Datasets
Models
Downloads: 1
Diff of
/03-Experiments/12-AutoGluon.ipynb
[000000]
..
[b4c0b6]
Switch to unified view
| a | b/03-Experiments/12-AutoGluon.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "code", |
||
| 5 | "execution_count": 1, |
||
| 6 | "metadata": {}, |
||
| 7 | "outputs": [ |
||
| 8 | { |
||
| 9 | "data": { |
||
| 10 | "text/plain": [ |
||
| 11 | "<Experiment: artifact_location='/Users/arham/Downloads/Projects/03-Experiments/mlruns/3', creation_time=1713916994501, experiment_id='3', last_update_time=1713916994501, lifecycle_stage='active', name='AutoGluon', tags={}>" |
||
| 12 | ] |
||
| 13 | }, |
||
| 14 | "execution_count": 1, |
||
| 15 | "metadata": {}, |
||
| 16 | "output_type": "execute_result" |
||
| 17 | } |
||
| 18 | ], |
||
| 19 | "source": [ |
||
| 20 | "import mlflow\n", |
||
| 21 | "\n", |
||
| 22 | "# Set the MLflow tracking URI to a new SQLite URI\n", |
||
| 23 | "mlflow.set_tracking_uri(\"sqlite:///new_mlflow.db\")\n", |
||
| 24 | "mlflow.set_experiment(\"AutoGluon\")" |
||
| 25 | ] |
||
| 26 | }, |
||
| 27 | { |
||
| 28 | "cell_type": "markdown", |
||
| 29 | "metadata": {}, |
||
| 30 | "source": [ |
||
| 31 | "Experiment Setup" |
||
| 32 | ] |
||
| 33 | }, |
||
| 34 | { |
||
| 35 | "cell_type": "code", |
||
| 36 | "execution_count": 12, |
||
| 37 | "metadata": {}, |
||
| 38 | "outputs": [], |
||
| 39 | "source": [ |
||
| 40 | "import pandas as pd\n", |
||
| 41 | "from sklearn.model_selection import train_test_split\n", |
||
| 42 | "import matplotlib.pyplot as plt\n", |
||
| 43 | "import seaborn as sns\n", |
||
| 44 | "import numpy as np\n", |
||
| 45 | "from sklearn.preprocessing import MinMaxScaler\n", |
||
| 46 | "from sklearn.preprocessing import PolynomialFeatures\n", |
||
| 47 | "import lightgbm as lgb\n", |
||
| 48 | "from sklearn.metrics import accuracy_score\n", |
||
| 49 | "\n", |
||
| 50 | "import pandas as pd\n", |
||
| 51 | "from sklearn.model_selection import train_test_split\n", |
||
| 52 | "import matplotlib.pyplot as plt\n", |
||
| 53 | "import seaborn as sns\n", |
||
| 54 | "import numpy as np\n", |
||
| 55 | "from sklearn.preprocessing import MinMaxScaler\n", |
||
| 56 | "from sklearn.preprocessing import PolynomialFeatures\n", |
||
| 57 | "import lightgbm as lgb\n", |
||
| 58 | "from sklearn.metrics import accuracy_score\n", |
||
| 59 | "import warnings\n", |
||
| 60 | "from sklearn.tree import DecisionTreeClassifier\n", |
||
| 61 | "from sklearn.model_selection import cross_val_score\n", |
||
| 62 | "from sklearn.metrics import accuracy_score, precision_score, recall_score\n", |
||
| 63 | "import xgboost as xgb\n", |
||
| 64 | "from sklearn.metrics import accuracy_score, precision_score, recall_score\n", |
||
| 65 | "from sklearn.model_selection import cross_val_score\n", |
||
| 66 | "\n", |
||
| 67 | "\n", |
||
| 68 | "def load_data(path):\n", |
||
| 69 | " df = pd.read_csv(path)\n", |
||
| 70 | " train_df, test_df = train_test_split(df, test_size=0.35, random_state=42)\n", |
||
| 71 | " train_df, val_df, = train_test_split(train_df, test_size=0.20, random_state=42)\n", |
||
| 72 | " train_df = train_df.drop(['id'], axis=1).drop_duplicates().reset_index(drop=True)\n", |
||
| 73 | " test_df = test_df.drop(['id'], axis=1).drop_duplicates().reset_index(drop=True)\n", |
