WO5VeGAwcO0K5dOypVqoSenh4DBw7kwYMH0rmNGjWiZs2aUkvgjz/+iIWFBS1btiw0lhcvXpCSksLQoUOlCqyuri7ff/+91NXWxMSEL774Quq2e+PGDY4fP46bmxuQ1+UyOzsbW1tbuTyOHDmiVHddb29v7t27x7p16xSOJSYmUrduXXR0dKR9Tk5O5OTkyLVa16xZE1VVVel1hQoV8m01Vsa7re1FzUvZmGvXro26unqB13/f+6+oZatYsSJdunSR7vFvv/1GRkYGvXv3zjd9QEAABgYGctvDl7eLdE1B+Nyo/H9PkeioI4St2kTixausXhrGoX1H6efeCwCZSt5XuYj129i6+TcuX0hiju8irienvbf7qyAI+cuRyUpkK01EZVEoEW9/iS1JZcqUkXstk8nI+f8B+28qF507dyYyMpK4uDimTp36r5zE5e1yvOkmmt++HCUmI7CxsZGrIEBe5cPa2jrfVt13n01qaipdu3alTp06bN26lbNnz7Js2TJAflKUYcOGSd0uQ0NDGTx4sEIX1/y8GUcXEhJCfHy8tF28eJETJ05I6dzc3Pjll1+kFqnatWtLFZjnz5+jqqrK2bNn5fJITExkyZIlhcZgaGiIj48P/v7+CpVnZRX03gPQ19fnyZMnCuc9fvwYAwODIuVVUt73d6jM+6848QwbNoyIiAj++usvQkND6dOnD9ra2vmm9fHx4cmTJ3KbkbZZvmkF4b/o0cPHZGVlUc5EflIq4/LG3Lt7P99z7t99QLny8p/b5UyMuHf3gZRnZmYWyVevy6VJuXqDCpXz/n7u3cnLOznpnTTXblCxkvgbE4SiEGMWFYnKolCgatWqSePd3sjMzOT06dPUqFFDqTwMDAwwNTWVJsUByM7O5ty5c/8ottjYWCwsLJg6dSqOjo7Y2NiQlpZWrLyKE6OdnR1ZWVmcPXtW2peUlMTjx4+LFYOy+vXrx/79+4mLiyvW+WfPniUnJ4eFCxfSpEkTbG1t811uY8CAAaSlpbF06VIuX76Mu7u7UvmbmppSsWJFrl+/jrW1tdxWtWpVKV337t159eoVUVFRbNq0SWpVBKhfvz7Z2dncvXtXIQ8zM+W+/IwdOxYVFRWFyqW9vT0JCQm8ePFC2hcTE4OKiopC996CVK9eXe7Zv3Hu3DlsbW2VzkcZJRVzcamrq5Odna2wv3Pnzujo6LBixQqioqIK7KasoaGBvr6+3CaTif+ChNIjMzOLSwlXaNqyobRPJpPRrEVD4s5cyPecuDPnadqikdw+p1aNiT9zXsrzQtwlqlazkEtjWc2CP2/mtcz/kf4nt2/dxcraUi5N1Wrm/O+PW/+0WIIgfObUPnUAwr+bjo4OI0eOZNKkSRgZGWFubs68efN4+fIlQ4cOJSEhQal8xo4dS0BAANbW1tjZ2REUFMSjR4+Uaql6HxsbG9LT04mIiKBhw4bs2rWL7du3Fzu/osZYvXp1OnbsyDfffMOKFStQU1Nj/PjxaGlpFTsGZUyYMIFdu3bRrl07ZsyYQYsWLShbtqw0hvLtrpP5sba2JjMzk6CgIFxcXOQmvnlb2bJl+fLLL5k0aRJffPEFlStXVkhz48YN4uPj5fbZ2Njg7++Pp6cnBgYGdOzYkYyMDM6cOcOjR4+YOHEikPfe6tGjB76+viQmJtKvXz8pD1tbW9zc3Bg0aBALFy6kfv363Lt3j+joaOrUqUOXLl0KvU+ampr4+/szevRouf1ubm7MmDEDd3d3/Pz8uHfvHmPHjmXgwIFSF01lTJgwgRYtWjB79my+/PJLsrOz2bx5M8ePH5eb+bUklFTMxWVpacnJkydJTU1FV1cXIyMjVFRUpLGLPj4+2NjY0LRp0w8eiyD8m61b+SPzgvy5GJ/I+XMX8fimP1raWmzdvBOAecH+3Ll9j4XfBwMQvnozG38NYcjIARzef4wuPb+gVr0aTPt2tpTnmmUb+CEkgNPH4zgRc5qWbZvR1rkFA3p8I6VZu2w9npNHcOXSVS5fTOLLPi5YWVsydoj8rNOCIBRMjKRXJH7WFQoVGBhIr169GDhwIA0aNCA5OZm9e/dStmz+60blx9vbm379+jFo0CCaNm2Krq4uzs7OaGpqFjuubt26MWHCBMaMGUO9evWIjY3F19e32PkVJ8bQ0FAqVqxIq1at+PLLLxk+fDjly5cvdgzK0NTUJDo6Gm9vb0JDQ2nevDn29vaMHz8eJyenQmdwrVu3LosWLWLu3LnUqlWLjRs3EhAQkG/aoUOH8vr16/e2GE2cOJH69evLbXFxcQwbNow1a9YQGhpK7dq1adWqFWFhYXIti5BXCUpISKBFixaYm5vLHQsNDWXQoEF8++23VK9enR49enD69GmFdAVxd3fHyspKbp+2tjZ79+7l4cOHNGzYkK+++op27doRHBysdL6Qt/zHnj172LNnD05OTrRu3ZrY2Fiio6OpVatWkfIqTEnFXFxeXl6oqqpSo0YNTExM5MYFv3mPDB48+KPEIgj/Zrt37CfQ7wfGeY9g56HN2NeqztA+Y3lwL28Sm4qVzShv+vdkN3GnzzNxxFT6DOrJb4c309GlHaPcv+Xalb/HZu/ffYgZk+bw9dhB7DqyBdcBPRgzeDJnT8ZLacJWbWblklC+mzWR3w5F0LRFQzx6jyY99Y+PVnZBKA1yZCWzlSay3LfnrheEjyQnJwd7e3tcXV2ZNWvWpw4nX/+FGD+0DRs2MGHCBP788898J04RhKNHj9KuXTtu3rxZ5FZOG5PCJ7kSBEEQBIBr9xSHfpS0zRXdCk+khH5/Kq67/V8luqEKH0VaWhr79u2jVatWZGRkEBwczI0bN+jfv/+nDk3yX4jxY3n58iW3bt0iMDCQb775RlQUBQUZGRncu3cPPz8/evfu/VG6wwqCIAjCh5RDKWsWLAGiG6rwUaioqBAWFkbDhg1xcnLiwoULHDhwAHt7+48Ww9tLMLy7HT169F8RI+Qt2fC+ON8sNfGhzZs3Dzs7O8zMzPDx8fko1xT+WzZv3oyFhQWPHz9m3rx5nzocQRAEQfjHxGyoikQ3VOGzkZyc/N5jlSpV+uAT0ygrLS2NzMzMfI+Zmpqip6f3kSMShA9DdEMVBEEQlPUxuqGurzSgRPIZ9L8fSySffwPRDVX4bFhbW3/qEJRiYWFReCJBKAWeZRZvDUxBEARBED4OUVkUBEEQBEEQBOGzJ5bOUCQqi4IgCIIgCIIgfPbE2DxFYoIbQfgP8fPzo169ekU6p3Xr1owfP/6TxuHn54epqSkymYwdO3bg4eFBjx49SjSmkhYWFoahoeGnDuNfRdwTQRAEQfi8iMqiIPyHeHl5ER0dXaRztm3b9knXiUxMTMTf359Vq1Zx69YtOnXqxJIlSwgLC/tH+VpaWvLDDz+USIyfSmpqKjKZjPj4eGnfs2fPaNOmDTVq1OCPP4q/oHZxflgoTJ8+fbh69WqJ5ikIpc3gYf05ff4Aqbfj2X0ggvoNaheY3qW7M0dP7SL1djyHYn6lXYeWCmlsbK0I37yMq2mnuP6/s0Qd/IlKlSvkm9+mn1dx+3EiHbu0K5HyCMLnJEdWMltpIiqLgvAfkJubS1ZWFrq6uhgbGxfpXCMjo086g2pKSgoA3bt3x8zMDA0NDQwMDApsoXr9+vVHiu7DXut9s9q+z71792jTpg0vXrzg6NGjVK5cucjXfPNe+RC0tLQoX778B8lbEEqD7j074Tfbm4Vzl/FFq15cupjE5m0hlCtnlG96x0b1WLF2AZs3bKVDyy/Zszua0I1B2NnbSGksLKvwa9RGkq/e4EsXd9o49WDR/BVkvMpQyG/4KHfEHPeCUHw5JbSVJqKyKAifSEZGBp6enpQvXx5NTU2aN2/O6dOnATh8+DAymYw9e/bg4OCAhoYGx44dU2gtysrKwtPTE0NDQ4yNjfH29sbd3V2ui+e73VAtLS2ZM2cOQ4YMQU9PD3Nzc1avXi0Xm7e3N7a2tmhra2NlZYWvr2+RKz6Q17rl4uIC5K21KZPl/dz2bjfU1q1bM2bMGMaPH0+5cuVwdnYmNzcXPz8/zM3N0dDQoGLFinh6ekrp09LSmDBhAjKZTMoXYOvWrdSsWRMNDQ0sLS1ZuHChXEyWlpbMmjWLQYMGoa+vz/Dhw4G8Lpbm5uZoa2vTs2dPHjx4oFCeX3/9lQYNGqCpqYmVlRX+/v5yFTOZTMaKFSvo1q0bOjo6zJ49W+l7dfPmTVq0aIGBgQEHDx7E2Ng435bHx48fI5PJOHz4MJD/e+XHH3/E39+fhIQE6f68aclNT0+ne/fu6Orqoq+vj6urK3fu3JHyT0hIoE2bNujp6aGvr4+DgwNnzpyR7tHblfyC0grC5+ib0e5sDP+ZiI3buZqUwuQJfvz18hV9B3yZb/qvRwzi0IFjLA9ax7Wr15k3eykXEhIZ/HV/KY2P73ii9//OrBkLuHg+kbTUm+zbc4j79x/K5VWzth0jRnswfszUD1pGQRA+L6KyKAifyOTJk9m6dSvh4eGcO3cOa2trnJ2defjw7y8AU6ZMITAwkMTEROrUqaOQx9y5c9m4cSOhoaHExMTw9OlTduzYUei1Fy5ciKOjI3FxcYwaNYqRI0eSlJQkHdfT0yMsLIzLly+zZMkSQkJCWLx4cZHL6OXlRWhoKAC3bt3i1q1b700bHh6Ouro6MTExrFy5kq1bt7J48WJWrVrFtWvX2LFjB7Vr53Xn2rZtG5UrV2bmzJly+Z49exZXV1f69u3LhQsX8PPzw9fXV6HL64IFC6hbty5xcXH4+vpy8uRJhg4dypgxY4iPj6dNmzZ8//33cuccPXqUQYMGMW7cOC5fvsyqVasICwtTqBD6+fnRs2dPLly4wJAhQ5S6T0lJSTg5OVGjRg12796Nrq6uUue97e33SocOHfj222+pWbOmdH/69OlDTk4O3bt35+HDhxw5coT9+/dz/fp1+vTpI+Xj5uZG5cqVOX36NGfPnmXKlCmUKVMm32sWJa0glHZlypShTr2a/H7kuLQvNzeXo0eO49ioXr7nODSsK5ce4PDBY1J6mUxG+y9acT05lc1bQ7h47Ri7D0QodDHV0tJkRch8fCbN4t7d+yVaLkH4nIiWRUViNlRB+ARevHjBihUrCAsLo1OnTgCEhISwf/9+1q5dS8OGDQGYOXMmHTp0eG8+QUFB+Pj40LNnTwCCg4PZvXt3odfv3Lkzo0aNAvJaERcvXsyhQ4eoXr06ANOmTZPSWlpa4uXlRUREBJMnTy5SOXV1daWWKDMzswLT2tjYMG/ePOn1rl27MDMzo3379pQpUwZzc3MaNWoE5HWtVVVVRU9PTy7fRYsW0a5dO3x9fQGwtbXl8uXLzJ8/Hw8PDyld27Zt+fbbb6XXvr6+dOzYUSqfra0tsbGxREVFSWn8/f2ZMmUK7u7uAFhZWTFr1iwmT57MjBkzpHT9+/dn8ODBRblNDBo0CCcnJ37++WdUVVWLdO4b775XdHV1UVNTk7s/+/fv58KFC9y4cYMqVaoAsH79emrWrMnp06dp2LAh6enpTJo0CTs7OyDvubxPUdIKQmlnZGyImpoa9+7K90q4d/cB1jZV8z2nvGk5hcrdvbsPKF++HADlTIzR1dNh7PhhBM5eyvd+C2nTrjnrNiyll4sHx2PyeqP4z5nC6VPx7N198AOUTBA+H7mlbLxhSRAti4LwCaSkpJCZmYmTk5O0r0yZMjRq1IjExERpn6Oj43vzePLkCXfu3JEqUACqqqo4ODgUev23WyllMhlmZmbcvXtX2rdlyxacnJwwMzNDV1eXadOmkZ6ernT5iuPduHv37s1ff/2FlZUVX3/9Ndu3by90LF5iYqLcPQVwcnLi2rVrZGdnS/veva+JiYk0btxYbl/Tpk3lXickJDBz5kx0dXWl7euvv+bWrVu8fPn34vIFPbP36datG0ePHmXbtm1FPrco101MTKRKlSpSRRGgRo0aGBoaSu+7iRMnMmzYMNq3b09gYKA05jQ/RUmbkZHB06dP5bbc3NL2+6sglCwVlbxvrlG7D7J6eTiXLlwh+Ic17N97mEGD83oEfNGpDc1bNsHXJ+BThioIQiklKouC8C+mo6PzQfJ9t6ugTCYjJyfvi/vx48dxc3Ojc+fOREZGEhcXx9SpUz/4pDPvlrVKlSokJSWxfPlytLS0GDVqFC1btizW2MnCrqWM58+f4+/vT3x8vLRduHCBa9euoamp+Y/ynjp1KtOnT6d///789NNP0n4VlbyP6Ny3Zqx4X/lL6r3i5+fHpUuX6NKlCwcPHqRGjRps3779H6cNCAjAwMBAbnuRoTguVBD+qx4+eExWVhYm5eUnITMpb8zd93QNvXvnPib/34qYX/qHDx6TmZnJ1ST5H2KuJV2XZkNt3rIJllWrcDXtJH/cv8Af9y8AsHb9ErZFhpdI2QThcyG6oSoSlUVB+ASqVasmjc97IzMzk9OnT1OjRg2l8jAwMMDU1FSaFAcgOzubc+fO/aPYYmNjsbCwYOrUqTg6OmJjY0NaWto/yrO4tLS0cHFxYenSpRw+fJjjx49z4ULeFyF1dXW51kIAe3t7uXsKEBMTg62tbYHdO+3t7Tl58qTcvhMnTsi9btCgAUlJSVhbWytsbyp1/4Svry9+fn64ubmxZcsWAExMTADkxnq+PdlNQd53f27evMnNmzelfZcvX+bx48dy7ztbW1smTJjAvn37+PLLL6Vxp/lRNq2Pjw9PnjyR23Q0ijazryD8m2VmZnI+/hItWjWR9slkMpq3bMKZU/H5nnP2dIJceoCWrZtJ6TMzM4k/d5Fq73RjtbK25I+bfwIQtDiEtk49aN/iS2kDmP5dIONHf1dCpROEz4OoLCoSYxYF4RPQ0dFh5MiRTJo0CSMjI8zNzZk3bx4vX75k6NChJCQkKJXP2LFjCQgIwNraGjs7O4KCgnj06JHc7KBFZWNjQ3p6OhERETRs2JBdu3a9t7XoQwoLCyM7O5vGjRujra3Njz/+iJaWFhYWFkDeWMrff/+dvn37oqGhQbly5fj2229p2LAhs2bNok+fPhw/fpzg4GCWL19e4LU8PT1xcnJiwYIFdO/enb1798qNVwSYPn06Xbt2xdzcnK+++goVFRUSEhK4ePGiwmQ4xTV16lRUVVVxc3MjJyeHfv360aRJEwIDA6latSp3796VG09aEEtLS27cuEF8fDyVK1dGT0+P9u3bU7t2bdzc3Pjhhx/Iyspi1KhRtGrVCkdHR/766y8mTZrEV199RdWqVfnjjz84ffo0vXr1Usi/KGkBNDQ00NDQkNsnk4nfK4XSZdWycJasCCAh7iJxZy/w9chBaOtoEbEx7zM0aGUgt/68w5yZeROGhaxcz/Zd6xkxxoMDe4/Qo1dn6tavyaTxf4+DXh60jlXrFnIi5gwxR0/Stn1zvujYmi+75o2fvnf3fr6T2vzvj1ukp/3vI5RaEEoPsfKMIvE/tSB8IoGBgfTq1YuBAwfSoEEDkpOT2bt3L2XLllU6D29vb/r168egQYNo2rQpurq6ODs7y3WLLKpu3boxYcIExowZQ7169YiNjZUmjPmYDA0NCQkJwcnJiTp16nDgwAF+++03aZ3JmTNnkpqaSrVq1aQWuAYNGvDTTz8RERFBrVq1mD59OjNnzpSb3CY/TZo0ISQkhCVLllC3bl327dunUClzdnYmMjKSffv20bBhQ5o0acLixYulymtJmTJlCnPmzGHgwIFs2rSJdevWkZWVhYODA+PHj1e6YtqrVy86duxImzZtMDExYfPmzchkMn799VfKli1Ly5Ytad++PVZWVlJLpqqqKg8ePGDQoEHY2tri6upKp06d8Pf3V8i/KGkF4XPx6/Y9zPSdx+TvPDlwdDu1atvRr9dw7t/L63JdqXIFy92R1wAAZulJREFUTM1MpPRnTsUzatgkBri7En1sB127OTPYbSxXEq9JafZEHsB7oj+jxw3lUOyv9B/0FUMHjePUiX/Wi0QQBEEZstxcsXyrIJQWOTk52Nvb4+rqyqxZsz51OIJQIDND+08dgiAIgvAfcftxYuGJ/qEl5gNKJJ9x6T+WSD7/BqIbqiD8h6WlpbFv3z5atWpFRkYGwcHB3Lhxg/79+xd+siAIgiAIgiApbeMNS4LohioI/2EqKiqEhYXRsGFDnJycuHDhAgcOHMDe/uO12Ly9lMS729GjRz9aHP9GI0aMeO+9GTFixKcOTxAEQRAEoUCiG6ogCP9IcnLye49VqlQJLS2tjxjNv8vdu3d5+vRpvsf09fUpX778R47o30V0QxUEQRCU9TG6oS4soW6o34puqIIgCHmsra0/dQj/WuXLl//sK4SCIAiC8F8hWtAUicqiIAiC8Ek8/OvZpw5BEARBEIQCiMqiIAiCIAiCIAifvZziL1NdaonKoiAIgiAIgiAInz0xG6oiMRuqIAgK/Pz8qFevXpHOad26NePHj//kcRTkQ8QoCIIgCIJQWonKoiAICry8vIiOji7SOdu2bWPWrFkfKKLS4/bt24wdOxYrKys0NDSoUqUKLi4uRb7fhfmYFWNRCReEv40Y4c7VpOM8fZLMsaO/4ehYr8D0vb7swoXzh3n6JJlzZw/QsWNbhTR2dtZs27qOe3cv8+jhVWJjIqlSpaJ0fOhQN/bv+5n79xJ5nfEHBgb6JV0sQfgs5JbQVhzLli3D0tISTU1NGjduzKlTpwpM//PPP2NnZ4empia1a9dm9+7dcsefP3/OmDFjqFy5MlpaWtSoUYOVK1cWOS5RWRQEQZKbm0tWVha6uroYGxsX6VwjIyP09PQ+UGSlQ2pqKg4ODhw8eJD58+dz4cIFoqKiaNOmDaNHj/7o8bx53oIglIzeX7kwf950vp+9mMaNO3H+wmV2Rf6IiUn+n6dNmjiwYcMyQsMiaNS4Izt3RvHLz2uoWaO6lMbKyoJDB7eTlJRChw69cXDswJyAJbx6lSGl0dbWZN++w8ydG/zByygIpVkOuSWyFdWWLVuYOHEiM2bM4Ny5c9StWxdnZ2fu3r2bb/rY2Fj69evH0KFDiYuLo0ePHvTo0YOLFy9KaSZOnEhUVBQ//vgjiYmJjB8/njFjxrBz584ixSYqi4JQymVkZODp6Un58uXR1NSkefPmnD59GoDDhw8jk8nYs2cPDg4OaGhocOzYMYXun1lZWXh6emJoaIixsTHe3t64u7vTo0cPKc27rUuWlpbMmTOHIUOGoKenh7m5OatXr5aLzdvbG1tbW7S1tbGyssLX15fMzMxilVOZGPO7N97e3lSpUgUNDQ2sra1Zu3at3L3Zu3cv9evXR0tLi7Zt23L37l327NmDvb09+vr69O/fn5cvXyoV46hRo5DJZJw6dYpevXpha2tLzZo1mThxIidOnJDSpaen0717d3R1ddHX18fV1ZU7d+5Ix988nw0bNmBpaYmBgQF9+/bl2bO82UU9PDw4cuQIS5YsQSaTIZPJSE1Nfe/zTklJoXv37piamqKrq0vDhg05cOCAXOzLly/HxsYGTU1NTE1N+eqrrwq8liB8jsaNG87adZtZv/4nEq9cY/ToKbx8+QoP9775ph87Zih79x1m0aKVXLmSjJ//AuLiLjJylIeUZqb/ZKKiDuLz3WziEy5x/XoakZH7uXfvgZQmKGgt8xcs4+Spcx+6iIJQquWU0JaRkcHTp0/ltoyMjHcvJ1m0aBFff/01gwcPlloAtbW1WbduXb7plyxZQseOHZk0aRL29vbMmjWLBg0aEBz89w9GsbGxuLu707p1aywtLRk+fDh169YttMXyXaKyKAil3OTJk9m6dSvh4eGcO3cOa2trnJ2defjwoZRmypQpBAYGkpiYSJ06dRTymDt3Lhs3biQ0NJSYmBiePn3Kjh07Cr32woULcXR0JC4ujlGjRjFy5EiSkpKk43p6eoSFhXH58mWWLFlCSEgIixcvLlY5ixPjoEGD2Lx5M0uXLiUxMZFVq1ahq6srl8bPz4/g4GBiY2O5efMmrq6u/PDDD2zatIldu3axb98+goKCCo3v4cOHREVFMXr0aHR0dBSOGxoaApCTk0P37t15+PAhR44cYf/+/Vy/fp0+ffrIpU9JSWHHjh1ERkYSGRnJkSNHCAwMBPL+E2natClff/01t27d4tatW1SpUkU6993n/fz5czp37kx0dDRxcXF07NgRFxcX0tPTAThz5gyenp7MnDmTpKQkoqKiaNmypVLXEoTPRZkyZWjQoDYHDx6V9uXm5nLw4FGaNGmQ7zmNGzvIpQfYv/8ITRo7ACCTyejUqR3Xrl0nMvJH/rgZz7Gjv9Gtm/OHK4ggCP9YQEAABgYGcltAQEC+aV+/fs3Zs2dp3769tE9FRYX27dtz/PjxfM85fvy4XHoAZ2dnufTNmjVj586d/O9//yM3N5dDhw5x9epVvvjiiyKVRcyGKgil2IsXL1ixYgVhYWF06tQJgJCQEPbv38/atWtp2LAhADNnzqRDhw7vzScoKAgfHx969uwJQHBwsELf+Px07tyZUaNGAXmtiIsXL+bQoUNUr57XxWratGlSWktLS7y8vIiIiGDy5MlFLmtRY7x69So//fQT+/fvlz5wraysFNJ9//33ODk5ATB06FB8fHxISUmR0n711VccOnQIb2/vAuNLTk4mNzcXOzu7AtNFR0dz4cIFbty4IVW61q9fT82aNTl9+rT0zHJycggLC5O6/g4cOJDo6Ghmz56NgYEB6urqaGtrY2ZmpnCNd5+3kZERdevWlV7PmjWL7du3s3PnTsaMGUN6ejo6Ojp07doVPT09LCwsqF+/PkCh13ojIyND4VfV3NxcZDIxT7lQOpQrZ4Samhp37tyT23/37n2qV7fO9xwzMxPu3rkvt+/O3XuYmpoAUL58OfT0dJk0aTQz/OYx9bs5fPFFG37aEkKHL1w5evREftkKglBMxR1v+C4fHx8mTpwot09DQyPftPfv3yc7OxtTU1O5/aamply5ciXfc27fvp1v+tu3b0uvg4KCGD58OJUrV0ZNTQ0VFRVCQkKkH3uVJVoWBaEUS0lJITMzU6rsQN6v340aNSIxMVHa5+jo+N48njx5wp07d2jUqJG0T1VVFQcHh0Kv/3YrpUwmw8zMTK7//ZYtW3BycsLMzAxdXV2mTZsmtWYVRXFijI+PR1VVlVatWildBlNTU6nL7Nv73jem4G25ucr9F5SYmEiVKlXkWudq1KiBoaGh3DOztLSUGyNaoUIFpeIAxef9/PlzvLy8sLe3x9DQEF1dXRITE6Vn0aFDBywsLLCysmLgwIFs3LhR6a63b+T3K2tO9rMi5SEInxsVlbyvab/9to+lS9eQcP4y8xcsY/fuAwz/esAnjk4QSp+S6oaqoaGBvr6+3Pa+yuKHEhQUxIkTJ9i5cydnz55l4cKFjB49WmGYSWFEZVEQhHy7RZaEMmXKyL2WyWTk5OStYnT8+HHc3Nzo3LkzkZGRxMXFMXXqVF6/fv1BYnmXlpaWUuneLoNMJiuwTAWxsbFBJpO991fCoipuHKD4vL28vNi+fTtz5szh6NGjxMfHU7t2belZ6Onpce7cOTZv3kyFChWYPn06devW5fHjx0rH6+Pjw5MnT+Q2FVUxIZJQety//5CsrCypVfCN8uXLcedO/j/k3L59j/Km5eT2mZY3kVon799/SGZmJomJV+XSXLmSTJUqlUowekEQPpVy5cqhqqoqNzcBwJ07d97bY8fMzKzA9H/99RffffcdixYtwsXFhTp16jBmzBj69OnDggULihSfqCwKQilWrVo11NXViYmJkfZlZmZy+vRpatSooVQeBgYGmJqaSpPiAGRnZ3Pu3D+bSCE2NhYLCwumTp2Ko6MjNjY2pKWlFSuv4sRYu3ZtcnJyOHLkSLGuWVRGRkY4OzuzbNkyXrx4oXD8TcXL3t6emzdvcvPmTenY5cuXefz4sdLPDEBdXZ3s7Gyl0sbExODh4UHPnj2pXbs2ZmZmCpPUqKmp0b59e+bNm8f58+dJTU3l4MGDSl8rv19ZRRdUoTTJzMzk3LkLtGnTXNonk8lo06Y5J07k/1l08uRZ2r6VHqBduxacOHlWyvPMmQRsbavJpbGxsSI9/X8lXAJBEHJkJbMVhbq6Og4ODnJLaOXk5BAdHU3Tpk3zPadp06YKS27t379fSp+ZmUlmZqbUO+ENVVVVpX9YfkOMWRSEUkxHR4eRI0cyadIkjIyMMDc3Z968ebx8+ZKhQ4eSkJCgVD5jx44lICAAa2tr7OzsCAoK4tGjR//oy76NjQ3p6elERETQsGFDdu3axfbt24udX1FjtLS0xN3dnSFDhrB06VLq1q1LWload+/exdXVtdhxFOT/2rv3uJzv//Hjj0sl6UqkE1auqSjkVM425+W8GfJZrZjGPnIYEzlrmGzOar+MRdnHeXOapBL5TGFR2qaEZtqBchpin5Su3x++e8+lUCmR593tfbvter2fr9f7+Xpfra7X9X69X+/PP/+cjh070qZNG+bOnUuzZs3Iz88nJiaGkJAQ0tLS6NGjB87Oznh6erJ8+XLy8/Px9fWlc+fOj50uXFT/jh07xi+//IJarcbMzOyRsQ4ODmzfvp3+/fujUqmYNWuWzh+TPXv28PPPP/P6669Tq1Yt9u7dS0FBgXLvaVHHevgPlBAvgxUrVhMauoykEykkHj/JuHHvY2xsRPj6LQCsDV3OH39cYuas+4tRBQWHErv/ayZMGEVkZCzuQ97ExaUZvr7/3AO9dOkqNmz4f3x3+BiHDiXwxhtd6Nu3Bz16DlFirKwssLaywM5OA0DTpo7k3Moh89c/uH79z2fWfyFedKV57EVZ+Oijjxg2bBiurq60adOG5cuXc/v2bd577z3g/oJ89erVUxbJ+fDDD+ncuTNLliyhb9++bN68mePHjyurzteoUYPOnTszefJkjIyMqF+/PocOHWL9+vUsXbq0RLnJX3MhKrmFCxcyaNAgvLy8aNWqFefOnSMqKopatWoVuw1/f3/eeecdvL29ad++PWq1Gjc3N6pVq1bqvAYMGMDEiRMZO3YsLVq0ICEhgVmzZpW6vdLkGBISwuDBg/H19cXR0ZGRI0cWedWvrDRo0ICkpCS6du3KpEmTaNq0KT179iQ2NpaQkBDg/pWIXbt2UatWLV5//XV69OhBgwYN2LJlS4mO5efnh56eHo0bN8bCwuKx94IuXbqUWrVq0aFDB/r374+bmxutWv2zemPNmjXZvn073bp1w8nJiVWrVrFp0yaaNGlS4mMJUZlt+/pb/KfOZ/ZsPxK/j6J5syb06+9Fdvb9RWxsbOphbW2pxB89egJv77G87+PJ8cRo3n67D4OHvM+p1H9Wjd61ex9jxk5j0qTRJJ3Yz4j33mHov0aRkPDPTIpRI71ITIzmi1WLADh4YDuJidH06/fohcuEEM+Pv6eHzp49mxYtWnDy5En27dunLGKTmZnJxYsXlfgOHTqwceNGVq9eTfPmzfn666/ZuXMnTZs2VWL+/jLe09OTxo0bs3DhQj755BP+/e9/lyg3lba4qy4IIcT/KSgowMnJCXd3d+bNm1fR6RTpRcjxZVfV8JWKTkEIIcQL4m7ub+V+jBkajzJp55NfNpZJO88DmYYqhHiiCxcuEB0dTefOncnNzSU4OJjz58/j4VE2v1TLwouQoxBCCCGeXyW7m+/lIINFIcQTValShbCwMPz8/NBqtTRt2pT9+/fj5OT0zHJQq9WP3BcZGYlGo6nQHDMzMx+7AE1qaiq2trbPJBchhBBCiLIgg0UhxBPZ2NjorKhaEU6ePPnIffXq1cPIyKhCc6xbt+5jc6xbt+6zS0YIIYQQJVZRC9w8z2SwKIR4Idjb21d0Co+lr6//3Of4vJFb5oUQQjxP5K9SYTJYFEIIIYQQQrz05J7FwuTRGUIIIYQQQgghCpHBohBlICAggBYtWpSoTpcuXZgwYUKF5/E45ZGjKFu//PILKpXqsfdLCiGEEOLJCtCWyVaZyGBRiDLg5+dHbGxsieps375dnv/3BMOHD+ett96q6DSemrOz8yMfgvvVV19haGjIlStXStW2jY