Downloads: 1
Diff of
/FinalTestPCR.ipynb
[000000]
..
[4bdf3e]
Switch to unified view
| a | b/FinalTestPCR.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "code", |
||
| 5 | "execution_count": 65, |
||
| 6 | "id": "09f2ef64", |
||
| 7 | "metadata": {}, |
||
| 8 | "outputs": [], |
||
| 9 | "source": [ |
||
| 10 | "# importing the model\n", |
||
| 11 | "\n", |
||
| 12 | "import joblib\n", |
||
| 13 | "model = joblib.load('XGBoost_final.pkl')" |
||
| 14 | ] |
||
| 15 | }, |
||
| 16 | { |
||
| 17 | "cell_type": "code", |
||
| 18 | "execution_count": 60, |
||
| 19 | "id": "d4325fde", |
||
| 20 | "metadata": { |
||
| 21 | "scrolled": false |
||
| 22 | }, |
||
| 23 | "outputs": [], |
||
| 24 | "source": [ |
||
| 25 | "# loading the test dataset\n", |
||
| 26 | "\n", |
||
| 27 | "import pandas as pd\n", |
||
| 28 | "test_Df = pd.read_excel('TestDatasetExample (1).xls') # change this to the required file name/path." |
||
| 29 | ] |
||
| 30 | }, |
||
| 31 | { |
||
| 32 | "cell_type": "code", |
||
| 33 | "execution_count": 61, |
||
| 34 | "id": "bca2827b", |
||
| 35 | "metadata": {}, |
||
| 36 | "outputs": [], |
||
| 37 | "source": [ |
||
| 38 | "from sklearn.decomposition import PCA\n", |
||
| 39 | "from sklearn.preprocessing import StandardScaler\n", |
||
| 40 | "\n", |
||
| 41 | "# preprocessing and null value removal.\n", |
||
| 42 | "\n", |
||
| 43 | "test_Df=test_Df.replace(999, None)\n", |
||
| 44 | "\n", |
||
| 45 | "#imputation using mode\n", |
||
| 46 | "for col in test_Df.columns:\n", |
||
| 47 | " test_Df[col].fillna(test_Df[col].mode()[0], inplace=True)\n", |
||
| 48 | "\n", |
||
| 49 | "# only column 11 onwards taken for pca\n", |
||
| 50 | "test_Df_forPCA = test_Df.iloc[:,11:]\n", |
||
| 51 | "\n", |
||
| 52 | "# Standardize the features\n", |
||
| 53 | "scaler = StandardScaler()\n", |
||
| 54 | "test_Df_forPCA = scaler.fit_transform(test_Df_forPCA)\n", |
||
| 55 | "\n", |
||
| 56 | "# Perform PCA\n", |
||
| 57 | "pca = PCA(n_components=6) # Reduce to 6 principal components\n", |
||
| 58 | "test_Df_afterPCA = pca.fit_transform(test_Df_forPCA)\n", |
||
| 59 | "\n", |
||
| 60 | "test_Df_afterPCA = pd.DataFrame(test_Df_afterPCA)\n", |
||
| 61 | "test_Df = test_Df.iloc[:,0:11].merge(test_Df_afterPCA, left_index = True, right_index = True, how = 'right')\n", |
||
| 62 | "\n", |
||
| 63 | "new_column_names = {0: 'COMP0', 1: 'COMP1', 2: 'COMP2',3: 'COMP3',4:'COMP4',5:'COMP5',}\n", |
||
| 64 | "test_Df = test_Df.rename(columns=new_column_names)\n", |
||
| 65 | "\n", |
||
| 66 | "# scaling all the values\n", |
||
| 67 | "test_Df[['Age']] = StandardScaler().fit_transform(test_Df[['Age']])\n", |
||
| 68 | "\n", |
||
| 69 | "#drop proliferation as its not needed.\n", |
||
| 70 | "test_Df = test_Df.drop(columns=['Proliferation'])" |
||
| 71 | ] |
||
| 72 | }, |
||
| 73 | { |
||
| 74 | "cell_type": "code", |
||
| 75 | "execution_count": 62, |
||
| 76 | "id": "42d4a3c7", |
||
| 77 | "metadata": {}, |
||
| 78 | "outputs": [], |
||
| 79 | "source": [ |
||
| 80 | "# Making predictions on data\n", |
||
| 81 | "test_predictions = model.predict(test_Df.drop(columns=['ID']))" |
||
| 82 | ] |
||
| 83 | }, |
||
| 84 | { |
||
| 85 | "cell_type": "code", |
||
| 86 | "execution_count": 63, |
||
| 87 | "id": "da1931da", |
||
| 88 | "metadata": {}, |
||
| 89 | "outputs": [], |
||
| 90 | "source": [ |
||
| 91 | "test_predictions = pd.DataFrame(test_predictions, columns=['pCR(result)'])" |
||
| 92 | ] |
||
| 93 | }, |
||
| 94 | { |
||
| 95 | "cell_type": "code", |
||
| 96 | "execution_count": 64, |
||
| 97 | "id": "3fba86a0", |
||
| 98 | "metadata": {}, |
||
| 99 | "outputs": [], |
||
| 100 | "source": [ |
||
| 101 | "to_excel_Df = pd.DataFrame(test_Df['ID'])\n", |
||
| 102 | "#data after handling missing values\n", |
||
| 103 | "to_excel_Df = pd.concat((to_excel_Df, test_predictions), axis=1)\n", |
||
| 104 | "to_excel_Df.to_excel('FinalTestPCR.xlsx', index=False, header=True)\n", |
||
| 105 | "\n", |
||
| 106 | " " |
||
| 107 | ] |
||
| 108 | }, |
||
| 109 | { |
||
| 110 | "cell_type": "code", |
||
| 111 | "execution_count": null, |
||
| 112 | "id": "45827c84", |
||
| 113 | "metadata": {}, |
||
| 114 | "outputs": [], |
||
| 115 | "source": [] |
||
| 116 | }, |
||
| 117 | { |
||
| 118 | "cell_type": "code", |
||
| 119 | "execution_count": null, |
||
| 120 | "id": "77571afa", |
||
| 121 | "metadata": {}, |
||
| 122 | "outputs": [], |
||
| 123 | "source": [] |
||
| 124 | } |
||
| 125 | ], |
||
| 126 | "metadata": { |
||
| 127 | "kernelspec": { |
||
| 128 | "display_name": "Python 3 (ipykernel)", |
||
| 129 | "language": "python", |
||
| 130 | "name": "python3" |
||
| 131 | }, |
||
| 132 | "language_info": { |
||
| 133 | "codemirror_mode": { |
||
| 134 | "name": "ipython", |
||
| 135 | "version": 3 |
||
| 136 | }, |
||
| 137 | "file_extension": ".py", |
||
| 138 | "mimetype": "text/x-python", |
||
| 139 | "name": "python", |
||
| 140 | "nbconvert_exporter": "python", |
||
| 141 | "pygments_lexer": "ipython3", |
||
| 142 | "version": "3.10.11" |
||
| 143 | } |
||
| 144 | }, |
||
| 145 | "nbformat": 4, |
||
| 146 | "nbformat_minor": 5 |
||
| 147 | } |