||
| 74 | " val_df = val_df.drop(['id'], axis=1).drop_duplicates().reset_index(drop=True)\n", |
||
| 75 | " return train_df, val_df, test_df\n", |
||
| 76 | "\n", |
||
| 77 | "def encode_target(train):\n", |
||
| 78 | " target_key = {'Insufficient_Weight': 0, 'Normal_Weight': 1, 'Overweight_Level_I': 2, 'Overweight_Level_II': 3, 'Obesity_Type_I': 4,'Obesity_Type_II' : 5, 'Obesity_Type_III': 6}\n", |
||
| 79 | " train['NObeyesdad'] = train['NObeyesdad'].map(target_key)\n", |
||
| 80 | " return train\n", |
||
| 81 | "\n", |
||
| 82 | "def make_gender_binary(train):\n", |
||
| 83 | " train['Gender'] = train['Gender'].map({'Male':0, 'Female':1})\n", |
||
| 84 | "\n", |
||
| 85 | "def datatypes(train):\n", |
||
| 86 | " train['Weight'] = train['Weight'].astype(float)\n", |
||
| 87 | " train['Age'] = train['Age'].astype(float)\n", |
||
| 88 | " train['Height'] = train['Height'].astype(float)\n", |
||
| 89 | " return train\n", |
||
| 90 | "\n", |
||
| 91 | "# def age_binning(train_df):\n", |
||
| 92 | "# # train_df['Age_Group'] = pd.cut(train_df['Age'], bins=[0, 20, 30, 40, 50, train_df['Age'].max()], labels=['0-20', '21-30', '31-40', '41-50', '50+'])\n", |
||
| 93 | "# train_df['Age_Group'] = pd.cut(train_df['Age'], bins=[0, 20, 30, 40, 50, train_df['Age'].max()], labels=[1, 2, 3, 4, 5])\n", |
||
| 94 | "# train_df['Age_Group'] = train_df['Age_Group'].astype(int)\n", |
||
| 95 | "# return train_df\n", |
||
| 96 | "\n", |
||
| 97 | "def age_binning(df):\n", |
||
| 98 | " age_groups = []\n", |
||
| 99 | " for age in df['Age']:\n", |
||
| 100 | " if age <= 20:\n", |
||
| 101 | " age_group = 1\n", |
||
| 102 | " elif age <= 30:\n", |
||
| 103 | " age_group = 2\n", |
||
| 104 | " elif age <= 40:\n", |
||
| 105 | " age_group = 3\n", |
||
| 106 | " elif age <= 50:\n", |
||
| 107 | " age_group = 4\n", |
||
| 108 | " else:\n", |
||
| 109 | " age_group = 5\n", |
||
| 110 | " age_groups.append(age_group)\n", |
||
| 111 | " df['Age_Group'] = age_groups\n", |
||
| 112 | " return df\n", |
||
| 113 | "\n", |
||
| 114 | "def age_scaling_log(train_df):\n", |
||
| 115 | " train_df['Age'] = train_df['Age'].astype(float)\n", |
||
| 116 | " train_df['Log_Age'] = np.log1p(train_df['Age'])\n", |
||
| 117 | " return train_df\n", |
||
| 118 | "\n", |
||
| 119 | "def age_scaling_minmax(train_df):\n", |
||
| 120 | " train_df['Age'] = train_df['Age'].astype(float)\n", |
||
| 121 | " scaler_age = MinMaxScaler()\n", |
||
| 122 | " train_df['Scaled_Age'] = scaler_age.fit_transform(train_df['Age'].values.reshape(-1, 1))\n", |
||
| 123 | " return train_df, scaler_age\n", |
||
| 124 | "\n", |
||
| 125 | "def weight_scaling_log(train_df):\n", |
||
| 126 | " train_df['Weight'] = train_df['Weight'].astype(float)\n", |
||
| 127 | " train_df['Log_Weight'] = np.log1p(train_df['Weight'])\n", |
||
| 128 | " return train_df\n", |
||
| 129 | "\n", |
||
| 130 | "def weight_scaling_minmax(train_df):\n", |
||
| 131 | " train_df['Weight'] = train_df['Weight'].astype(float)\n", |
||
| 132 | " scaler_weight = MinMaxScaler()\n", |
||
| 133 | " train_df['Scaled_Weight'] = scaler_weight.fit_transform(train_df['Weight'].values.reshape(-1, 1))\n", |
||
| 134 | " return train_df, scaler_weight\n", |
||
| 135 | "\n", |
||
| 136 | "def height_scaling_log(train_df):\n", |
||