0NFy9e1HkQrxCi4oz+9zDOnjnKrZsZxB/+ltauLR4bP2hQP3788RC3bmaQnLSfXr26FYpxdLRn+/Z1XLmcxp/Xz3IkIQIbm38WzXrfx5P9Mdu4euU0eXd/x9S0Rll3S4iXgraMtspEBotCPAWtVkt+fj5qtZratWuXqK6ZmRkmJibllJkoK3+/x0/Dx8eHzZs389dffxXat27dOgYMGIC5uXmJ27179y56enpYW1ujry+3oAtR0YYMGcCiRXOYP38pbdr24ocfUomI2ICFRdF/H9q3c+U/X33OunWbaN3GjV27o/jm61CaNGmkxDRoUJ+4gztJTz9Hj56DaeXSg08WLOd//8tVYqpXNyIqOo6FnwaVex+FEC8XGSwK8ZDc3FzGjx+PpaUl1apVo1OnTiQmJgIQFxeHSqUiMjISFxcXDA0NOXz4cKHpn/n5+YwfP56aNWtSu3Zt/P39GTZsmM5VsoeneGo0GhYsWMCIESMwMTHB1taW1atX6+Tm7+9Pw4YNqV69Og0aNGDWrFnk5eWVqp/FybGoc+Pv74+NjQ2GhobY29sTGhqqc26ioqJo2bIlRkZGdOvWjezsbCIjI3FycqJGjRp4eHhw586dUuXcpUsXxo8fz5QpUzAzM8Pa2pqAgABlv4eHB0OHDtWpk5eXh7m5OevXrwegoKCAwMBAXn31VYyMjGjevDlff/21Ev+o9zglJYWuXbtiYmJCjRo1cHFx4fjx40q9w4cP89prr2FkZISNjQ3jx4/n9u3bALz77rv89ddffPPNNzq5nT9/nri4OHx8fMjIyODNN9/EysoKtVpN69at2b9/v068RqNh3rx5eHt7U6NGDUaNGlVoGuq9e/fw8fFR+teoUSNWrFih087fV2wXL15MnTp1qF27NmPGjNH5WXrcew3w008/0bt3b9RqNVZWVnh5eZX66qgQlcWED0cSGrqR8PVbSUs7i++Yqdy58xfDh/+ryPix43yIiopj6dJVnD59joCARSQn/4Tv6PeUmLlz/dm37wDTpn3CyZOn+PnnC+zZE8Ply1eVmJVBX7Jo0eccO5ZU7n0UojIrKKOtMpHBohAPmTJlCt988w3h4eEkJSVhb2+Pm5sb165dU2KmTp3KwoULSUtLo1mzZoXa+PTTT9mwYQPr1q0jPj6emzdvsnPnzicee8mSJbi6upKcnIyvry+jR48mPT1d2W9iYkJYWBipqamsWLGCNWvWsGzZslL1szQ5ent7s2nTJlauXElaWhpffPEFarVaJyYgIIDg4GASEhL49ddfcXd3Z/ny5WzcuJGIiAiio6MJCir9t9/h4eEYGxtz7NgxPvvsM+bOnUtMTAwAnp6efPvtt+Tk5CjxUVFR3Llzh4EDBwIQGBjI+vXrWbVqFadOnWLixIm8++67HDp0SOc4D7/Hnp6evPLKKyQmJnLixAmmTp2KgYEBABkZGfTq1YtBgwbxww8/sGXLFg4fPszYsWMBMDc3580332Tt2rU6xwgLC+OVV17hjTfeICcnhz59+hAbG0tycjK9evWif//+ZGZm6tRZvHgxzZs3Jzk5mVmzZhU6PwUFBbzyyits27aN1NRUZs+ezfTp09m6datO3MGDB8nIyODgwYOEh4cTFhZGWFiYsv9x7/Wff/5Jt27daNmyJcePH2ffvn1kZWXh7u5e7PdRiMrGwMCAVq2aEXvgO6VMq9Vy4MBh2rVzKbJOu7YuHHggHiA6Jk6JV6lU9OndnTNnfyZizwZ+/y2F+MPfMmCAW/l1RIiXmLaM/lUmMm9JiAfcvn2bkJAQwsLC6N27NwBr1qwhJiaG0NBQWrduDcDcuXPp2bPnI9sJCgpi2rRpygAlODiYvXv3PvH4ffr0wdfXF7h/FXHZsmUcPHiQRo3uT0maOXOmEqvRaPDz82Pz5s1MmTKlxH0taY5nzpxh69atxMTE0KNHDwAaNGhQKG7+/Pl07NgRuD/9ctq0aWRkZCixgwcP5uDBg/j7+5c4Z4BmzZoxZ84cABwcHAgODiY2NpaePXvi5uaGsbExO3bswMvLC4CNGzcyYMAATExMyM3NZcGCBezfv5/27dsrfTh8+DBffPEFnTt3Vo7z8HucmZnJ5MmTcXR0VI79t8DAQDw9PZUrxQ4ODqxcuZLOnTsTEhJCtWrV8PHxoXfv3pw/f55XX30VrVZLeHg4w4YNo0qVKjRv3pzmzZsrbc6bN48dO3awe/duZdAJ0K1bNyZNmqS8/uWXX3TOj4GBAR9//LHy+tVXX+XIkSNs3bpVZzBXq1YtgoOD0dPTw9HRkb59+xIbG8vIkSOf+F4HBwfTsmVLFixYoJStXbsWGxsbzpw5Q8OGDQu9b7m5ueTm5uqUabVaVCpVoVghXkTm5mbo6+uTnaV7hT0r+zKNGtkVWcfa2oKs7Ms6ZdlZV7CysgDA0tIcExM1UyaPYc6cz5g+YwFvvNGFbVu/pEfPIXz33dHy6YwQQvwfubIoxAMyMjLIy8tTBjtw/8N3mzZtSEtLU8pcXV0f2caNGzfIysqiTZs2Spmenh4uLkV/s/ygB69SqlQqrK2tyc7OVsq2bNlCx44dsba2Rq1WM3PmzEJXnoqjNDmePHkSPT09nQHVk/pgZWWlTJl9sOzBPpXUw1dy69Spo7Snr6+Pu7s7GzZsAO4P/nft2oWnpycA586d486dO/Ts2RO1Wq1s69evJyMjQ6fdh9/jjz76iPfff58ePXqwcOFCnfiUlBTCwsJ02nRzc6OgoIDz588D0LNnT1555RXWrVsHQGxsLJmZmbz33v3pZjk5Ofj5+eHk5ETNmjVRq9WkpaUVen8f97P3t88//xwXFxcsLCxQq9WsXr26UDtNmjRBT0+vyPP4pPc6JSWFgwcP6vT370H0w+fxb4GBgZiamupsBQW3ntgXIV5mVarc/5i2+9soVqxcQ0rKKRYt+pyIvfsZNcqrgrMTovKRaaiFyZVFIUrB2Ni4XNr9e1rj31QqFQUF93/tHDlyBE9PTz7++GPc3NwwNTVl8+bNLFmypFxyeZiRkVGx4h7sg0qlemyfSuNJ7Xl6etK5c2eys7OJiYnByMiIXr16ASjTUyMiIqhXr55OO4aGhjqvH36PAwIC8PDwICIigsjISObMmcPmzZsZOHAgOTk5fPDBB4wfP75Qvra2tsD9D33Dhw8nPDycgIAA1q1bR9euXZWBtJ+fHzExMSxevBh7e3uMjIwYPHgwd+/efWxeD9u8eTN+fn4sWbKE9u3bY2JiwqJFizh27Fixz+OT3uucnBz69+/Pp59+WmhfnTp1iqwzbdo0PvroI50ys9qOjz2OEC+SK1eukZ+fj6WV7mJVVpYWXMq6XGSdS5cuY2VpoVNmaWVO1v/FX7lyjby8PNLSzurEnD59lo4d2iCEKFuV7bEXZUGuLArxADs7O6pWrUp8fLxSlpeXR2JiIo0bNy5WG6amplhZWSmL4sD9RUeSkp5u4YGEhATq16/PjBkzcHV1xcHBgQsXLpSqrdLk6OzsTEFBQaF7+543HTp0wMbGhi1btrBhwwaGDBmiDIwaN26MoaEhmZmZ2Nvb62w2NjZPbLthw4ZMnDiR6Oho3n77beUqYatWrUhNTS3Upr29PVWrVlXqv/fee/z6669s376dHTt24OPjo+yLj49n+PDhDBw4EGdnZ6ytrQtNMS2O+Ph4OnTogK+vLy1btsTe3v6RV/se5UnvdatWrTh16hQajaZQfx81mDU0NKRGjRo6m0xBFZVJXl4eSUk/0K1rJ6VMpVLRtWsnjh49UWSdo8dO0LVbJ52yHt1fV+Lz8vI4fjyFRg11p7E6ODTgQuZvZdwDIYQoTAaLQjzA2NiY0aNHM3nyZPbt20dqaiojR47kzp07Oh/sn2TcuHEEBgaya9cu0tPT+fDDD7l+/fpTfTh2cHAgMzOTzZs3k5GRwcqVK9mxY0ep2ytpjhqNhmHDhjFixAh27typrOT58MIpzwMPDw9WrVpFTEyMMgUV7i8Q5Ofnx8SJEwkPDycjI4OkpCSCgoIIDw9/ZHt//fUXY8eOJS4ujgsXLhAfH09iYiJOTk7A/ftLExISGDt2LCdPnuTs2bPs2rVL515DuH//YLdu3Rg1ahSGhoa8/fbbyj4HBwe2b9/OyZMnSUlJwcPDo1RXYB0cHDh+/DhRUVGcOXOGWbNm6XwpUBxPeq/HjBnDtWvXeOedd0hMTCQjI4OoqCjee+897t27V+Kchagslq9Yg4+PB15eQ3B0tOfz4IUYGxsRHr4FgHVrVzB//lQlPjgoFLc3ujBhwgc0amTHrFkf4eLSjP8Xsk6JWbI0hCFD+uMzwgM7Ow2+o4fTr29Pvlj1z+8sKysLmjdvgr2dBoCmTR1p3rwJtWrVfCb9FqKykOcsFiaDRSEesnDhQgYNGoSXlxetWrXi3LlzREVFUatWrWK34e/vzzvvvIO3tzft27dX7mGrVq1aqfMaMGAAEydOZOzYsbRo0YKEhIQiV8MszxxDQkIYPHgwvr6+ODo6MnLkSOXxEM8TT09PUlNTqVevns79p3B/4ZhZs2YRGBiIk5MTvXr1IiIigldfffWR7enp6XH16lW8vb1p2LAh7u7u9O7dW1lIplmzZhw6dIgzZ87w2muv0bJlS2bPnk3dunULteXj48P169fx8PDQOddLly6lVq1adOjQgf79++Pm5karVq1K3PcPPviAt99+m6FDh9K2bVuuXr2qLJpUEo97r+vWrUt8fDz37t3jjTfewNnZmQkTJlCzZk3lHishXkbbtu3G338ec2b7cTwxmubNG9Ov37tkZ99f9MbGpi51rK2U+CNHj+PlPZb33/fkxPEY3n67L4MG+3Dq1D+rYO/atY8xY6YyaZIvyUn7GTHCA/ehI4lP+OdLoFGjvDieGM0XXywGIO7gDo4nRtO/3xvPqOdCVA4FaMtkq0xUWq22cvVIiOdQQUEBTk5OuLu7M2/evIpOp0gvQo6icjGoWu/JQUIIIQSQd/f3cj/GSM2QMmlnzS/byqSd54EscCNEObhw4QLR0dF07tyZ3NxcgoODOX/+PB4eHhWdmuJFyFEIIYQQQlQcGSwKUQ6qVKlCWFgYfn5+aLVamjZtyv79+5V73J6Fvx+gXpTIyEg0Gk2F5piZmfnYRYNSU1OVlUSFEEIIIcqbtpJNIS0LMg1ViErq3Llzj9xXr169Yj8Ko7zk5+c/drVPjUaDvr58n1WZyTRUIYQQxfUspqGO0Awuk3bW/vJ1mbTzPJBPYkJUUvb29hWdwmPp6+s/9zkKIYQQQrzMZLAohBBCCCGEeOnJNNTCZLAohBBCCCGEeOmV/OnGlZ88EEsIIYQQQgghRCEyWBRCVCoBAQG0aNGiRHW6dOnChAkTKjyPxymPHMvai5CjEEII8SgFWm2ZbJWJDBaFEJWKn58fsbGxJaqzfft25s2bV04ZVQ7Dhw/nrbfequg0hHjujf73MM6eOcqtmxnEH/6W1q4tHhs/aFA/fvzxELduZpCctJ9evboVinF0tGf79nVcuZzGn9fPciQhAhubusr+93082R+zjatXTpN393dMTWuUdbeEeCloy2irTGSwKISoFLRaLfn5+ajVamrXrl2iumZmZpiYmJRTZkKIl8WQIQNYtGgO8+cvpU3bXvzwQyoRERuwsCj6d1L7dq7856vPWbduE63buLFrdxTffB1KkyaNlJgGDeoTd3An6enn6NFzMK1cevDJguX873+5Skz16kZERcex8NOgcu+jEOLlIoNFIcRzKzc3l/Hjx2NpaUm1atXo1KkTiYmJAMTFxaFSqYiMjMTFxQVDQ0MOHz5caPpnfn4+48ePp2bNmtSuXRt/f3+GDRumc5Xs4emTGo2GBQsWMGLECExMTLC1tWX16tU6ufn7+9OwYUOqV69OgwYNmDVrFnl5eaXqZ3FyLOrc+Pv7Y2Njg6GhIfb29oSGhuqcm6ioKFq2bImRkRHdunUjOzubyMhInJycqFGjBh4eHty5c6dUOd++fRtvb2/UajV16tRhyZIlpWpHiMpkwocjCQ3dSPj6raSlncV3zFTu3PmL4cP/VWT82HE+REXFsXTpKk6fPkdAwCKSk3/Cd/R7Sszcuf7s23eAadM+4eTJU/z88wX27Inh8uWrSszKoC9ZtOhzjh1LKvc+ClGZFaAtk60ykcGiEOK5NWXKFL755hvCw8NJSkrC3t4eNzc3rl27psRMnTqVhQsXkpaWRrNmzQq18emnn7JhwwbWrVtHfHw8N2/eZOfOnU889pIlS3B1dSU5ORlfX19Gjx5Nenq6st/ExISwsDBSU1NZsWIFa9asYdmyZaXqZ2ly9Pb2ZtOmTaxcuZK0tDS++OIL1Gq1TkxAQADBwcEkJCTw66+/4u7uzvLly9m4cSMRERFER0cTFFS6KxGTJ0/m0KFD7Nq1i+joaOLi4khKkg+q4uVlYGBAq1bNiD3wnVKm1Wo5cOAw7dq5FFmnXVsXDjwQDxAdE6fEq1Qq+vTuzpmzPxOxZwO//5ZC/OFvGTDArfw6IsRLTFtG/yoTeXSGEOK5dPv2bUJCQggLC6N3794ArFmzhpiYGEJDQ2ndujUAc+fOpWfPno9sJygoiGnTpjFw4EAAgoOD2bt37xOP36dPH3x9fYH7VxGXLVvGwYMHadTo/vSwmTNnKrEajQY/Pz82b97MlClTStzXkuZ45swZtm7dSkxMDD169ACgQYMGheLmz59Px44dAfDx8WHatGlkZGQosYMHD+bgwYP4+/uXKN+cnBxCQ0P5z3/+Q/fu3QEIDw/nlVdeeWSd3NxccnNzdcq0Wi0qlapExxbieWVuboa+vj7ZWVd0yrOyL9OokV2RdaytLcjKvqxTlp11BSsrCwAsLc0xMVEzZfIY5sz5jOkzFvDGG13YtvVLevQcwnffHS2fzgjxkpJHZxQmVxaFEM+ljIwM8vLylMEO3P/mvk2bNqSlpSllrq6uj2zjxo0bZGVl0aZNG6VMT08PF5eiv+V/0INXKVUqFdbW1mRnZytlW7ZsoWPHjlhbW6NWq5k5cyaZmZnF7t/T5Hjy5En09PTo3LlzsftgZWWlTJl9sOzBPhVXRkYGd+/epW3btkqZmZmZMpAuSmBgIKampjpbQcGtEh9biJdJlSr3P6bt/jaKFSvXkJJyikWLPidi735GjfKq4OyEEC8DGSwKIV5oxsbG5dKugYGBzmuVSkVBwf3vHI8cOYKnpyd9+vRhz549JCcnM2PGDO7evVsuuTzMyMioWHEP9kGlUj22T+Vt2rRp3LhxQ2erUkUWFRKVx5Ur18jPz8fSylyn3MrSgktZl4usc+nSZawsLXTKLK3Myfq/+CtXrpGXl0da2lmdmNOnz2JrU68MsxdCgNyzWBQZLAohnkt2dnZUrVqV+Ph4pSwvL4/ExEQaN25crDZMTU2xsrJSFsUBuHfv3lPfW5eQkED9+vWZMWMGrq6uODg4cOHChVK1VZocnZ2dKSgo4NChQ6U65tOys7PDwMCAY8eOKWXXr1/nzJkzj6xjaGhIjRo1dDaZgioqk7y8PJKSfqBb105KmUqlomvXThw9eqLIOkePnaBrt046ZT26v67E5+Xlcfx4Co0a6k5jdXBowIXM38q4B0IIuWexMLlnUQjxXDI2Nmb06NFMnjwZMzMzbG1t+eyzz7hz5w4+Pj6kpKQUq51x48YRGBiIvb09jo6OBAUFcf369acaqDg4OJCZmcnmzZtp3bo1ERER7Nixo9TtlTRHjUbDsGHDGDFiBCtXrqR58+ZcuHCB7Oxs3N3dS51HcanVanx8fJg8eTK1a9fG0tKSGTNmKFPmhHhZLV+xhrWhyziR9AOJicmMHzcSY2MjwsO3ALBu7Qp+/+MiM2cuBCA4KJTY2K+ZMOEDIiP34+7+Ji4uzRjt+8+9z0uWhrBxQwjffXeUuEMJuL3RhX59e9Kjx2AlxsrKAmtrS+ztNAA0bepITs5tMjN/5/r1P59Z/4UQlY8MFoUQz62FCxdSUFCAl5cXt27dwtXVlaioKGrVqlXsNvz9/bl06RLe3t7o6ekxatQo3Nzc0NPTK3VeAwYMYOLEiYwdO5bc3Fz69u3LrFmzCAgIKFV7pckxJCSE6dOn4+vry9WrV7G1tWX69Oml7FHJLVq0iJycHPr374+JiQmTJk3ixo0bz+z4QjyPtm3bjYW5GXNm+2FtbUFKyin69XuX7Oz7i97Y2NTVmfp95OhxvLzH8vHHU5g/z5+z584zaLAPp079s/Lyrl37GDNmKlOmjGPZsrmcOfMz7kNHEp/wz2yEUaO8mD1rkvI67uD9L698fCay/qut5d1tISoNWeCmMJVWq61c10qFEOIxCgoKcHJywt3dnXnz5lV0OkV6EXIsCwZV5Z4rIYQQxZN39/dyP8ZA2/5l0s6OzG/LpJ3ngVxZFEJUahcuXCA6OprOnTuTm5tLcHAw58+fx8PDo6JTU7wIOQohhBDi5SODRSFEpValShXCwsLw8/NDq9XStGlT9u/fj5OT0zPLQa1WP3JfZGQkGo2mQnPMzMx87KJBqamp2NraPpNchBBCiIpS2VYyLQsyDVUIIcrZuXPnHrmvXr16xX4URnnJz8/nl19+eeR+jUaDvn7Zf7co01CFEEIU17OYhtrftl+ZtPNt5p4yaed5IFcWhRCinNnb21d0Co+lr6//3OcohBBCiGdPBotCCCGEEEKIl15le0ZiWZDBohBCCCGEEOKlJ/csFiZPUBZCvDACAgJo0aJFiep06dKFCRMmVHgej1MeOZa1FyFHIYQQ4mlotdoy2SoTGSwKIV4Yfn5+xMbGlqjO9u3bK/WzCsvC8OHDeeuttyo6DSEqhdH/HsbZM0e5dTOD+MPf0tq1xWPjBw3qx48/HuLWzQySk/bTq1e3QjGOjvZs376OK5fT+PP6WY4kRGBjU1fZ/76PJ/tjtnH1ymny7v6OqWmNsu6WEOIlJYNFIcRzT6vVkp+fj1qtpnbt2iWqa2ZmhomJSTllJoQQ/xgyZACLFs1h/vyltGnbix9+SCUiYgMWFkX/3mrfzpX/fPU569ZtonUbN3btjuKbr0Np0qSREtOgQX3iDu4kPf0cPXoOppVLDz5ZsJz//S9Xiale3Yio6DgWfhpU7n0UojIrKKOtMpHBohCiQuTm5jJ+/HgsLS2pVq0anTp1IjExEYC4uDhUKhWRkZG4uLhgaGjI4cOHC03/zM/PZ/z48dSsWZPatWvj7+/PsGHDdK6SPTx9UqPRsGDBAkaMGIGJiQm2trasXr1aJzd/f38aNmxI9erVadCgAbNmzSIvL69U/SxOjkWdG39/f2xsbDA0NMTe3p7Q0FCdcxMVFUXLli0xMjKiW7duZGdnExkZiZOTEzVq1MDDw4M7d+6UKufbt2/j7e2NWq2mTp06LFmypFBMcc6jEC+bCR+OJDR0I+Hrt5KWdhbfMVO5c+cvhg//V5HxY8f5EBUVx9Klqzh9+hwBAYtITv4J39HvKTFz5/qzb98Bpk37hJMnT/HzzxfYsyeGy5evKjErg75k0aLPOXYsqdz7KERlpi2jf5WJDBaFEBViypQpfPPNN4SHh5OUlIS9vT1ubm5cu3ZNiZk6dSoLFy4kLS2NZs2aFWrj008/ZcOGDaxbt474+Hhu3rzJzp07n3jsJUuW4OrqSnJyMr6+vowePZr09HRlv4mJCWFhYaSmprJixQrWrFnDsmXLStXP0uTo7e3Npk2bWLlyJWlpaXzxxReo1WqdmICAAIKDg0lISODXX3/F3d2d5cuXs3HjRiIiIoiOjiYoqHRXGSZPnsyhQ4fYtWsX0dHRxMXFkZRU+EPok86jEC8TAwMDWrVqRuyB75QyrVbLgQOHadfOpcg67dq6cOCBeIDomDglXqVS0ad3d86c/ZmIPRv4/bcU4g9/y4ABbuXXESGEeIAMFoUQz9zt27cJCQlh0aJF9O7dm8aNG7NmzRqMjIyUK2gAc+fOpWfPntjZ2WFmZlaonaCgIKZNm8bAgQNxdHQkODiYmjVrPvH4ffr0wdfXF3t7e/z9/TE3N+fgwYPK/pkzZ9KhQwc0Gg39+/fHz8+PrVu3lqqvJc3xzJkzbN26lbVr1zJw4EAaNGhA9+7dGTp0qE7c/Pnz6dixIy1btsTHx4dDhw4REhJCy5Ytee211xg8eLBOn4orJyeH0NBQFi9eTPfu3XF2diY8PJz8/PxCsU86jw/Kzc3l5s2bOltlWwRAvNzMzc3Q19cnO+uKTnlW9mWsrSyKrGNtbUFW9mWdsuysK1j9X7ylpTkmJmqmTB5DdHQcffp6sHPXPrZt/ZLXXmtXPh0R4iVWgLZMtspEHp0hhHjmMjIyyMvLo2PHjkqZgYEBbdq0IS0tjdatWwPg6ur6yDZu3LhBVlYWbdq0Ucr09PRwcXGhoODxdww8eJVSpVJhbW1Ndna2UrZlyxZWrlxJRkYGOTk55OfnU6NGyReMKE2OJ0+eRE9Pj86dOxe7D1ZWVsqU2QfLvv/++xLnnJGRwd27d2nbtq1SZmZmRqNGjQrFPuk8PigwMJCPP/5Yp0xVRY2enizEIcSjVKly/zv93d9GsWLlGgBSUk7Rvr0ro0Z58d13RysyPSEqHfkSszC5siiEeG4ZGxuXS7sGBgY6r1UqlTJ4O3LkCJ6envTp04c9e/aQnJzMjBkzuHv3brnk8jAjI6NixT3YB5VK9dg+lZeSHHPatGncuHFDZ6tSRRYeEpXHlSvXyM/Px9LKXKfcytKCS1mXi6xz6dJlrCx1rzpaWpmT9X/xV65cIy8vj7S0szoxp0+fxdamXhlmL4QQRZPBohDimbOzs6Nq1arEx8crZXl5eSQmJtK4ceNitWFqaoqVlZWyKA7AvXv3iry3riQSEhKoX78+M2bMwNXVFQcHBy5cuFCqtkqTo7OzMwUFBRw6dKhUx3xadnZ2GBgYcOzYMaXs+vXrnDlz5qnaNTQ0pEaNGjqbSqV62nSFeG7k5eWRlPQD3bp2UspUKhVdu3bi6NETRdY5euwEXbt10inr0f11JT4vL4/jx1No1NBOJ8bBoQEXMn8r4x4IIWQaamEyWBRCPHPGxsaMHj2ayZMns2/fPlJTUxk5ciR37tzBx8en2O2MGzeOwMBAdu3aRXp6Oh9++CHXr19/qkGIg4MDmZmZbN68mYyMDFauXMmOHTtK3V5Jc9RoNAwbNowRI0awc+dOzp8/T1xcXKnvmSwptVqNj48PkydP5sCBA/z0008MHz5cmQ4nhHi05SvW4OPjgZfXEBwd7fk8eCHGxkaEh28BYN3aFcyfP1WJDw4Kxe2NLkyY8AGNGtkxa9ZHuLg04/+FrFNiliwNYciQ/viM8MDOToPv6OH069uTL1aFKzFWVhY0b94EezsNAE2bOtK8eRNq1ar5TPotRGVRkauhfv7552g0GqpVq0bbtm2feCvJtm3bcHR0pFq1ajg7O7N3716d/SqVqsht0aJFJcpL7lkUQlSIhQsXUlBQgJeXF7du3cLV1ZWoqChq1apV7Db8/f25dOkS3t7e6OnpMWrUKNzc3NDT0yt1XgMGDGDixImMHTuW3Nxc+vbty6xZswgICChVe6XJMSQkhOnTp+Pr68vVq1extbVl+vTppexRyS1atIicnBz69++PiYkJkyZN4saNG8/s+EK8qLZt242FuRlzZvthbW1BSsop+vV7l+zs+4ve2NjU1ZmqfeTocby8x/Lxx1OYP8+fs+fOM2iwD6dO/bOq8K5d+xgzZipTpoxj2bK5nDnzM+5DRxKf8M+MhVGjvJg9a5LyOu7g/S+4fHwmsv6rZ/NFkxCVQUEF3bO4ZcsWPvroI1atWkXbtm1Zvnw5bm5upKenY2lpWSg+ISGBd955h8DAQPr168fGjRt56623SEpKomnTpgBcvHhRp05kZCQ+Pj4MGjSoRLmptHInpxCikigoKMDJyQl3d3fmzZtX0ekU6UXI8VkxqCr3XAkhhCievLu/l/sxXq/XvUzaifl5L7m5uTplhoaGGBoaFhnftm1bWrduTXBwMHD/s4KNjQ3jxo1j6tSpheKHDh3K7du32bNnj1LWrl07WrRowapVq4o8xltvvcWtW7eIjY0tUV9kXpEQ4oV14cIF1qxZw5kzZ/jxxx8ZPXo058+fx8PDo6JTU7wIOQohhBACtGW0BQYGYmpqqrMFBgYWecy7d+9y4sQJevTooZRVqVKFHj16cOTIkSLrHDlyRCcewM3N7ZHxWVlZRERElOhWn7/JNFQhxAurSpUqhIWF4efnh1arpWnTpuzfvx8nJ6dnloNarX7kvsjISDQaTYXmmJmZ+dhFg1JTU7G1tX0muQghhBDPs7JanGbatGl89NFHOmWPuqp45coV7t27h5WVlU65lZUVp0+fLrLOpUuXioy/dOlSkfHh4eGYmJjw9ttvF7cLChksCiFeWDY2NjorqlaEkydPPnJfvXr1MDIyqtAc69at+9gc69at++ySEUIIIV4Cj5tyWhHWrl2Lp6cn1apVK3FdGSwKIcRTsLe3r+gUHktfX/+5z1EIIYR4HlTEYy/Mzc3R09MjKytLpzwrKwtra+si61hbWxc7/rvvviM9PZ0tW7aUKj+5Z1EIIUSFKKt7Q2STTTbZZKv827Og1WrLZCuJqlWr4uLiorPwTEFBAbGxsbRv377IOu3bty+0UE1MTEyR8aGhobi4uNC8efMS5fU3ubIohBBCCCGEEBXko48+YtiwYbi6utKmTRuWL1/O7du3ee+99wDw9vamXr16yiI5H374IZ07d2bJkiX07duXzZs3c/z4cVavXq3T7s2bN9m2bRtLliwpdW4yWBRCCCGEEEK89CpiGircfxTG5cuXmT17NpcuXaJFixbs27dPWcQmMzOTKlX+mRDaoUMHNm7cyMyZM5k+fToODg7s3LlTecbi3zZv3oxWq+Wdd94pdW7ynEUhxDMXEBDAzp07H7vwysO6dOlCixYtWL58eYXm8TjlkWNZe55y1JfnLAohhCim/GfwnMXWdV8vk3YS//hvmbTzPJB7FoUQz5yfn1+JHwq7ffv2l/4h9k8yfPhw3nrrrYpOQ4iX2uh/D+PcmaPk3Mwg4fC3tHZt8dj4QYP68dOPh8i5mUFy0n569+pWKMbR0Z4d29dx9XIaN66f5UhCBDY2/6xk/L6PJ7Ex27h25TT5d3/H1LRGWXdLCPGSksGiEOKZ0Wq15Ofno1arqV27donqmpmZYWJiUk6ZCSHE0xsyZACLF81h3vyltG7bi5QfUtkbsQELi6J/37Vv58qGrz5n3bpNuLZxY/fuKL75OpQmTRopMQ0a1OfQwZ2kp5+je8/BtHTpwScLlvO//+UqMdWrGxEVHcfCT4PKvY9CVGYVscDN804Gi0KIp5Kbm8v48eOxtLSkWrVqdOrUicTERADi4uJQqVRERkbi4uKCoaEhhw8fJiAggBYtWiht5OfnM378eGrWrEnt2rXx9/dn2LBhOlfJunTpwoQJE5TXGo2GBQsWMGLECExMTLC1tS10Y7e/vz8NGzakevXqNGjQgFmzZpGXl1eqfhYnx6LOjb+/PzY2NhgaGmJvb09oaKjOuYmKiqJly5YYGRnRrVs3srOziYyMxMnJiRo1auDh4cGdO3dKlfPt27fx9vZGrVZTp06dIm9w12g0zJ8/X4mrX78+u3fv5vLly7z55puo1WqaNWvG8ePHlTphYWHUrFmTqKgonJycUKvV9OrVi4sXL5YqTyEqi4kfjuTL0I2Er99KWtpZfMdM5c6dv3hv+L+KjB83zoeoqDiWLF3F6dPnmBOwiOTkn/Ad/Z4SM2+uP5H7DjB12iecPHmKn3++wJ49MVy+fFWJWRn0JZ8t+pxjx5LKvY9CVGYFaMtkq0xksCiEeCpTpkzhm2++ITw8nKSkJOzt7XFzc+PatWtKzNSpU1m4cCFpaWk0a9asUBuffvopGzZsYN26dcTHx3Pz5k127tz5xGMvWbIEV1dXkpOT8fX1ZfTo0aSnpyv7TUxMCAsLIzU1lRUrVrBmzRqWLVtWqn6WJkdvb282bdrEypUrSUtL44svvkCtVuvEBAQEEBwcTEJCAr/++ivu7u4sX76cjRs3EhERQXR0NEFBpbtaMHnyZA4dOsSuXbuIjo4mLi6OpKTCHyaXLVtGx44dSU5Opm/fvnh5eeHt7c27775LUlISdnZ2eHt763xbeufOHRYvXsxXX33Ff//7XzIzM/Hz8ytVnkJUBgYGBrRq1YzYA98pZVqtltgDh2nXzqXIOu3auujEA0THxCnxKpWKPr27c/bsz+zds4E/fksh4fC3DBjgVn4dEeIlJlcWC5PBohCi1G7fvk1ISAiLFi2id+/eNG7cmDVr1mBkZKRcQQOYO3cuPXv2xM7ODjMzs0LtBAUFMW3aNAYOHIijoyPBwcHUrFnzicfv06cPvr6+2Nvb4+/vj7m5OQcPHlT2z5w5kw4dOqDRaOjfvz9+fn5s3bq1VH0taY5nzpxh69atrF27loEDB9KgQQO6d+/O0KFDdeLmz59Px44dadmyJT4+Phw6dIiQkBBatmzJa6+9xuDBg3X6VFw5OTmEhoayePFiunfvjrOzM+Hh4eTn5xeK7dOnDx988AEODg7Mnj2bmzdv0rp1a4YMGULDhg3x9/cnLS1N5wHAeXl5rFq1CldXV1q1asXYsWMfex9qbm4uN2/e1Nkq2x9U8XIzNzdDX1+f7KwrOuXZ2ZextrIoso61tQVZ2Zd1yrKyrijxlpbmmJiomTJ5DFHRcfTu68HOXfv4euuXvP5au/LpiBBCPEAGi0KIUsvIyCAvL4+OHTsqZQYGBrRp04a0tDSlzNXV9ZFt3Lhxg6ysLNq0aaOU6enp4eJS9DfxD3rwKqVKpcLa2prs7GylbMuWLXTs2BFra2vUajUzZ84kMzOz2P17mhxPnjyJnp4enTt3LnYfrKyslCmzD5Y92KfiysjI4O7du7Rt21YpMzMzo1GjRoViH84BwNnZuVDZg3lUr14dOzs75XWdOnUem2dgYCCmpqY6m7bgVon7JcTL5O+l8nd/G8WKlWtISTnFZ4s+J2LvfkaN8qrg7ISofGQaamEyWBRClDtjY+NyadfAwEDntUqloqCgAIAjR47g6elJnz592LNnD8nJycyYMYO7d++WSy4PMzIyKlbcg31QqVSP7VN5eTiHR5U9mEdReT7uSuG0adO4ceOGzqaqIgsWicrjypVr5OfnY2llrlNuaWnBpazLRda5dOkyVpa6Vx2trMyV+CtXrpGXl0da2lmdmNOnz2JrI4+eEaKsacvoX2Uig0UhRKnZ2dlRtWpV4uPjlbK8vDwSExNp3LhxsdowNTXFyspKWRQH4N69e0XeW1cSCQkJ1K9fnxkzZuDq6oqDgwMXLlwoVVulydHZ2ZmCggIOHTpUqmM+LTs7OwwMDDh27JhSdv36dc6cOVMh+RgaGlKjRg2d7e9BqBCVQV5eHklJP9CtayelTKVS0a1rJ44ePVFknaPHTtCtWyedsh7dX1fi8/LyOH48hYYN7XRiHBwacCHztzLugRBCFKZf0QkIIV5cxsbGjB49msmTJ2NmZoatrS2fffYZd+7cwcfHh5SUlGK1M27cOAIDA7G3t8fR0ZGgoCCuX7/+VIMJBwcHMjMz2bx5M61btyYiIoIdO3aUur2S5qjRaBg2bBgjRoxg5cqVNG/enAsXLpCdnY27u3up8ygutVqNj48PkydPpnbt2lhaWjJjxgxlWpsQouwtW7GGdaHLOJH0A4mJyYwfNxJjYyPCwrcAsG7tCv744yIzZi4EICgolAOxXzNxwgfsjdzPUPc3cXFpxr99pyhtLl4awqYNIXz33VHiDiXg9kYX+vXtSfceg5UYKysLrK0tsbPTAODc1JFbObfJzPyd69f/fGb9F+JFVyD30hcig0UhxFNZuHAhBQUFeHl5cevWLVxdXYmKiqJWrVrFbsPf359Lly7h7e2Nnp4eo0aNws3NDT09vVLnNWDAACZOnMjYsWPJzc2lb9++zJo1i4CAgFK1V5ocQ0JCmD59Or6+vly9ehVbW1umT59eyh6V3KJFi8jJyaF///6YmJgwadIkbty48cyOL8TLZtu23ViYmxEw2w9rawtSUk7Rt9+7ZGffX/TG1qauznTuI0eP8673WOZ+PIX58/w5e+48gwb7cOrUP6s679q1D98xU/GfMo7ly+aSfuZnhgwdSXzCPzMdPhjlxexZk5TXcQfvfzE2wmci678q3aJeQryMKtsU0rKg0spydEKI50xBQQFOTk64u7szb968ik6nSC9Cjs87/apyz5UQQojiyb/7e7kfo4lV2ycHFcOprGNPDnpByJVFIUSFu3DhAtHR0XTu3Jnc3FyCg4M5f/48Hh4eFZ2a4kXIUQghhBClJ9NQC5PBohCiwlWpUoWwsDD8/PzQarU0bdqU/fv34+Tk9MxyUKvVj9wXGRmJRqOp0BwzMzMfu2hQamoqtra2zyQXIYQQojKSaaiFyTRUIYQAzp0798h99erVK/ajMMpLfn4+v/zyyyP3azQa9PVfrO//ZBqqEEKI4noW01AdLVuXSTunsxOfHPSCeLE+WQghRDmxt7ev6BQeS19f/7nPUQghhHiRyTTUwmSwKIQQQgghhHjpyTTUwmSwKIQQQgghhHjpyZXFwuTpzEKI51JAQAAtWrQoUZ0uXbowYcKECs/jccojx7L2IuQohBBCiPIng0UhxHPJz8+P2NjYEtXZvn27PPPwCYYPH85bb71V0WkIUWmN/vcwzp05Ss7NDBIOf0tr1xaPjR80qB8//XiInJsZJCftp3evboViHB3t2bF9HVcvp3Hj+lmOJERgY1NX2f++jyexMdu4duU0+Xd/x9S0Rll3S4iXgraM/lUmMlgUQjxXtFot+fn5qNVqateuXaK6ZmZmmJiYlFNmQgjxeEOGDGDxojnMm7+U1m17kfJDKnsjNmBhUfTvsvbtXNnw1eesW7cJ1zZu7N4dxTdfh9KkSSMlpkGD+hw6uJP09HN07zmYli49+GTBcv73v1wlpnp1I6Ki41j4aVC591GIykyrLSiTrTKRwaIQotzl5uYyfvx4LC0tqVatGp06dSIx8f6y0nFxcahUKiIjI3FxccHQ0JDDhw8Xmv6Zn5/P+PHjqVmzJrVr18bf359hw4bpXCV7ePqkRqNhwYIFjBgxAhMTE2xtbVm9erVObv7+/jRs2JDq1avToEEDZs2aRV5eXqn6WZwcizo3/v7+2NjYYGhoiL29PaGhoTrnJioqipYtW2JkZES3bt3Izs4mMjISJycnatSogYeHB3fu3ClVzrdv38bb2xu1Wk2dOnVYsmRJoRiNRsP8+fOVuPr167N7924uX77Mm2++iVqtplmzZhw/frxUOQhRWUz8cCRfhm4kfP1W0tLO4jtmKnfu/MV7w/9VZPy4cT5ERcWxZOkqTp8+x5yARSQn/4Tv6PeUmHlz/Yncd4Cp0z7h5MlT/PzzBfbsieHy5atKzMqgL/ls0eccO5ZU7n0UQrxcZLAohCh3U6ZM4ZtvviE8PJykpCTs7e1xc3Pj2rVrSszUqVNZuHAhaWlpNGvWrFAbn376KRs2bGDdunXEx8dz8+ZNdu7c+cRjL1myBFdXV5KTk/H19WX06NGkp6cr+01MTAgLCyM1NZUVK1awZs0ali1bVqp+liZHb29vNm3axMqVK0lLS+OLL75ArVbrxAQEBBAcHExCQgK//vor7u7uLF++nI0bNxIREUF0dDRBQaW7ojB58mQOHTrErl27iI6OJi4ujqSkwh84ly1bRseOHUlOTqZv3754eXnh7e3Nu+++S1JSEnZ2dnh7eyOP7hUvKwMDA1q1akbsge+UMq1WS+yBw7Rr51JknXZtXXTiAaJj4pR4lUpFn97dOXv2Z/bu2cAfv6WQcPhbBgxwK7+OCPESK0BbJltlIoNFIUS5un37NiEhISxatIjevXvTuHFj1qxZg5GRkXIFDWDu3Ln07NkTOzs7zMzMCrUTFBTEtGnTGDhwII6OjgQHB1OzZs0nHr9Pnz74+vpib2+Pv78/5ubmHDx4UNk/c+ZMOnTogEajoX///vj5+bF169ZS9bWkOZ45c4atW7eydu1aBg4cSIMGDejevTtDhw7ViZs/fz4dO3akZcuW+Pj4cOjQIUJCQmjZsiWvvfYagwcP1ulTceXk5BAaGsrixYvp3r07zs7OhIeHk5+fXyi2T58+fPDBBzg4ODB79mxu3rxJ69atGTJkCA0bNsTf35+0tDSysrKKPFZubi43b97U2WRgKSoTc3Mz9PX1yc66olOenX0ZayuLIutYW1uQlX1Zpywr64oSb2lpjomJmimTxxAVHUfvvh7s3LWPr7d+yeuvtSufjgjxEtNqtWWyVSYyWBRClKuMjAzy8vLo2LGjUmZgYECbNm1IS0tTylxdXR/Zxo0bN8jKyqJNmzZKmZ6eHi4uRX9b/6AHr1KqVCqsra3Jzs5WyrZs2ULHjh2xtrZGrVYzc+ZMMjMzi92/p8nx5MmT6Onp0blz52L3wcrKSpky+2DZg30qroyMDO7evUvbtm2VMjMzMxo1alQo9uEcAJydnQuVPSqPwMBATE1NdTZtwa0S5yzEy6RKlfsf03Z/G8WKlWtISTnFZ4s+J2LvfkaN8qrg7IQQLwMZLAohngvGxsbl0q6BgYHOa5VKRUHB/ZvPjxw5gqenJ3369GHPnj0kJyczY8YM7t69Wy65PMzIyKhYcQ/2QaVSPbZP5eXhHB5V9qg8pk2bxo0bN3Q2VRVZjEhUHleuXCM/Px9LK3OdcktLCy5lXS6yzqVLl7Gy1L3qaGVlrsRfuXKNvLw80tLO6sScPn0WW5t6ZZi9EAJkGmpRZLAohChXdnZ2VK1alfj4eKUsLy+PxMREGjduXKw2TE1NsbKyUhbFAbh3716R99aVREJCAvXr12fGjBm4urri4ODAhQsXStVWaXJ0dnamoKCAQ4cOleqYT8vOzg4DAwOOHTumlF2/fp0zZ86U+bEMDQ2pUaOGzvb3AFOIyiAvL4+kpB/o1rWTUqZSqejWtRNHj54oss7RYyfo1q2TTlmP7q8r8Xl5eRw/nkLDhnY6MQ4ODbiQ+VsZ90AIIdNQC9Ov6ASEEJWbsbExo0ePZvLkyZiZmWFra8tnn33GnTt38PHxISUlpVjtjBs3jsDAQOzt7XF0dCQoKIjr168/1YDDwcGBzMxMNm/eTOvWrYmIiGDHjh2lbq+kOWo0GoYNG8aIESNYuXIlzZs358KFC2RnZ+Pu7l7qPIpLrVbj4+PD5MmTqV27NpaWlsyYMUOZ+iaEKJllK9awLnQZJ5J+IDExmfHjRmJsbERY+BYA1q1dwR9/XGTGzIUABAWFciD2ayZO+IC9kfsZ6v4mLi7N+LfvFKXNxUtD2LQhhO++O0rcoQTc3uhCv7496d5jsBJjZWWBtbUldnYaAJybOnIr5zaZmb9z/fqfz6z/QojKRwaLQohyt3DhQgoKCvDy8uLWrVu4uroSFRVFrVq1it2Gv78/ly5dwtvbGz09PUaNGoWbmxt6enqlzmvAgAFMnDiRsWPHkpubS9++fZk1axYBAQGlaq80OYaEhDB9+nR8fX25evUqtra2TJ8+vZQ9KrlFixaRk5ND//79MTExYdKkSdy4ceOZHV+IymTbtt1YmJsRMNsPa2sLUlJO0bffu2Rn31/0xtamrs5U7SNHj/Ou91jmfjyF+fP8OXvuPIMG+3Dq1D8rNu/atQ/fMVPxnzKO5cvmkn7mZ4YMHUl8wj+zGD4Y5cXsWZOU13EH73/pNcJnIuu/Kt2CXUK8jAoq2VXBsqDSVrZrpUKIl0JBQQFOTk64u7szb968ik6nSC9CjhVJv6rccyWEEKJ48u/+Xu7HsK7pVCbtXPoz7clBLwi5siiEeCFcuHCB6OhoOnfuTG5uLsHBwZw/fx4PD4+KTk3xIuQohBBCiKLJNbTCZLAohHghVKlShbCwMPz8/NBqtTRt2pT9+/fj5FQ23wIWh1qtfuS+yMhINBpNheaYmZn52EWDUlNTsbW1fSa5CCGEEOLFJ9NQhRCimM6dO/fIffXq1Sv2ozDKS35+Pr/88ssj92s0GvT1n5/vCGUaqhBCiOJ6FtNQLUwLP2e4NC7fSH9y0AtCBotCCCEqhAwWhRBCFNezGCya12hYJu1cuVn2j6CqKLI+uhBCCCGEEEKIQp6f+UhCCCGEEEIIUUHk0RmFyWBRCCGEEEII8dKTu/MKk2mo4qUWEBBAixYtSlSnS5cuTJgwocLzeJzyyLG8qFQqdu7cqbw+ffo07dq1o1q1aso5KapMCCGEEEKULxksipean58fsbGxJaqzfft2ecD6EwwfPhyVSoVKpcLAwAArKyt69uzJ2rVrKSgo0Im9ePEivXv3Vl7PmTMHY2Nj0tPTlfemqLLK4MiRI+jp6dG3b9+KTkUIUUZG/3sY584cJedmBgmHv6W1a4vHxg8a1I+ffjxEzs0MkpP207tXt0Ixjo727Ni+jquX07hx/SxHEiKwsamr7H/fx5PYmG1cu3Ka/Lu/Y2pao6y7JcRLoQBtmWyViQwWxUtJq9WSn5+PWq2mdu3aJaprZmaGiYlJOWVWefTq1YuLFy/yyy+/EBkZSdeuXfnwww/p168f+fn5Spy1tTWGhobK64yMDDp16kT9+vWV96aospK6e/fu03WoHISGhjJu3Dj++9//8scff5Trsf7+mRdClJ8hQwaweNEc5s1fSuu2vUj5IZW9ERuwsCj691b7dq5s+Opz1q3bhGsbN3bvjuKbr0Np0uSf5fsbNKjPoYM7SU8/R/eeg2np0oNPFiznf//LVWKqVzciKjqOhZ8GlXsfhajMtFptmWyViQwWRaWRm5vL+PHjsbS0pFq1anTq1InExEQA4uLiUKlUREZG4uLigqGhIYcPHy40/TM/P5/x48dTs2ZNateujb+/P8OGDeOtt95SYh6e4qnRaFiwYAEjRozAxMQEW1tbVq9erZObv78/DRs2pHr16jRo0IBZs2aRl5dXqn4WJ8eizo2/vz82NjYYGhpib29PaGiozrmJioqiZcuWGBkZ0a1bN7Kzs4mMjMTJyYkaNWrg4eHBnTt3ip2noaEh1tbW1KtXj1atWjF9+nR27dpFZGQkYWFhStyD01BVKhUnTpxg7ty5qFQqAgICiiwD+PXXX3F3d6dmzZqYmZnx5ptv6jxjcPjw4bz11lt88skn1K1bl0aNGpWo3uLFi6lTpw61a9dmzJgxOu/X484nwE8//UTv3r1Rq9VYWVnh5eXFlStXdM5PTk4OW7ZsYfTo0fTt21fnnHh4eDB06FCd+Ly8PMzNzVm/fj0ABQUFBAYG8uqrr2JkZETz5s35+uuvlfhH/cxnZGTw5ptvYmVlhVqtpnXr1uzfv1/nWBcvXqRv374YGRnx6quvsnHjRjQaDcuXL1di/vzzT95//30sLCyoUaMG3bp1IyUlpegfBiFeEhM/HMmXoRsJX7+VtLSz+I6Zyp07f/He8H8VGT9unA9RUXEsWbqK06fPMSdgEcnJP+E7+j0lZt5cfyL3HWDqtE84efIUP/98gT17Yrh8+aoSszLoSz5b9DnHjiWVex+FEC8XGSyKSmPKlCl88803hIeHk5SUhL29PW5ubly7dk2JmTp1KgsXLiQtLY1mzZoVauPTTz9lw4YNrFu3jvj4eG7evKlzP92jLFmyBFdXV5KTk/H19WX06NGkp//zQFYTExPCwsJITU1lxYoVrFmzhmXLlpWqn6XJ0dvbm02bNrFy5UrS0tL44osvUKvVOjEBAQEEBweTkJCgDKiWL1/Oxo0biYiIIDo6mqCgp/vWulu3bjRv3pzt27cXuf/ixYs0adKESZMmcfHiRfz8/Iosy8vLw83NDRMTE7777jvi4+NRq9X06tVL5wpibGws6enpxMTEsGfPnmLXO3jwIBkZGRw8eJDw8HDCwsJ0BnOPO59//vkn3bp1o2XLlhw/fpx9+/aRlZWFu7u7Tl+3bt2Ko6MjjRo14t1332Xt2rXKt5Genp58++235OTkKPFRUVHcuXOHgQMHAhAYGMj69etZtWoVp06dYuLEibz77rscOnRI5zgP/8zn5OTQp08fYmNjSU5OplevXvTv35/MzEyd/v3xxx/ExcXxzTffsHr1arKzs3XaHTJkiPKFwokTJ2jVqhXdu3fX+f9NiJeJgYEBrVo1I/bAd0qZVqsl9sBh2rVzKbJOu7YuOvEA0TFxSrxKpaJP7+6cPfsze/ds4I/fUkg4/C0DBriVX0eEeIkVaLVlslUmshqqqBRu375NSEgIYWFhyv1va9asISYmhtDQUFq3bg3A3Llz6dmz5yPbCQoKYtq0acoH8uDgYPbu3fvE4/fp0wdfX1/g/lXEZcuWcfDgQeVq1syZM5VYjUaDn58fmzdvZsqUKSXua0lzPHPmDFu3biUmJoYePXoA0KBBg0Jx8+fPp2PHjgD4+Pgwbdo0MjIylNjBgwdz8OBB/P39S5zzgxwdHfnhhx+K3GdtbY2+vj5qtRpra2sA1Gp1obL//Oc/FBQU8OWXX6JSqQBYt24dNWvWJC4ujjfeeAMAY2NjvvzyS6pWrVqierVq1SI4OBg9PT0cHR3p27cvsbGxjBw58onnMzg4mJYtW7JgwQKlbO3atdjY2HDmzBkaNrz/wN/Q0FDeffdd4P6U3Rs3bnDo0CG6dOmCm5sbxsbG7NixAy8vLwA2btzIgAEDMDExITc3lwULFrB//37at2+v5HD48GG++OILOnfurBz74Z95MzMzmjdvrryeN28eO3bsYPfu3YwdO5bTp0+zf/9+EhMTcXV1BeDLL7/EwcFBqXP48GG+//57srOzlSnEixcvZufOnXz99deMGjWq0Hubm5tLbm6uTplWq1XeByFedObmZujr65OdpTuLIDv7Mo6N7IqsY21tQVb2ZZ2yrKwrWFtZAGBpaY6JiZopk8cwe85nTJuxALc3uvD11i/p0XMI//3uaPl0RoiXlLaS3W9YFmSwKCqFjIwM8vLylMEO3P+Wt02bNqSlpSmDxb8//Bblxo0bZGVl0aZNG6VMT08PFxeXQouyPOzBq5QqlQpra2udKzFbtmxh5cqVZGRkkJOTQ35+PjVqlHwBgtLkePLkSfT09HQGEE/qg5WVlTJl9sGy77//vsQ5P6wsBggpKSmcO3eu0L2j//vf/8jIyFBeOzs7KwPFktRr0qQJenp6yus6derw448/Ak8+nykpKRw8eLDQlVu4/3PasGFD0tPT+f7779mxYwcA+vr6DB06lNDQULp06YK+vj7u7u5s2LABLy8vbt++za5du9i8eTMA586d486dO4W++Lh79y4tW7bUKXv4Zz4nJ4eAgAAiIiK4ePEi+fn5/PXXX8qVxfT0dPT19WnVqpVSx97enlq1aun0MScnp9D9o3/99ZfOeXxQYGAgH3/8sU6ZqooalZ4sxCHEo1Spcn8C2O5vo1ixcg0AKSmnaN/elVGjvGSwKEQZq2xXBcuCDBbFS8XY2Lhc2jUwMNB5rVKplMHbkSNH8PT05OOPP8bNzQ1TU1M2b97MkiVLyiWXhxkZGRUr7sE+/L2K6YMe7NPTSEtL49VXX32qNnJycnBxcWHDhg2F9llYWCj//fD7Xdx6j+v7k85nTk4O/fv359NPPy20r06dOsD9q4r5+fnUrfvPaoZarRZDQ0OCg4MxNTXF09OTzp07k52dTUxMDEZGRvTq1Us5BkBERAT16tXTOcaDiwUVdQ78/PyIiYlh8eLF2NvbY2RkxODBg0u0AFBOTg516tQhLi6u0L6aNWsWWWfatGl89NFHOmW1ajsW+5hCPO+uXLlGfn4+llbmOuWWlhZcyrpcZJ1Lly5jZWmhU2ZlZa7EX7lyjby8PNLSzurEnD59lo4d2iCEEOVN7lkUlYKdnR1Vq1YlPj5eKcvLyyMxMZHGjRsXqw1TU1OsrKyURXEA7t27R1LS0y0YkJCQQP369ZkxYwaurq44ODhw4cKFUrVVmhydnZ0pKCgodC9bRThw4AA//vgjgwYNeqp2WrVqxdmzZ7G0tMTe3l5nMzU1LfN6D3rS+WzVqhWnTp1Co9EUOoaxsTH5+fmsX7+eJUuWcPLkSWVLSUmhbt26bNq0CYAOHTpgY2PDli1b2LBhA0OGDFEGsY0bN8bQ0JDMzMxCx7CxsXls/vHx8QwfPpyBAwfi7OyMtbW1zgI/jRo1Ij8/n+TkZKXs3LlzXL9+XaePly5dQl9fv9Dxzc11Pyj/zdDQkBo1auhsMgVVVCZ5eXkkJf1At66dlDKVSkW3rp04evREkXWOHjtBt26ddMp6dH9dic/Ly+P48RQaNtSdxurg0IALmb+VcQ+EELIaamEyWBSVgrGxMaNHj2by5Mns27eP1NRURo4cyZ07d/Dx8Sl2O+PGjSMwMJBdu3aRnp7Ohx9+yPXr15/qQ62DgwOZmZls3ryZjIwMVq5cqUw/LI2S5qjRaBg2bBgjRoxg586dnD9/nri4OLZu3VrqHIojNzeXS5cu8fvvv5OUlMSCBQt488036devH97e3k/VtqenJ+bm5rz55pt89913Sp/Gjx/Pb789+gNUaes96Ennc8yYMVy7do133nmHxMREMjIyiIqK4r333uPevXvs2bOH69ev4+PjQ9OmTXW2QYMG6ayq6uHhwapVq4iJicHT01MpNzExwc/Pj4kTJxIeHk5GRgZJSUkEBQURHh7+2PwdHBzYvn27MkD18PDQuWLs6OhIjx49GDVqFN9//z3JycmMGjUKIyMj5WesR48etG/fnrfeeovo6Gh++eUXEhISmDFjBsePHy/WeRSiMlq2Yg3v+3jg5TUER0d7Pg9eiLGxEWHhWwBYt3YFn8yfqsQHBYXi9kYXJk74gEaN7Jg96yNcXJrx/0LWKTGLl4bgPqQ/PiM8sLPT4Dt6OP369mTVqn/+X7eysqB58ybY2WkAcG7qSPPmTahVq+Yz6bcQlYW2jP5VJjJYFJXGwoULGTRoEF5eXrRq1Ypz584RFRWlc6/Vk/j7+/POO+/g7e1N+/btUavVuLm5Ua1atVLnNWDAACZOnMjYsWNp0aIFCQkJzJo1q9TtlSbHkJAQBg8ejK+vL46OjowcOZLbt2+XOofi2LdvH3Xq1EGj0dCrVy8OHjzIypUr2bVrl879gKVRvXp1/vvf/2Jra8vbb7+Nk5MTPj4+/O9//3vsvaClrfewx53PunXrEh8fz71793jjjTdwdnZmwoQJ1KxZkypVqhAaGkqPHj2KvJI5aNAgjh8/riwA5OnpSWpqKvXq1dO5HxfuL0wza9YsAgMDcXJyolevXkRERDxxiu/SpUupVasWHTp0oH///ri5uencnwiwfv16rKyseP311xk4cCAjR47ExMRE+RlTqVTs3buX119/nffee4+GDRvyr3/9iwsXLmBlZVXs8yhEZbNt226m+M8jYLYfJxKjadG8MX37vUt29v1Fb2xt6mJt/c//I0eOHudd77G8/74nScdjePvtvgwa7MOpU/+spr1r1z58x0zFb5IvJ5P2M2KEB0OGjiQ+4Z8ZJh+M8uJEYjSrv1gMQNzBHZxIjKZ/vzeeUc+FEJWVSlvZrpUKUYYKCgpwcnLC3d2defPmVXQ6RXoRchQvtt9++w0bGxv2799P9+7dy6xd/ar1nhwkhBBCAPl3fy/3Y1Q1fKVM2rmbW3mmicsCN0I84MKFC0RHR9O5c2dyc3MJDg7m/PnzeHh4VHRqihchR/FiO3DgADk5OTg7O3Px4kWmTJmCRqPh9ddfr+jUhBBCiHIj19AKk8GiEA+oUqUKYWFh+Pn5odVqadq0Kfv378fJyemZ5VDUIxf+FhkZiUajqdAcMzMzH7toUGpqKra2ts8kF1E+8vLymD59Oj///DMmJiZ06NCBDRs2FFolVgghhBCVm0xDFeI5c+7cuUfuq1evXrEfhVFe8vPzdVbPfJhGo0FfX76HEk8m01CFEEIU17OYhlpWf5eeRa7PigwWhRBCCCGeE7m5uQQGBjJt2rRCz00VQohnTQaLQgghhBDPiZs3b2JqasqNGzdKtEqzEEKUB3l0hhBCCCGEEEKIQmSwKIQQQgghhBCiEBksCiGEEEIIIYQoRAaLQgghhBDPCUNDQ+bMmSOL2wghnguywI0QQgghhBBCiELkyqIQQgghhBBCiEJksCiEEEIIIYQQohAZLAohhBBCCCGEKEQGi0IIIYQQQgghCpHBohBCCCFECQ0fPpy33nqrWLFdunRhwoQJJWr/9OnTtGvXjmrVqtGiRYsS51dRAgICXqh8hRCPJ4NFIYQQQlRKz8vAZfv27cybN69EdebMmYOxsTHp6enExsaWU2ZPR6VSsXPnTp0yPz+/5zZfIUTJ6Vd0AkIIIYQQlZmZmVmJ62RkZNC3b1/q169f6uPevXuXqlWrlrp+aajVatRq9TM9phCi/MiVRSGEEEJUuC5dujBu3DgmTJhArVq1sLKyYs2aNdy+fZv33nsPExMT7O3tiYyMBCAsLIyaNWvqtLFz505UKpWy/+OPPyYlJQWVSoVKpSIsLIxffvkFlUrFyZMnlXp//vknKpWKuLg4AO7du4ePjw+vvvoqRkZGNGrUiBUrVjxV3x6chqrRaFiwYAEjRozAxMQEW1tbVq9erexXqVScOHGCuXPnolKpCAgIAODHH3+kW7duGBkZUbt2bUaNGkVOTo5S7++psZ988gl169alUaNGSn+3bt3Ka6+9hpGREa1bt+bMmTMkJibi6uqKWq2md+/eXL58WWkrMTGRnj17Ym5ujqmpKZ07dyYpKUmnDwADBw5EpVIprx++mltQUMDcuXN55ZVXMDQ0pEWLFuzbt0/Z/3d+27dvp2vXrlSvXp3mzZtz5MiRUp9vIUTZkcGiEEIIIZ4L4eHhmJub8/333zNu3DhGjx7NkCFD6NChA0lJSbzxxht4eXlx586dJ7Y1dOhQJk2aRJMmTbh48SIXL15k6NChxcqjoKCAV155hW3btpGamsrs2bOZPn06W7dufdouKpYsWYKrqyvJycn4+voyevRo0tPTAbh48SJNmjRh0qRJXLx4ET8/P27fvo2bmxu1atUiMTGRbdu2sX//fsaOHavTbmxsLOnp6cTExLBnzx6lfM6cOcycOZOkpCT09fXx8PBgypQprFixgu+++45z584xe/ZsJf7WrVsMGzaMw4cPc/ToURwcHOjTpw+3bt0C7g8mAdatW8fFixeV1w9bsWIFS5YsYfHixfzwww+4ubkxYMAAzp49qxM3Y8YM/Pz8OHnyJA0bNuSdd94hPz//6U+0EOLpaIUQQgghKljnzp21nTp1Ul7n5+drjY2NtV5eXkrZxYsXtYD2yJEj2nXr1mlNTU112tixY4f2wY82c+bM0TZv3lwn5vz581pAm5ycrJRdv35dC2gPHjz4yPzGjBmjHTRokPJ62LBh2jfffLPYffvwww+V1/Xr19e+++67yuuCggKtpaWlNiQkRClr3ry5ds6cOcrr1atXa2vVqqXNyclRyiIiIrRVqlTRXrp0ScnJyspKm5ubW6i/X375pVK2adMmLaCNjY1VygIDA7WNGjV6ZB/u3bunNTEx0X777bdKGaDdsWOHTtzD57xu3braTz75RCemdevWWl9f30fmd+rUKS2gTUtLe2Q+QohnQ64sCiGEEOK50KxZM+W/9fT0qF27Ns7OzkqZlZUVANnZ2eWey+eff46LiwsWFhao1WpWr15NZmZmmbX/YF9VKhXW1taP7VdaWhrNmzfH2NhYKevYsSMFBQXKFUkAZ2fnIu9TfPB4f5/Hh8/tg8fPyspi5MiRODg4YGpqSo0aNcjJySnRObh58yZ//PEHHTt21Cnv2LEjaWlpj8yvTp06wLN5n4UQjycL3AghhBDiuWBgYKDzWqVS6ZT9fT9iQUEBVapUQavV6sTn5eU98RhVqtz/nvzBug/X27x5M35+fixZsoT27dtjYmLCokWLOHbsWMk69BhF9bWgoOCp231wMPmo4/19Hh8ue/D4w4YN4+rVq6xYsYL69etjaGhI+/btuXv37lPnWNz8yuJ8CCGejlxZFEIIIcQLx8LCglu3bnH79m2l7MFFawCqVq3KvXv3CtWD+/cFPqpefHw8HTp0wNfXl5YtW2Jvb09GRkbZdqCEnJycSElJ0elvfHw8VapUoVGjRmV+vPj4eMaPH0+fPn1o0qQJhoaGXLlyRSfGwMCg0Pl9UI0aNahbty7x8fGF2m7cuHGZ5yyEKHsyWBRCCCHEC6dt27ZUr16d6dOnk5GRwcaNGwkLC9OJ0Wg0nD9/npMnT3LlyhVyc3MxMjKiXbt2LFy4kLS0NA4dOsTMmTN16jk4OHD8+HGioqI4c+YMs2bNeuQCLs+Kp6cn1apVY9iwYfz0008cPHiQcePG4eXlpUwrLUsODg589dVXpKWlcezYMTw9PTEyMtKJ0Wg0xMbGcunSJa5fv15kO5MnT+bTTz9ly5YtpKenM3XqVE6ePMmHH35Y5jkLIcqeDBaFEEII8cIxMzPjP//5D3v37sXZ2ZlNmzYpj5j426BBg+jVqxddu3bFwsKCTZs2AbB27Vry8/NxcXFhwoQJzJ8/X6feBx98wNtvv83QoUNp27YtV69exdfX91l1rUjVq1cnKiqKa9eu0bp1awYPHkz37t0JDg4ul+OFhoZy/fp1WrVqhZeXF+PHj8fS0lInZsmSJcTExGBjY0PLli2LbGf8+PF89NFHTJo0CWdnZ/bt28fu3btxcHAol7yFEGVLpX14wr8QQgghhBBCiJeeXFkUQgghhBBCCFGIDBaFEEIIIUopMzMTtVr9yK0sH7chhBDPmkxDFUIIIYQopfz8fH755ZdH7tdoNOjry5PKhBAvJhksCiGEEEIIIYQoRKahCiGEEEIIIYQoRAaLQgghhBBCCCEKkcGiEEIIIYQQQohCZLAohBBCCCGEEKIQGSwKIYQQQgghhChEBotCCCGEEEIIIQqRwaIQQgghhBBCiEL+PwuGi5pmTijeAAAAAElFTkSuQmCC",