| 137 | " train_df['Log_Height'] = np.log1p(train_df['Height'])\n", |
||
| 138 | " return train_df\n", |
||
| 139 | "\n", |
||
| 140 | "def height_scaling_minmax(train_df):\n", |
||
| 141 | " scaler_height = MinMaxScaler()\n", |
||
| 142 | " train_df['Scaled_Height'] = scaler_height.fit_transform(train_df['Height'].values.reshape(-1, 1))\n", |
||
| 143 | " return train_df, scaler_height\n", |
||
| 144 | "\n", |
||
| 145 | "def make_gender_binary(train):\n", |
||
| 146 | " train['Gender'] = train['Gender'].map({'Female':1, 'Male':0})\n", |
||
| 147 | " return train\n", |
||
| 148 | "\n", |
||
| 149 | "def fix_binary_columns(train):\n", |
||
| 150 | " Binary_Cols = ['family_history_with_overweight','FAVC', 'SCC','SMOKE']\n", |
||
| 151 | " # if yes then 1 else 0\n", |
||
| 152 | " for col in Binary_Cols:\n", |
||
| 153 | " train[col] = train[col].map({'yes': 1, 'no': 0})\n", |
||
| 154 | " # column datatype integer\n", |
||
| 155 | " train[col] = train[col].astype(int)\n", |
||
| 156 | " return train\n", |
||
| 157 | "\n", |
||
| 158 | "def freq_cat_cols(train):\n", |
||
| 159 | " # One hot encoding\n", |
||
| 160 | " cat_cols = ['CAEC', 'CALC']\n", |
||
| 161 | " for col in cat_cols:\n", |
||
| 162 | " train[col] = train[col].map({'no': 0, 'Sometimes': 1, 'Frequently': 2, 'Always': 3})\n", |
||
| 163 | " return train\n", |
||
| 164 | "\n", |
||
| 165 | "def Mtrans(train):\n", |
||
| 166 | " \"\"\"\n", |
||
| 167 | " Public_Transportation 8692\n", |
||
| 168 | " Automobile 1835\n", |
||
| 169 | " Walking 231\n", |
||
| 170 | " Motorbike 19\n", |
||
| 171 | " Bike 16\n", |
||
| 172 | " \"\"\"\n", |
||
| 173 | " # train['MTRANS'] = train['MTRANS'].map({'Public_Transportation': 3, 'Automobile': 5, 'Walking': 1, 'Motorbike': 4, 'Bike': 2})\n", |
||
| 174 | " # dummify column\n", |
||
| 175 | " train = pd.get_dummies(train, columns=['MTRANS'])\n", |
||
| 176 | " # convert these columns to integer\n", |
||
| 177 | " train['MTRANS_Automobile'] = train['MTRANS_Automobile'].astype(int)\n", |
||
| 178 | " train['MTRANS_Walking'] = train['MTRANS_Walking'].astype(int)\n", |
||
| 179 | " train['MTRANS_Motorbike'] = train['MTRANS_Motorbike'].astype(int)\n", |
||
| 180 | " train['MTRANS_Bike'] = train['MTRANS_Bike'].astype(int)\n", |
||
| 181 | " train['MTRANS_Public_Transportation'] = train['MTRANS_Public_Transportation'].astype(int)\n", |
||
| 182 | " return train\n", |
||
| 183 | "\n", |
||
| 184 | "\n", |
||
| 185 | "def other_features(train):\n", |
||
| 186 | " train['BMI'] = train['Weight'] / (train['Height'] ** 2)\n", |
||
| 187 | " # train['Age'*'Gender'] = train['Age'] * train['Gender']\n", |
||
| 188 | " polynomial_features = PolynomialFeatures(degree=2)\n", |
||
| 189 | " X_poly = polynomial_features.fit_transform(train[['Age', 'BMI']])\n", |
||
| 190 | " poly_features_df = pd.DataFrame(X_poly, columns=['Age^2', 'Age^3', 'BMI^2', 'Age * BMI', 'Age * BMI^2', 'Age^2 * BMI^2'])\n", |
||
| 191 | " train = pd.concat([train, poly_features_df], axis=1)\n", |
||
| 192 | " return train\n", |
||
| 193 | "\n", |
||
| 194 | "\n", |
||
| 195 | "def test_pipeline(test, scaler_age, scaler_weight, scaler_height):\n", |
||
| 196 | " test = datatypes(test)\n", |
||
| 197 | " test = encode_target(test)\n", |
||
| 198 | " test = age_binning(test)\n", |
||
| 199 | " test = age_scaling_log(test)\n", |
||
| 200 | " test['Scaled_Age'] = scaler_age.transform(test['Age'].values.reshape(-1, 1))\n", |
||
| 201 | " test = weight_scaling_log(test)\n", |
||
| 202 | " test['Scaled_Weight'] = scaler_weight.transform(test['Weight'].values.reshape(-1, 1))\n", |
||
| 203 | " test = height_scaling_log(test)\n", |
||
| 204 | " test['Scaled_Height'] = scaler_height.transform(test['Height'].values.reshape(-1, 1))\n", |
||
| 205 | " test = make_gender_binary(test)\n", |
||
| 206 | " test = fix_binary_columns(test)\n", |
||
| 207 | " test = freq_cat_cols(test)\n", |
||
| 208 | " test = Mtrans(test)\n", |
||
| 209 | " test = other_features(test)\n", |
||
| 210 | "\n", |
||
| 211 | " return test\n", |
||
| 212 | "\n", |
||
| 213 | "def train_model(params, X_train, y_train):\n", |
||
| 214 | " lgb_train = lgb.Dataset(X_train, y_train)\n", |
||
| 215 | " model = lgb.train(params, lgb_train, num_boost_round=1000)\n", |
||
| 216 | " return model\n", |
||
| 217 | "\n", |
||
| 218 | "def evaluate_model(model, X_val, y_val):\n", |
||
| 219 | " y_pred = model.predict(X_val)\n", |
||
| 220 | " y_pred = [np.argmax(y) for y in y_pred]\n", |
||
| 221 | " accuracy = accuracy_score(y_val, y_pred)\n", |
||
| 222 | " return accuracy\n", |
||
| 223 | "\n", |
||
| 224 | "def objective(trial, X_train, y_train):\n", |
||
| 225 | " params = {\n", |
||
| 226 | " 'objective': 'multiclass',\n", |
||
| 227 | " 'num_class': 7,\n", |
||
| 228 | " 'metric': 'multi_logloss',\n", |
||
| 229 | " 'boosting_type': 'gbdt',\n", |
||
| 230 | " 'learning_rate': trial.suggest_loguniform('learning_rate', 0.005, 0.5),\n", |
||
| 231 | " 'num_leaves': trial.suggest_int('num_leaves', 10, 1000),\n", |
||
| 232 | " 'max_depth': trial.suggest_int('max_depth', -1, 20),\n", |
||
| 233 | " 'bagging_fraction': trial.suggest_uniform('bagging_fraction', 0.6, 0.95),\n", |
||
| 234 | " 'feature_fraction': trial.suggest_uniform('feature_fraction', 0.6, 0.95),\n", |
||
| 235 | " 'verbosity': -1\n", |
||
| 236 | " }\n", |
||
| 237 | "\n", |
||
| 238 | " n_splits = 5\n", |
||
| 239 | " kf = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=42)\n", |
||
| 240 | " scores = []\n", |
||
| 241 | "\n", |
||
| 242 | " for train_index, val_index in kf.split(X_train, y_train):\n", |
||
| 243 | " X_tr, X_val = X_train.iloc[train_index], X_train.iloc[val_index]\n", |
||
| 244 | " y_tr, y_val = y_train.iloc[train_index], y_train.iloc[val_index]\n", |
||
| 245 | "\n", |
||
| 246 | " model = train_model(params, X_tr, y_tr)\n", |
||
| 247 | " accuracy = evaluate_model(model, X_val, y_val)\n", |
||
| 248 | " scores.append(accuracy)\n", |
||
| 249 | "\n", |
||
| 250 | " return np.mean(scores)\n", |
||
| 251 | "\n", |
||
| 252 | "def optimize_hyperparameters(X_train, y_train, n_trials=2):\n", |
||
| 253 | " study = optuna.create_study(direction='maximize')\n", |
||
| 254 | " study.optimize(lambda trial: objective(trial, X_train, y_train), n_trials=n_trials)\n", |
||
| 255 | " return study.best_params" |
||
| 256 | ] |
||
| 257 | }, |
||
| 258 | { |
||
| 259 | "cell_type": "markdown", |
||
| 260 | "metadata": {}, |
||
| 261 | "source": [ |
||
| 262 | "Experiment" |
||
| 263 | ] |
||
| 264 | }, |
||
| 265 | { |
||
| 266 | "cell_type": "code", |
||
| 267 | "execution_count": 13, |