+ "text/plain": [
+ "<Figure size 640x480 with 2 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "mi = mutual_info_regression(regression_features, regression_target, random_state=42)\n",
+ "mi_df = pd.DataFrame(mi, index=regression_features.columns, columns=['mutual_information'])\n",
+ "mi_top_features = mi_df.sort_values(by=['mutual_information'], ascending=False).head(features_to_be_selected)\n",
+ "sns.heatmap(mi_top_features, annot=True)\n",
+ "plt.title(f'Top {features_to_be_selected} features - Mutual Information Regression')\n",
+ "plt.show()\n",
+ "mi_top_features = mi_top_features.head(10)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 42,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Best params for Random Forest Regressor: {'criterion': 'absolute_error', 'max_depth': 12, 'max_features': 'sqrt', 'n_estimators': 300, 'random_state': 42}\n",
+ "Best parameter (Cross-validation MAE): -22.663288981102575 \n",
+ "\n"
+ ]
+ }
+ ],
+ "source": [
+ "# hyperparameters grid search\n",
+ "rf = RandomForestRegressor()\n",
+ "rf_search = GridSearchCV(rf, param_grid={\n",
+ " 'n_estimators': np.arange(200, 500, 100).tolist(),\n",
+ " 'max_features': ['sqrt'],\n",
+ " 'random_state': [42],\n",
+ " 'criterion': ['absolute_error'],\n",
+ " 'max_depth': np.arange(5, 15, 1).tolist()}, scoring='neg_mean_absolute_error')\n",
+ "rf_search.fit(regression_features, regression_target)\n",
+ "print(\"Best params for Random Forest Regressor: \", rf_search.best_params_)\n",
+ "print(\"Best parameter (Cross-validation MAE): \", rf_search.best_score_, \"\\n\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 43,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 640x480 with 2 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "# rank features using random forest\n",
+ "rf = make_pipeline(StandardScaler(),\n",
+ " RandomForestRegressor().set_params(**rf_search.best_params_))\n",
+ "rf.fit(regression_features, regression_target)\n",
+ "rf_features = pd.DataFrame(rf.steps[1][1].feature_importances_, index=regression_features.columns,\n",
+ " columns=['feature_ranking'])\n",
+ "selected_rf_features = rf_features.sort_values(by=['feature_ranking'], ascending=False).head(features_to_be_selected)\n",
+ "sns.heatmap(data=selected_rf_features, annot=True)\n",
+ "plt.title('Top 17 Random Forest Regressor ranked features')\n",
+ "plt.show()\n",
+ "selected_rf_features = selected_rf_features.head(6)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 44,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "['original_shape_Maximum2DDiameterColumn', 'original_firstorder_90Percentile', 'original_glcm_JointEntropy', 'original_glcm_Imc1', 'original_gldm_SmallDependenceLowGrayLevelEmphasis', 'original_firstorder_Minimum', 'original_glrlm_RunPercentage', 'original_firstorder_Variance', 'ChemoGrade', 'original_shape_LeastAxisLength', 'original_shape_Maximum2DDiameterSlice', 'TumourStage', 'original_shape_Sphericity', 'original_glszm_SizeZoneNonUniformity', 'original_firstorder_Range', 'original_glcm_SumEntropy', 'original_firstorder_RootMeanSquared', 'original_shape_Maximum2DDiameterRow', 'original_glcm_JointEnergy', 'Gene', 'original_gldm_DependenceNonUniformityNormalized', 'original_glszm_SmallAreaHighGrayLevelEmphasis', 'original_shape_Maximum3DDiameter', 'original_firstorder_MeanAbsoluteDeviation', 'original_shape_MinorAxisLength', 'original_glszm_ZoneEntropy', 'original_glcm_MaximumProbability', 'original_firstorder_10Percentile', 'original_gldm_LargeDependenceHighGrayLevelEmphasis', 'original_firstorder_Maximum', 'original_glszm_SizeZoneNonUniformityNormalized', 'ER', 'original_firstorder_Kurtosis', 'HER2', 'original_firstorder_RobustMeanAbsoluteDeviation', 'original_shape_MajorAxisLength', 'original_shape_Elongation', 'original_glszm_LowGrayLevelZoneEmphasis', 'Age', 'original_glcm_SumSquares', 'original_firstorder_Skewness', 'original_glrlm_ShortRunHighGrayLevelEmphasis', 'original_gldm_SmallDependenceHighGrayLevelEmphasis', 'original_firstorder_InterquartileRange']\n",
+ "44\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Ensure ER, HER2, and Gene are retained\n",
+ "important_features = ['ER', 'HER2', 'Gene']\n",
+ "\n",
+ "# Combine the important features with the features selected by statistical methods\n",
+ "selected_features = np.concatenate(\n",
+ " (important_features, binary_stored_features.index.values, selected_rf_features.index.values, mi_top_features.index.values,regression_features.columns[rfe.support_]))\n",
+ "\n",
+ "# Remove duplicates (if any) and select the final set of features\n",
+ "selected_features = set(selected_features)\n",
+ "selected_features = list(selected_features)\n",
+ "\n",
+ "# Update the features used in the model\n",
+ "top_features = regression_features[selected_features]\n",
+ "\n",
+ "\n",
+ "print(selected_features)\n",
+ "print(len(selected_features))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Split Train and Test data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 45,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "X_train, X_test, y_train, y_test = train_test_split(top_features, regression_target, test_size=0.3, random_state=42)\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Evaluate Models (Tuning Hyperparameters with Grid Search)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### SVR"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 46,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Best params for SVR: {'svr__C': 8.700000000000001, 'svr__epsilon': 2.9000000000000004}\n",
+ "Best parameter (Cross-validation MAE): -20.47193616995508 \n",
+ "\n",
+ "Mean absolute error for svm test score: 22.12215193929716\n",
+ "Mean absolute error for svm cross-validation score: -20.47193616995508\n"
+ ]
+ }
+ ],
+ "source": [
+ "top_features_svr = make_pipeline(StandardScaler(), SVR())\n",
+ "top_features_svr_search = GridSearchCV(top_features_svr,\n",
+ " param_grid={'svr__C': np.arange(0, 10, 0.1).tolist(),\n",
+ " 'svr__epsilon': np.arange(0, 3, 0.1).tolist()},\n",
+ " scoring='neg_mean_absolute_error',\n",
+ " )\n",
+ "top_features_svr_search.fit(X_train, y_train)\n",
+ "print(\"Best params for SVR: \", top_features_svr_search.best_params_)\n",
+ "print(\"Best parameter (Cross-validation MAE): \", top_features_svr_search.best_score_, \"\\n\")\n",
+ "\n",
+ "grid_keys = list(top_features_svr_search.best_params_.keys())\n",
+ "param_keys = [param.replace('svr__', '') for param in grid_keys]\n",
+ "grid_values = list(top_features_svr_search.best_params_.values())\n",
+ "param_dict_svr = {k: v for k, v in zip(param_keys, grid_values)}\n",
+ "\n",
+ "top_features_svr = make_pipeline(StandardScaler(), SVR().set_params(**param_dict_svr))\n",
+ "top_features_svr.fit(X_train, y_train)\n",
+ "print(\"Mean absolute error for svm test score: \",\n",
+ " mean_absolute_error(y_test, top_features_svr.predict(X_test)))\n",
+ "print(\"Mean absolute error for svm cross-validation score: \",\n",
+ " np.mean(cross_val_score(top_features_svr, X_train, y_train, scoring='neg_mean_absolute_error')))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Random Forest Regressor"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 47,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Fitting 5 folds for each of 90 candidates, totalling 450 fits\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.566 total time= 0.3s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.495 total time= 0.3s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.563 total time= 0.3s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.919 total time= 0.3s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.552 total time= 0.3s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.435 total time= 0.5s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.432 total time= 0.5s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.344 total time= 0.5s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.055 total time= 0.5s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.598 total time= 0.5s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.478 total time= 0.6s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.324 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.329 total time= 0.6s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.118 total time= 0.6s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.617 total time= 0.6s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.330 total time= 0.3s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.395 total time= 0.3s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.494 total time= 0.3s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.045 total time= 0.3s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.567 total time= 0.3s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.304 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.424 total time= 0.4s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.447 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.169 total time= 0.4s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.726 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.370 total time= 0.5s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.392 total time= 0.5s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.396 total time= 0.6s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.216 total time= 0.6s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=5, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.610 total time= 0.6s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.695 total time= 0.3s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.246 total time= 0.3s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.335 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.858 total time= 0.3s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.926 total time= 0.3s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.444 total time= 0.5s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.177 total time= 0.5s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.272 total time= 0.5s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.898 total time= 0.5s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.732 total time= 0.5s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.402 total time= 0.7s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.159 total time= 0.7s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.243 total time= 0.7s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.989 total time= 0.7s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.704 total time= 0.7s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.270 total time= 0.3s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.574 total time= 0.3s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.251 total time= 0.3s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.951 total time= 0.3s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.644 total time= 0.3s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.414 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.329 total time= 0.4s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.246 total time= 0.5s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.071 total time= 0.5s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.753 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.393 total time= 0.6s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.305 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.195 total time= 0.6s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.165 total time= 0.6s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=6, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.736 total time= 0.6s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.807 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.074 total time= 0.4s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.542 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.991 total time= 0.4s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.654 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.642 total time= 0.5s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.137 total time= 0.5s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.280 total time= 0.5s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.891 total time= 0.6s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.671 total time= 0.5s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.443 total time= 0.7s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.224 total time= 0.7s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.150 total time= 0.7s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.940 total time= 0.7s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.720 total time= 0.7s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.326 total time= 0.3s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.267 total time= 0.3s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.482 total time= 0.3s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.268 total time= 0.3s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.901 total time= 0.3s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.483 total time= 0.5s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.131 total time= 0.5s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.387 total time= 0.5s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.204 total time= 0.5s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-22.013 total time= 0.5s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.559 total time= 0.6s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.158 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.256 total time= 0.7s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.251 total time= 0.7s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=7, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.965 total time= 0.6s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.803 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.656 total time= 0.4s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.449 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.120 total time= 0.4s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-22.006 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.779 total time= 0.6s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.445 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.464 total time= 0.6s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.199 total time= 0.6s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.916 total time= 0.6s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.614 total time= 0.8s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.357 total time= 0.8s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.255 total time= 0.8s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.281 total time= 0.8s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.941 total time= 0.8s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.335 total time= 0.3s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.325 total time= 0.3s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.323 total time= 0.3s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.125 total time= 0.3s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.562 total time= 0.3s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.369 total time= 0.5s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.300 total time= 0.5s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.257 total time= 0.5s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.087 total time= 0.5s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.891 total time= 0.5s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.470 total time= 0.7s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.298 total time= 0.7s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.275 total time= 0.7s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.160 total time= 0.7s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=8, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.730 total time= 0.7s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.455 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.451 total time= 0.8s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.484 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.789 total time= 0.4s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.898 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.386 total time= 0.6s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.220 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.227 total time= 0.6s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.815 total time= 0.6s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-22.060 total time= 0.6s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.441 total time= 7.5min\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.183 total time= 0.9s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.098 total time= 0.9s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.861 total time= 0.8s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-22.046 total time= 0.8s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.623 total time= 0.3s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.642 total time= 0.3s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.227 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.801 total time= 0.3s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.438 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.568 total time= 0.6s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.578 total time= 0.9s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.238 total time= 0.5s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.790 total time= 0.5s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.874 total time= 0.5s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.511 total time= 0.7s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.495 total time= 0.7s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.073 total time= 0.8s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.847 total time= 0.7s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=9, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.833 total time= 0.7s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.414 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.016 total time= 0.4s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.463 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.948 total time= 0.4s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-22.119 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.521 total time= 0.6s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-16.925 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.416 total time= 0.6s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.766 total time= 0.6s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.999 total time= 0.6s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.417 total time= 0.8s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-16.961 total time= 0.8s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.127 total time= 0.8s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.758 total time= 0.8s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.862 total time= 0.8s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.316 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.683 total time= 0.4s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.941 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.744 total time= 0.4s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-22.149 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.189 total time= 0.5s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.371 total time= 0.5s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.926 total time= 0.6s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.779 total time= 0.6s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.996 total time= 0.5s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.183 total time= 0.7s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.394 total time= 0.7s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.850 total time= 0.7s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.804 total time= 0.7s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=10, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-22.048 total time= 0.7s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.417 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-16.753 total time= 0.4s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.354 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.042 total time= 0.4s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-22.312 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.469 total time= 0.6s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-16.847 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.227 total time= 0.6s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.872 total time= 0.6s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-22.097 total time= 4.6min\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.536 total time= 1.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-16.856 total time= 0.8s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.084 total time= 0.8s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.954 total time= 0.8s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-22.031 total time= 0.8s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.438 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.515 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.908 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.764 total time= 0.4s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.843 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.415 total time= 0.6s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.310 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.946 total time= 0.7s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.908 total time= 0.6s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.958 total time= 0.5s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.322 total time= 0.7s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.396 total time= 0.8s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.999 total time= 0.7s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.039 total time= 0.7s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=11, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-22.025 total time= 0.7s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.175 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.045 total time= 0.4s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.390 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.085 total time= 0.4s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-22.065 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.388 total time= 0.6s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-16.871 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.148 total time= 0.7s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.936 total time= 0.6s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-22.077 total time= 0.8s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.345 total time= 0.9s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-16.918 total time= 0.9s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.923 total time= 0.9s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.063 total time= 0.9s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-22.076 total time= 1.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.025 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.227 total time= 0.4s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.708 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.957 total time= 0.4s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.689 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.241 total time= 0.6s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.170 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.707 total time= 0.6s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.979 total time= 0.6s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.992 total time= 0.6s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.269 total time= 0.8s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.299 total time= 0.7s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.759 total time= 0.8s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.986 total time= 0.8s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=12, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.930 total time= 0.7s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.381 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.133 total time= 0.4s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.910 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.794 total time= 0.4s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-22.138 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.395 total time= 0.6s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.146 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.691 total time= 0.7s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.835 total time= 0.7s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.988 total time= 0.6s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.426 total time= 0.9s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.040 total time= 0.9s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.586 total time= 0.9s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.982 total time= 0.9s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.942 total time= 0.9s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.222 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.530 total time= 0.4s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.851 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.928 total time= 0.4s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-22.061 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.164 total time= 0.6s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.219 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.804 total time= 0.6s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.943 total time= 0.6s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-22.097 total time= 0.6s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.323 total time= 0.8s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.159 total time= 0.8s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.649 total time= 0.8s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.042 total time= 0.8s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=13, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.914 total time= 0.8s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.328 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.116 total time= 0.4s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.284 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.903 total time= 0.4s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.974 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.430 total time= 0.7s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.107 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.777 total time= 0.7s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.822 total time= 0.7s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-22.038 total time= 0.6s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.463 total time= 0.9s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.080 total time= 0.9s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.789 total time= 0.9s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.950 total time= 0.9s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=sqrt, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-22.161 total time= 0.9s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=auto, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=nan total time= 0.0s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-20.220 total time= 0.4s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-17.641 total time= 0.4s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.120 total time= 0.4s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.045 total time= 0.4s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=200, randomforestregressor__random_state=42;, score=-21.766 total time= 0.4s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.182 total time= 0.6s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-17.534 total time= 0.6s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.084 total time= 0.6s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-20.998 total time= 0.6s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=300, randomforestregressor__random_state=42;, score=-21.936 total time= 0.7s\n",
+ "[CV 1/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.237 total time= 0.9s\n",
+ "[CV 2/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-17.522 total time= 0.8s\n",
+ "[CV 3/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.878 total time= 0.8s\n",
+ "[CV 4/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-20.974 total time= 0.8s\n",
+ "[CV 5/5] END randomforestregressor__criterion=absolute_error, randomforestregressor__max_depth=14, randomforestregressor__max_features=log2, randomforestregressor__n_estimators=400, randomforestregressor__random_state=42;, score=-21.873 total time= 0.8s\n",
+ "Best params for Random Forest Regressor: {'randomforestregressor__criterion': 'absolute_error', 'randomforestregressor__max_depth': 12, 'randomforestregressor__max_features': 'log2', 'randomforestregressor__n_estimators': 200, 'randomforestregressor__random_state': 42}\n",
+ "Best parameter (Cross-validation MAE): -20.121129585922827 \n",
+ "\n",
+ "Mean absolute error for random forest test score: 22.163871527869794\n",
+ "Mean absolute error for random forest cross-validation score: -20.121129585922827\n"
+ ]
+ }
+ ],
+ "source": [
+ "top_features_rr = make_pipeline(StandardScaler(), RandomForestRegressor())\n",
+ "top_features_rr_search = GridSearchCV(top_features_rr, param_grid={\n",
+ " 'randomforestregressor__n_estimators': np.arange(200, 500, 100).tolist(),\n",
+ " 'randomforestregressor__max_features': ['sqrt', 'auto', 'log2'],\n",
+ " 'randomforestregressor__random_state': [42],\n",
+ " 'randomforestregressor__criterion': ['absolute_error'],\n",
+ " 'randomforestregressor__max_depth': np.arange(5, 15, 1).tolist()}, verbose=3, scoring='neg_mean_absolute_error')\n",
+ "top_features_rr_search.fit(X_train, y_train)\n",
+ "print(\"Best params for Random Forest Regressor: \", top_features_rr_search.best_params_)\n",
+ "print(\"Best parameter (Cross-validation MAE): \", top_features_rr_search.best_score_, \"\\n\")\n",
+ "\n",
+ "grid_keys = list(top_features_rr_search.best_params_.keys())\n",
+ "param_keys = [param.replace('randomforestregressor__', '') for param in grid_keys]\n",
+ "grid_values = list(top_features_rr_search.best_params_.values())\n",
+ "param_dict_rr = {k: v for k, v in zip(param_keys, grid_values)}\n",
+ "\n",
+ "top_features_rr = make_pipeline(StandardScaler(),\n",
+ " RandomForestRegressor().set_params(**param_dict_rr))\n",
+ "top_features_rr.fit(X_train, y_train)\n",
+ "print(\"Mean absolute error for random forest test score: \",\n",
+ " mean_absolute_error(y_test, top_features_rr.predict(X_test)))\n",
+ "print(\"Mean absolute error for random forest cross-validation score: \", np.mean(cross_val_score(top_features_rr, X_train, y_train, scoring='neg_mean_absolute_error')))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Lasso"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 48,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Best params for Lasso Regression: {'lasso__alpha': 100}\n",
+ "Best parameter (Cross-validation MAE): -21.124440765781685 \n",
+ "\n",
+ "Mean absolute error for Lasso Regression test score: 21.528357314395084\n",
+ "Mean absolute error for Lasso Regression cross-validation score: -21.124440765781685\n"
+ ]
+ }
+ ],
+ "source": [
+ "lasso = make_pipeline(StandardScaler(), Lasso())\n",
+ "lasso_search = GridSearchCV(lasso, param_grid={'lasso__alpha': np.arange(0, 10000, 100).tolist()},\n",
+ " scoring='neg_mean_absolute_error')\n",
+ "lasso_search.fit(X_train, y_train)\n",
+ "print(\"Best params for Lasso Regression: \", lasso_search.best_params_)\n",
+ "print(\"Best parameter (Cross-validation MAE): \", lasso_search.best_score_, \"\\n\")\n",
+ "\n",
+ "grid_keys = list(lasso_search.best_params_.keys())\n",
+ "param_keys = [param.replace('lasso__', '') for param in grid_keys]\n",
+ "grid_values = list(lasso_search.best_params_.values())\n",
+ "param_dict_lasso = {k: v for k, v in zip(param_keys, grid_values)}\n",
+ "\n",
+ "lasso = make_pipeline(StandardScaler(), Lasso().set_params(**param_dict_lasso))\n",
+ "lasso.fit(X_train, y_train)\n",
+ "\n",
+ "print(\"Mean absolute error for Lasso Regression test score: \",\n",
+ " mean_absolute_error(y_test, lasso.predict(X_test)))\n",
+ "print(\"Mean absolute error for Lasso Regression cross-validation score: \",\n",
+ " np.mean(cross_val_score(lasso, X_train, y_train, scoring='neg_mean_absolute_error')))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### XGBOOST"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 49,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Best params for XGBoost Regression: {'colsample_bytree': 0.8, 'learning_rate': 0.1, 'max_depth': 7, 'n_estimators': 50, 'subsample': 0.8}\n",
+ "Best parameter (Cross-validation MAE): -20.28442165675229 \n",
+ "\n",
+ "Mean absolute error for XGBoost Regression test score: 22.997028170830486\n",
+ "Mean absolute error for XGBoost Regression cross-validation score: -20.28442165675229\n"
+ ]
+ }
+ ],
+ "source": [
+ "from xgboost import XGBRegressor\n",
+ "from sklearn.model_selection import GridSearchCV, cross_val_score\n",
+ "from sklearn.metrics import mean_absolute_error\n",
+ "import numpy as np\n",
+ "\n",
+ "# Define the model\n",
+ "xgb = XGBRegressor()\n",
+ "\n",
+ "# Define parameter grid\n",
+ "xgb_search = GridSearchCV(\n",
+ " xgb,\n",
+ " param_grid={\n",
+ " 'n_estimators': [50, 100, 150],\n",
+ " 'learning_rate': [0.01, 0.1, 0.2],\n",
+ " 'max_depth': [3, 5, 7],\n",
+ " 'subsample': [0.8, 1.0],\n",
+ " 'colsample_bytree': [0.8, 1.0]\n",
+ " },\n",
+ " scoring='neg_mean_absolute_error',\n",
+ " cv=5\n",
+ ")\n",
+ "\n",
+ "# Perform grid search\n",
+ "xgb_search.fit(X_train, y_train)\n",
+ "\n",
+ "# Display best parameters and corresponding cross-validation score\n",
+ "print(\"Best params for XGBoost Regression: \", xgb_search.best_params_)\n",
+ "print(\"Best parameter (Cross-validation MAE): \", xgb_search.best_score_, \"\\n\")\n",
+ "\n",
+ "# Apply best parameters\n",
+ "xgb.set_params(**xgb_search.best_params_)\n",
+ "xgb.fit(X_train, y_train)\n",
+ "\n",
+ "# Evaluate XGBoost on the test set and using cross-validation\n",
+ "print(\"Mean absolute error for XGBoost Regression test score: \",\n",
+ " mean_absolute_error(y_test, xgb.predict(X_test)))\n",
+ "print(\"Mean absolute error for XGBoost Regression cross-validation score: \",\n",
+ " np.mean(cross_val_score(xgb, X_train, y_train, scoring='neg_mean_absolute_error')))\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Best ML model selection"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 50,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-5 {\n",
+ " /* Definition of color scheme common for light and dark mode */\n",
+ " --sklearn-color-text: black;\n",
+ " --sklearn-color-line: gray;\n",
+ " /* Definition of color scheme for unfitted estimators */\n",
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
+ " /* Definition of color scheme for fitted estimators */\n",
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
+ "\n",
+ " /* Specific color for light theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-icon: #696969;\n",
+ "\n",
+ " @media (prefers-color-scheme: dark) {\n",
+ " /* Redefinition of color scheme for dark theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-icon: #878787;\n",
+ " }\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 pre {\n",
+ " padding: 0;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 input.sk-hidden--visually {\n",
+ " border: 0;\n",
+ " clip: rect(1px 1px 1px 1px);\n",
+ " clip: rect(1px, 1px, 1px, 1px);\n",
+ " height: 1px;\n",
+ " margin: -1px;\n",
+ " overflow: hidden;\n",
+ " padding: 0;\n",
+ " position: absolute;\n",
+ " width: 1px;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-dashed-wrapped {\n",
+ " border: 1px dashed var(--sklearn-color-line);\n",
+ " margin: 0 0.4em 0.5em 0.4em;\n",
+ " box-sizing: border-box;\n",
+ " padding-bottom: 0.4em;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-container {\n",
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+ " so we also need the `!important` here to be able to override the\n",
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+ " display: inline-block !important;\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-text-repr-fallback {\n",
+ " display: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-parallel-item,\n",
+ "div.sk-serial,\n",
+ "div.sk-item {\n",
+ " /* draw centered vertical line to link estimators */\n",
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+ " background-size: 2px 100%;\n",
+ " background-repeat: no-repeat;\n",
+ " background-position: center center;\n",
+ "}\n",
+ "\n",
+ "/* Parallel-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-5 div.sk-parallel-item::after {\n",
+ " content: \"\";\n",
+ " width: 100%;\n",
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+ " flex-grow: 1;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-parallel {\n",
+ " display: flex;\n",
+ " align-items: stretch;\n",
+ " justify-content: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-parallel-item {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-parallel-item:first-child::after {\n",
+ " align-self: flex-end;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-parallel-item:last-child::after {\n",
+ " align-self: flex-start;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-parallel-item:only-child::after {\n",
+ " width: 0;\n",
+ "}\n",
+ "\n",
+ "/* Serial-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-5 div.sk-serial {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ " align-items: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " padding-right: 1em;\n",
+ " padding-left: 1em;\n",
+ "}\n",
+ "\n",
+ "\n",
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+ "clickable and can be expanded/collapsed.\n",
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+ "*/\n",
+ "\n",
+ "/* Pipeline and ColumnTransformer style (default) */\n",
+ "\n",
+ "#sk-container-id-5 div.sk-toggleable {\n",
+ " /* Default theme specific background. It is overwritten whether we have a\n",
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable label */\n",
+ "#sk-container-id-5 label.sk-toggleable__label {\n",
+ " cursor: pointer;\n",
+ " display: block;\n",
+ " width: 100%;\n",
+ " margin-bottom: 0;\n",
+ " padding: 0.5em;\n",
+ " box-sizing: border-box;\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 label.sk-toggleable__label-arrow:before {\n",
+ " /* Arrow on the left of the label */\n",
+ " content: \"▸\";\n",
+ " float: left;\n",
+ " margin-right: 0.25em;\n",
+ " color: var(--sklearn-color-icon);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 label.sk-toggleable__label-arrow:hover:before {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable content - dropdown */\n",
+ "\n",
+ "#sk-container-id-5 div.sk-toggleable__content {\n",
+ " max-height: 0;\n",
+ " max-width: 0;\n",
+ " overflow: hidden;\n",
+ " text-align: left;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-toggleable__content.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-toggleable__content pre {\n",
+ " margin: 0.2em;\n",
+ " border-radius: 0.25em;\n",
+ " color: var(--sklearn-color-text);\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-toggleable__content.fitted pre {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+ " /* Expand drop-down */\n",
+ " max-height: 200px;\n",
+ " max-width: 100%;\n",
+ " overflow: auto;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+ " content: \"▾\";\n",
+ "}\n",
+ "\n",
+ "/* Pipeline/ColumnTransformer-specific style */\n",
+ "\n",
+ "#sk-container-id-5 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific style */\n",
+ "\n",
+ "/* Colorize estimator box */\n",
+ "#sk-container-id-5 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-label label.sk-toggleable__label,\n",
+ "#sk-container-id-5 div.sk-label label {\n",
+ " /* The background is the default theme color */\n",
+ " color: var(--sklearn-color-text-on-default-background);\n",
+ "}\n",
+ "\n",
+ "/* On hover, darken the color of the background */\n",
+ "#sk-container-id-5 div.sk-label:hover label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Label box, darken color on hover, fitted */\n",
+ "#sk-container-id-5 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator label */\n",
+ "\n",
+ "#sk-container-id-5 div.sk-label label {\n",
+ " font-family: monospace;\n",
+ " font-weight: bold;\n",
+ " display: inline-block;\n",
+ " line-height: 1.2em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-label-container {\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific */\n",
+ "#sk-container-id-5 div.sk-estimator {\n",
+ " font-family: monospace;\n",
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
+ " border-radius: 0.25em;\n",
+ " box-sizing: border-box;\n",
+ " margin-bottom: 0.5em;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-estimator.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "/* on hover */\n",
+ "#sk-container-id-5 div.sk-estimator:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 div.sk-estimator.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+ "\n",
+ "/* Common style for \"i\" and \"?\" */\n",
+ "\n",
+ ".sk-estimator-doc-link,\n",
+ "a:link.sk-estimator-doc-link,\n",
+ "a:visited.sk-estimator-doc-link {\n",
+ " float: right;\n",
+ " font-size: smaller;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1em;\n",
+ " height: 1em;\n",
+ " width: 1em;\n",
+ " text-decoration: none !important;\n",
+ " margin-left: 1ex;\n",
+ " /* unfitted */\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted,\n",
+ "a:link.sk-estimator-doc-link.fitted,\n",
+ "a:visited.sk-estimator-doc-link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "/* Span, style for the box shown on hovering the info icon */\n",
+ ".sk-estimator-doc-link span {\n",
+ " display: none;\n",
+ " z-index: 9999;\n",
+ " position: relative;\n",
+ " font-weight: normal;\n",
+ " right: .2ex;\n",
+ " padding: .5ex;\n",
+ " margin: .5ex;\n",
+ " width: min-content;\n",
+ " min-width: 20ex;\n",
+ " max-width: 50ex;\n",
+ " color: var(--sklearn-color-text);\n",
+ " box-shadow: 2pt 2pt 4pt #999;\n",
+ " /* unfitted */\n",
+ " background: var(--sklearn-color-unfitted-level-0);\n",
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted span {\n",
+ " /* fitted */\n",
+ " background: var(--sklearn-color-fitted-level-0);\n",
+ " border: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link:hover span {\n",
+ " display: block;\n",
+ "}\n",
+ "\n",
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+ "\n",
+ "#sk-container-id-5 a.estimator_doc_link {\n",
+ " float: right;\n",
+ " font-size: 1rem;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1rem;\n",
+ " height: 1rem;\n",
+ " width: 1rem;\n",
+ " text-decoration: none;\n",
+ " /* unfitted */\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 a.estimator_doc_link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "#sk-container-id-5 a.estimator_doc_link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-5 a.estimator_doc_link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "</style><div id=\"sk-container-id-5\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestRegressor(criterion='absolute_error', max_depth=12,\n",
+ " max_features='log2', n_estimators=200, random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" checked><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> RandomForestRegressor<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.ensemble.RandomForestRegressor.html\">?<span>Documentation for RandomForestRegressor</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestRegressor(criterion='absolute_error', max_depth=12,\n",
+ " max_features='log2', n_estimators=200, random_state=42)</pre></div> </div></div></div></div>"
+ ],
+ "text/plain": [
+ "RandomForestRegressor(criterion='absolute_error', max_depth=12,\n",
+ " max_features='log2', n_estimators=200, random_state=42)"
+ ]
+ },
+ "execution_count": 50,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "rf = RandomForestRegressor().set_params(**param_dict_rr)\n",
+ "Xs = StandardScaler().fit_transform(top_features)\n",
+ "rf.fit(Xs, regression_target)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 51,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-6 {\n",
+ " /* Definition of color scheme common for light and dark mode */\n",
+ " --sklearn-color-text: black;\n",
+ " --sklearn-color-line: gray;\n",
+ " /* Definition of color scheme for unfitted estimators */\n",
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
+ " /* Definition of color scheme for fitted estimators */\n",
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
+ "\n",
+ " /* Specific color for light theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-icon: #696969;\n",
+ "\n",
+ " @media (prefers-color-scheme: dark) {\n",
+ " /* Redefinition of color scheme for dark theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-icon: #878787;\n",
+ " }\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 pre {\n",
+ " padding: 0;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 input.sk-hidden--visually {\n",
+ " border: 0;\n",
+ " clip: rect(1px 1px 1px 1px);\n",
+ " clip: rect(1px, 1px, 1px, 1px);\n",
+ " height: 1px;\n",
+ " margin: -1px;\n",
+ " overflow: hidden;\n",
+ " padding: 0;\n",
+ " position: absolute;\n",
+ " width: 1px;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-dashed-wrapped {\n",
+ " border: 1px dashed var(--sklearn-color-line);\n",
+ " margin: 0 0.4em 0.5em 0.4em;\n",
+ " box-sizing: border-box;\n",
+ " padding-bottom: 0.4em;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-container {\n",
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+ " so we also need the `!important` here to be able to override the\n",
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+ " display: inline-block !important;\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-text-repr-fallback {\n",
+ " display: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-parallel-item,\n",
+ "div.sk-serial,\n",
+ "div.sk-item {\n",
+ " /* draw centered vertical line to link estimators */\n",
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+ " background-size: 2px 100%;\n",
+ " background-repeat: no-repeat;\n",
+ " background-position: center center;\n",
+ "}\n",
+ "\n",
+ "/* Parallel-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-6 div.sk-parallel-item::after {\n",
+ " content: \"\";\n",
+ " width: 100%;\n",
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+ " flex-grow: 1;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-parallel {\n",
+ " display: flex;\n",
+ " align-items: stretch;\n",
+ " justify-content: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-parallel-item {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-parallel-item:first-child::after {\n",
+ " align-self: flex-end;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-parallel-item:last-child::after {\n",
+ " align-self: flex-start;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-parallel-item:only-child::after {\n",
+ " width: 0;\n",
+ "}\n",
+ "\n",
+ "/* Serial-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-6 div.sk-serial {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ " align-items: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " padding-right: 1em;\n",
+ " padding-left: 1em;\n",
+ "}\n",
+ "\n",
+ "\n",
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+ "clickable and can be expanded/collapsed.\n",
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+ "*/\n",
+ "\n",
+ "/* Pipeline and ColumnTransformer style (default) */\n",
+ "\n",
+ "#sk-container-id-6 div.sk-toggleable {\n",
+ " /* Default theme specific background. It is overwritten whether we have a\n",
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable label */\n",
+ "#sk-container-id-6 label.sk-toggleable__label {\n",
+ " cursor: pointer;\n",
+ " display: block;\n",
+ " width: 100%;\n",
+ " margin-bottom: 0;\n",
+ " padding: 0.5em;\n",
+ " box-sizing: border-box;\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 label.sk-toggleable__label-arrow:before {\n",
+ " /* Arrow on the left of the label */\n",
+ " content: \"▸\";\n",
+ " float: left;\n",
+ " margin-right: 0.25em;\n",
+ " color: var(--sklearn-color-icon);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 label.sk-toggleable__label-arrow:hover:before {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable content - dropdown */\n",
+ "\n",
+ "#sk-container-id-6 div.sk-toggleable__content {\n",
+ " max-height: 0;\n",
+ " max-width: 0;\n",
+ " overflow: hidden;\n",
+ " text-align: left;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-toggleable__content.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-toggleable__content pre {\n",
+ " margin: 0.2em;\n",
+ " border-radius: 0.25em;\n",
+ " color: var(--sklearn-color-text);\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-toggleable__content.fitted pre {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+ " /* Expand drop-down */\n",
+ " max-height: 200px;\n",
+ " max-width: 100%;\n",
+ " overflow: auto;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+ " content: \"▾\";\n",
+ "}\n",
+ "\n",
+ "/* Pipeline/ColumnTransformer-specific style */\n",
+ "\n",
+ "#sk-container-id-6 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific style */\n",
+ "\n",
+ "/* Colorize estimator box */\n",
+ "#sk-container-id-6 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-label label.sk-toggleable__label,\n",
+ "#sk-container-id-6 div.sk-label label {\n",
+ " /* The background is the default theme color */\n",
+ " color: var(--sklearn-color-text-on-default-background);\n",
+ "}\n",
+ "\n",
+ "/* On hover, darken the color of the background */\n",
+ "#sk-container-id-6 div.sk-label:hover label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Label box, darken color on hover, fitted */\n",
+ "#sk-container-id-6 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator label */\n",
+ "\n",
+ "#sk-container-id-6 div.sk-label label {\n",
+ " font-family: monospace;\n",
+ " font-weight: bold;\n",
+ " display: inline-block;\n",
+ " line-height: 1.2em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-label-container {\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific */\n",
+ "#sk-container-id-6 div.sk-estimator {\n",
+ " font-family: monospace;\n",
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
+ " border-radius: 0.25em;\n",
+ " box-sizing: border-box;\n",
+ " margin-bottom: 0.5em;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-estimator.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "/* on hover */\n",
+ "#sk-container-id-6 div.sk-estimator:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 div.sk-estimator.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+ "\n",
+ "/* Common style for \"i\" and \"?\" */\n",
+ "\n",
+ ".sk-estimator-doc-link,\n",
+ "a:link.sk-estimator-doc-link,\n",
+ "a:visited.sk-estimator-doc-link {\n",
+ " float: right;\n",
+ " font-size: smaller;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1em;\n",
+ " height: 1em;\n",
+ " width: 1em;\n",
+ " text-decoration: none !important;\n",
+ " margin-left: 1ex;\n",
+ " /* unfitted */\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted,\n",
+ "a:link.sk-estimator-doc-link.fitted,\n",
+ "a:visited.sk-estimator-doc-link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "/* Span, style for the box shown on hovering the info icon */\n",
+ ".sk-estimator-doc-link span {\n",
+ " display: none;\n",
+ " z-index: 9999;\n",
+ " position: relative;\n",
+ " font-weight: normal;\n",
+ " right: .2ex;\n",
+ " padding: .5ex;\n",
+ " margin: .5ex;\n",
+ " width: min-content;\n",
+ " min-width: 20ex;\n",
+ " max-width: 50ex;\n",
+ " color: var(--sklearn-color-text);\n",
+ " box-shadow: 2pt 2pt 4pt #999;\n",
+ " /* unfitted */\n",
+ " background: var(--sklearn-color-unfitted-level-0);\n",
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted span {\n",
+ " /* fitted */\n",
+ " background: var(--sklearn-color-fitted-level-0);\n",
+ " border: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link:hover span {\n",
+ " display: block;\n",
+ "}\n",
+ "\n",
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+ "\n",
+ "#sk-container-id-6 a.estimator_doc_link {\n",
+ " float: right;\n",
+ " font-size: 1rem;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1rem;\n",
+ " height: 1rem;\n",
+ " width: 1rem;\n",
+ " text-decoration: none;\n",
+ " /* unfitted */\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 a.estimator_doc_link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "#sk-container-id-6 a.estimator_doc_link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-6 a.estimator_doc_link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "</style><div id=\"sk-container-id-6\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=0.8, device=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=0.1, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=7, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=50, n_jobs=None,\n",
+ " num_parallel_tree=None, random_state=None, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" checked><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> XGBRegressor<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=0.8, device=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=0.1, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=7, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=50, n_jobs=None,\n",
+ " num_parallel_tree=None, random_state=None, ...)</pre></div> </div></div></div></div>"
+ ],
+ "text/plain": [
+ "XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=0.8, device=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=0.1, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=7, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=50, n_jobs=None,\n",
+ " num_parallel_tree=None, random_state=None, ...)"
+ ]
+ },
+ "execution_count": 51,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "xgboost = XGBRegressor().set_params(**xgb_search.best_params_)\n",
+ "Xs = StandardScaler().fit_transform(top_features)\n",
+ "xgboost.fit(Xs, regression_target)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 52,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-7 {\n",
+ " /* Definition of color scheme common for light and dark mode */\n",
+ " --sklearn-color-text: black;\n",
+ " --sklearn-color-line: gray;\n",
+ " /* Definition of color scheme for unfitted estimators */\n",
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
+ " /* Definition of color scheme for fitted estimators */\n",
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
+ "\n",
+ " /* Specific color for light theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-icon: #696969;\n",
+ "\n",
+ " @media (prefers-color-scheme: dark) {\n",
+ " /* Redefinition of color scheme for dark theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-icon: #878787;\n",
+ " }\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 pre {\n",
+ " padding: 0;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 input.sk-hidden--visually {\n",
+ " border: 0;\n",
+ " clip: rect(1px 1px 1px 1px);\n",
+ " clip: rect(1px, 1px, 1px, 1px);\n",
+ " height: 1px;\n",
+ " margin: -1px;\n",
+ " overflow: hidden;\n",
+ " padding: 0;\n",
+ " position: absolute;\n",
+ " width: 1px;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-dashed-wrapped {\n",
+ " border: 1px dashed var(--sklearn-color-line);\n",
+ " margin: 0 0.4em 0.5em 0.4em;\n",
+ " box-sizing: border-box;\n",
+ " padding-bottom: 0.4em;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-container {\n",
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+ " so we also need the `!important` here to be able to override the\n",
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+ " display: inline-block !important;\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-text-repr-fallback {\n",
+ " display: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-parallel-item,\n",
+ "div.sk-serial,\n",
+ "div.sk-item {\n",
+ " /* draw centered vertical line to link estimators */\n",
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+ " background-size: 2px 100%;\n",
+ " background-repeat: no-repeat;\n",
+ " background-position: center center;\n",
+ "}\n",
+ "\n",
+ "/* Parallel-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-7 div.sk-parallel-item::after {\n",
+ " content: \"\";\n",
+ " width: 100%;\n",
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+ " flex-grow: 1;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-parallel {\n",
+ " display: flex;\n",
+ " align-items: stretch;\n",
+ " justify-content: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-parallel-item {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-parallel-item:first-child::after {\n",
+ " align-self: flex-end;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-parallel-item:last-child::after {\n",
+ " align-self: flex-start;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-parallel-item:only-child::after {\n",
+ " width: 0;\n",
+ "}\n",
+ "\n",
+ "/* Serial-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-7 div.sk-serial {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ " align-items: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " padding-right: 1em;\n",
+ " padding-left: 1em;\n",
+ "}\n",
+ "\n",
+ "\n",
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+ "clickable and can be expanded/collapsed.\n",
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+ "*/\n",
+ "\n",
+ "/* Pipeline and ColumnTransformer style (default) */\n",
+ "\n",
+ "#sk-container-id-7 div.sk-toggleable {\n",
+ " /* Default theme specific background. It is overwritten whether we have a\n",
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable label */\n",
+ "#sk-container-id-7 label.sk-toggleable__label {\n",
+ " cursor: pointer;\n",
+ " display: block;\n",
+ " width: 100%;\n",
+ " margin-bottom: 0;\n",
+ " padding: 0.5em;\n",
+ " box-sizing: border-box;\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 label.sk-toggleable__label-arrow:before {\n",
+ " /* Arrow on the left of the label */\n",
+ " content: \"▸\";\n",
+ " float: left;\n",
+ " margin-right: 0.25em;\n",
+ " color: var(--sklearn-color-icon);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 label.sk-toggleable__label-arrow:hover:before {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable content - dropdown */\n",
+ "\n",
+ "#sk-container-id-7 div.sk-toggleable__content {\n",
+ " max-height: 0;\n",
+ " max-width: 0;\n",
+ " overflow: hidden;\n",
+ " text-align: left;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-toggleable__content.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-toggleable__content pre {\n",
+ " margin: 0.2em;\n",
+ " border-radius: 0.25em;\n",
+ " color: var(--sklearn-color-text);\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-toggleable__content.fitted pre {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+ " /* Expand drop-down */\n",
+ " max-height: 200px;\n",
+ " max-width: 100%;\n",
+ " overflow: auto;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+ " content: \"▾\";\n",
+ "}\n",
+ "\n",
+ "/* Pipeline/ColumnTransformer-specific style */\n",
+ "\n",
+ "#sk-container-id-7 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific style */\n",
+ "\n",
+ "/* Colorize estimator box */\n",
+ "#sk-container-id-7 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-label label.sk-toggleable__label,\n",
+ "#sk-container-id-7 div.sk-label label {\n",
+ " /* The background is the default theme color */\n",
+ " color: var(--sklearn-color-text-on-default-background);\n",
+ "}\n",
+ "\n",
+ "/* On hover, darken the color of the background */\n",
+ "#sk-container-id-7 div.sk-label:hover label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Label box, darken color on hover, fitted */\n",
+ "#sk-container-id-7 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator label */\n",
+ "\n",
+ "#sk-container-id-7 div.sk-label label {\n",
+ " font-family: monospace;\n",
+ " font-weight: bold;\n",
+ " display: inline-block;\n",
+ " line-height: 1.2em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-label-container {\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific */\n",
+ "#sk-container-id-7 div.sk-estimator {\n",
+ " font-family: monospace;\n",
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
+ " border-radius: 0.25em;\n",
+ " box-sizing: border-box;\n",
+ " margin-bottom: 0.5em;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-estimator.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "/* on hover */\n",
+ "#sk-container-id-7 div.sk-estimator:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-estimator.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+ "\n",
+ "/* Common style for \"i\" and \"?\" */\n",
+ "\n",
+ ".sk-estimator-doc-link,\n",
+ "a:link.sk-estimator-doc-link,\n",
+ "a:visited.sk-estimator-doc-link {\n",
+ " float: right;\n",
+ " font-size: smaller;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1em;\n",
+ " height: 1em;\n",
+ " width: 1em;\n",
+ " text-decoration: none !important;\n",
+ " margin-left: 1ex;\n",
+ " /* unfitted */\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted,\n",
+ "a:link.sk-estimator-doc-link.fitted,\n",
+ "a:visited.sk-estimator-doc-link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "/* Span, style for the box shown on hovering the info icon */\n",
+ ".sk-estimator-doc-link span {\n",
+ " display: none;\n",
+ " z-index: 9999;\n",
+ " position: relative;\n",
+ " font-weight: normal;\n",
+ " right: .2ex;\n",
+ " padding: .5ex;\n",
+ " margin: .5ex;\n",
+ " width: min-content;\n",
+ " min-width: 20ex;\n",
+ " max-width: 50ex;\n",
+ " color: var(--sklearn-color-text);\n",
+ " box-shadow: 2pt 2pt 4pt #999;\n",
+ " /* unfitted */\n",
+ " background: var(--sklearn-color-unfitted-level-0);\n",
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted span {\n",
+ " /* fitted */\n",
+ " background: var(--sklearn-color-fitted-level-0);\n",
+ " border: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link:hover span {\n",
+ " display: block;\n",
+ "}\n",
+ "\n",
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+ "\n",
+ "#sk-container-id-7 a.estimator_doc_link {\n",
+ " float: right;\n",
+ " font-size: 1rem;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1rem;\n",
+ " height: 1rem;\n",
+ " width: 1rem;\n",
+ " text-decoration: none;\n",
+ " /* unfitted */\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 a.estimator_doc_link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "#sk-container-id-7 a.estimator_doc_link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 a.estimator_doc_link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "</style><div id=\"sk-container-id-7\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SVR(C=8.700000000000001, epsilon=2.9000000000000004)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" checked><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> SVR<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.svm.SVR.html\">?<span>Documentation for SVR</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>SVR(C=8.700000000000001, epsilon=2.9000000000000004)</pre></div> </div></div></div></div>"
+ ],
+ "text/plain": [
+ "SVR(C=8.700000000000001, epsilon=2.9000000000000004)"
+ ]
+ },
+ "execution_count": 52,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "svr = SVR().set_params(**param_dict_svr)\n",
+ "Xs = StandardScaler().fit_transform(top_features)\n",
+ "svr.fit(Xs, regression_target)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 53,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-8 {\n",
+ " /* Definition of color scheme common for light and dark mode */\n",
+ " --sklearn-color-text: black;\n",
+ " --sklearn-color-line: gray;\n",
+ " /* Definition of color scheme for unfitted estimators */\n",
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
+ " /* Definition of color scheme for fitted estimators */\n",
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
+ "\n",
+ " /* Specific color for light theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-icon: #696969;\n",
+ "\n",
+ " @media (prefers-color-scheme: dark) {\n",
+ " /* Redefinition of color scheme for dark theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-icon: #878787;\n",
+ " }\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 pre {\n",
+ " padding: 0;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 input.sk-hidden--visually {\n",
+ " border: 0;\n",
+ " clip: rect(1px 1px 1px 1px);\n",
+ " clip: rect(1px, 1px, 1px, 1px);\n",
+ " height: 1px;\n",
+ " margin: -1px;\n",
+ " overflow: hidden;\n",
+ " padding: 0;\n",
+ " position: absolute;\n",
+ " width: 1px;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-dashed-wrapped {\n",
+ " border: 1px dashed var(--sklearn-color-line);\n",
+ " margin: 0 0.4em 0.5em 0.4em;\n",
+ " box-sizing: border-box;\n",
+ " padding-bottom: 0.4em;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-container {\n",
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+ " so we also need the `!important` here to be able to override the\n",
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+ " display: inline-block !important;\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-text-repr-fallback {\n",
+ " display: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-parallel-item,\n",
+ "div.sk-serial,\n",
+ "div.sk-item {\n",
+ " /* draw centered vertical line to link estimators */\n",
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+ " background-size: 2px 100%;\n",
+ " background-repeat: no-repeat;\n",
+ " background-position: center center;\n",
+ "}\n",
+ "\n",
+ "/* Parallel-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-8 div.sk-parallel-item::after {\n",
+ " content: \"\";\n",
+ " width: 100%;\n",
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+ " flex-grow: 1;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-parallel {\n",
+ " display: flex;\n",
+ " align-items: stretch;\n",
+ " justify-content: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-parallel-item {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-parallel-item:first-child::after {\n",
+ " align-self: flex-end;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-parallel-item:last-child::after {\n",
+ " align-self: flex-start;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-parallel-item:only-child::after {\n",
+ " width: 0;\n",
+ "}\n",
+ "\n",
+ "/* Serial-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-8 div.sk-serial {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ " align-items: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " padding-right: 1em;\n",
+ " padding-left: 1em;\n",
+ "}\n",
+ "\n",
+ "\n",
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+ "clickable and can be expanded/collapsed.\n",
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+ "*/\n",
+ "\n",
+ "/* Pipeline and ColumnTransformer style (default) */\n",
+ "\n",
+ "#sk-container-id-8 div.sk-toggleable {\n",
+ " /* Default theme specific background. It is overwritten whether we have a\n",
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable label */\n",
+ "#sk-container-id-8 label.sk-toggleable__label {\n",
+ " cursor: pointer;\n",
+ " display: block;\n",
+ " width: 100%;\n",
+ " margin-bottom: 0;\n",
+ " padding: 0.5em;\n",
+ " box-sizing: border-box;\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 label.sk-toggleable__label-arrow:before {\n",
+ " /* Arrow on the left of the label */\n",
+ " content: \"▸\";\n",
+ " float: left;\n",
+ " margin-right: 0.25em;\n",
+ " color: var(--sklearn-color-icon);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 label.sk-toggleable__label-arrow:hover:before {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable content - dropdown */\n",
+ "\n",
+ "#sk-container-id-8 div.sk-toggleable__content {\n",
+ " max-height: 0;\n",
+ " max-width: 0;\n",
+ " overflow: hidden;\n",
+ " text-align: left;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-toggleable__content.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-toggleable__content pre {\n",
+ " margin: 0.2em;\n",
+ " border-radius: 0.25em;\n",
+ " color: var(--sklearn-color-text);\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-toggleable__content.fitted pre {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+ " /* Expand drop-down */\n",
+ " max-height: 200px;\n",
+ " max-width: 100%;\n",
+ " overflow: auto;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+ " content: \"▾\";\n",
+ "}\n",
+ "\n",
+ "/* Pipeline/ColumnTransformer-specific style */\n",
+ "\n",
+ "#sk-container-id-8 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific style */\n",
+ "\n",
+ "/* Colorize estimator box */\n",
+ "#sk-container-id-8 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-label label.sk-toggleable__label,\n",
+ "#sk-container-id-8 div.sk-label label {\n",
+ " /* The background is the default theme color */\n",
+ " color: var(--sklearn-color-text-on-default-background);\n",
+ "}\n",
+ "\n",
+ "/* On hover, darken the color of the background */\n",
+ "#sk-container-id-8 div.sk-label:hover label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Label box, darken color on hover, fitted */\n",
+ "#sk-container-id-8 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator label */\n",
+ "\n",
+ "#sk-container-id-8 div.sk-label label {\n",
+ " font-family: monospace;\n",
+ " font-weight: bold;\n",
+ " display: inline-block;\n",
+ " line-height: 1.2em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-label-container {\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific */\n",
+ "#sk-container-id-8 div.sk-estimator {\n",
+ " font-family: monospace;\n",
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
+ " border-radius: 0.25em;\n",
+ " box-sizing: border-box;\n",
+ " margin-bottom: 0.5em;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-estimator.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "/* on hover */\n",
+ "#sk-container-id-8 div.sk-estimator:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-estimator.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+ "\n",
+ "/* Common style for \"i\" and \"?\" */\n",
+ "\n",
+ ".sk-estimator-doc-link,\n",
+ "a:link.sk-estimator-doc-link,\n",
+ "a:visited.sk-estimator-doc-link {\n",
+ " float: right;\n",
+ " font-size: smaller;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1em;\n",
+ " height: 1em;\n",
+ " width: 1em;\n",
+ " text-decoration: none !important;\n",
+ " margin-left: 1ex;\n",
+ " /* unfitted */\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted,\n",
+ "a:link.sk-estimator-doc-link.fitted,\n",
+ "a:visited.sk-estimator-doc-link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "/* Span, style for the box shown on hovering the info icon */\n",
+ ".sk-estimator-doc-link span {\n",
+ " display: none;\n",
+ " z-index: 9999;\n",
+ " position: relative;\n",
+ " font-weight: normal;\n",
+ " right: .2ex;\n",
+ " padding: .5ex;\n",
+ " margin: .5ex;\n",
+ " width: min-content;\n",
+ " min-width: 20ex;\n",
+ " max-width: 50ex;\n",
+ " color: var(--sklearn-color-text);\n",
+ " box-shadow: 2pt 2pt 4pt #999;\n",
+ " /* unfitted */\n",
+ " background: var(--sklearn-color-unfitted-level-0);\n",
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted span {\n",
+ " /* fitted */\n",
+ " background: var(--sklearn-color-fitted-level-0);\n",
+ " border: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link:hover span {\n",
+ " display: block;\n",
+ "}\n",
+ "\n",
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+ "\n",
+ "#sk-container-id-8 a.estimator_doc_link {\n",
+ " float: right;\n",
+ " font-size: 1rem;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1rem;\n",
+ " height: 1rem;\n",
+ " width: 1rem;\n",
+ " text-decoration: none;\n",
+ " /* unfitted */\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 a.estimator_doc_link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "#sk-container-id-8 a.estimator_doc_link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 a.estimator_doc_link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "</style><div id=\"sk-container-id-8\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Lasso(alpha=100)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" checked><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> Lasso<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.linear_model.Lasso.html\">?<span>Documentation for Lasso</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>Lasso(alpha=100)</pre></div> </div></div></div></div>"
+ ],
+ "text/plain": [
+ "Lasso(alpha=100)"
+ ]
+ },
+ "execution_count": 53,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "lasso = Lasso().set_params(**param_dict_lasso)\n",
+ "Xs = StandardScaler().fit_transform(top_features)\n",
+ "lasso.fit(Xs, regression_target)\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Predictions"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 54,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "mean_absolute_error Random Forest Regressor 21.70109895849521\n",
+ "mean_absolute_error XGBOOST : 23.603017563428956\n",
+ "mean_absolute_error SVR : 21.496141704952574\n",
+ "mean_absolute_error Lasso : 21.531602456976973\n"
+ ]
+ }
+ ],
+ "source": [
+ "predictions = rf.predict(X_test)\n",
+ "print(\"mean_absolute_error Random Forest Regressor\",mean_absolute_error(y_test,predictions))\n",
+ "\n",
+ "predictions = xgboost.predict(X_test)\n",
+ "print(\"mean_absolute_error XGBOOST : \",mean_absolute_error(y_test,predictions))\n",
+ "\n",
+ "predictions = svr.predict(X_test)\n",
+ "print(\"mean_absolute_error SVR :\",mean_absolute_error(y_test,predictions))\n",
+ "\n",
+ "\n",
+ "predictions = lasso.predict(X_test)\n",
+ "print(\"mean_absolute_error Lasso :\",mean_absolute_error(y_test,predictions))\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 55,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pickle"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"svr_test.pickle\", \"wb\") as f:\n",
+ " pickle.dump(rf, f)"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "base",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.12.2"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}