||
| 268 | "metadata": {}, |
||
| 269 | "outputs": [], |
||
| 270 | "source": [ |
||
| 271 | "path = '/Users/arham/Downloads/Projects/01-Dataset/01-Data-for-model-building/train.csv'\n", |
||
| 272 | "train_df, val_df, test_df = load_data(path)\n", |
||
| 273 | "\n", |
||
| 274 | "train_df = datatypes(train_df)\n", |
||
| 275 | "train_df = encode_target(train_df)\n", |
||
| 276 | "train_df = age_binning(train_df)\n", |
||
| 277 | "train_df, scaler_age = age_scaling_minmax(train_df)\n", |
||
| 278 | "train_df = age_scaling_log(train_df)\n", |
||
| 279 | "train_df, scaler_weight = weight_scaling_minmax(train_df)\n", |
||
| 280 | "train_df = weight_scaling_log(train_df)\n", |
||
| 281 | "train_df, scaler_height = height_scaling_minmax(train_df)\n", |
||
| 282 | "train_df = height_scaling_log(train_df)\n", |
||
| 283 | "train_df = make_gender_binary(train_df)\n", |
||
| 284 | "train_df = fix_binary_columns(train_df)\n", |
||
| 285 | "train_df = freq_cat_cols(train_df)\n", |
||
| 286 | "train_df = Mtrans(train_df)\n", |
||
| 287 | "train_df = other_features(train_df)\n", |
||
| 288 | "\n", |
||
| 289 | "val_df = test_pipeline(val_df, scaler_age, scaler_weight, scaler_height)\n", |
||
| 290 | "test_df = test_pipeline(test_df, scaler_age, scaler_weight, scaler_height)\n", |
||
| 291 | "\n", |
||
| 292 | "Target = 'NObeyesdad'\n", |
||
| 293 | "features = train_df.columns.drop(Target)\n", |
||
| 294 | "\n", |
||
| 295 | "features = ['Gender', 'Age', 'Height', 'Weight', 'family_history_with_overweight',\n", |
||
| 296 | " 'FAVC', 'FCVC', 'NCP', 'CAEC', 'SMOKE', 'CH2O', 'SCC', 'FAF', 'TUE',\n", |
||
| 297 | " 'CALC', \n", |
||
| 298 | " 'MTRANS_Automobile', 'MTRANS_Bike', 'MTRANS_Motorbike',\n", |
||
| 299 | " 'MTRANS_Public_Transportation', 'MTRANS_Walking']\n", |
||
| 300 | " # 'BMI', 'Age^2',\n", |
||
| 301 | " # 'Age^3', 'BMI^2', 'Age * BMI', 'Age * BMI^2', 'Age^2 * BMI^2'] \n", |
||
| 302 | "#'Scaled_Age', 'Log_Age', 'Scaled_Weight', 'Log_Weight', 'Scaled_Height', 'Log_Height',\n", |
||
| 303 | "\n", |
||
| 304 | "X_train = train_df[features]\n", |
||
| 305 | "y_train = train_df[Target]\n", |
||
| 306 | "X_val = val_df[features]\n", |
||
| 307 | "y_val = val_df[Target]\n", |
||
| 308 | "X_test = test_df[features]\n", |
||
| 309 | "y_test = test_df[Target]\n", |
||
| 310 | "\n", |
||
| 311 | "#combine X_train and y_train as one dataframe\n", |
||
| 312 | "tr = pd.concat([X_train, y_train], axis=1)\n", |
||
| 313 | "te = pd.concat([X_test, y_test], axis =1)\n", |
||
| 314 | "va = pd.concat([X_val, y_val], axis = 1)" |
||
| 315 | ] |
||
| 316 | }, |
||
| 317 | { |
||
| 318 | "cell_type": "code", |
||
| 319 | "execution_count": 16, |
||
| 320 | "metadata": {}, |
||
| 321 | "outputs": [ |
||
| 322 | { |
||
| 323 | "data": { |
||
| 324 | "text/plain": [ |
||
| 325 | "{6: 0.19790605021773372,\n", |
||
| 326 | " 5: 0.1545446122486797,\n", |
||
| 327 | " 1: 0.15056054850365977,\n", |
||
| 328 | " 4: 0.13879366255906606,\n", |
||
| 329 | " 0: 0.12202353377188918,\n", |
||
| 330 | " 3: 0.12081904938385991,\n", |
||
| 331 | " 2: 0.11535254331511165}" |
||
| 332 | ] |
||
| 333 | }, |
||
| 334 | "execution_count": 16, |
||
| 335 | "metadata": {}, |
||
| 336 | "output_type": "execute_result" |
||
| 337 | } |
||
| 338 | ], |
||
| 339 | "source": [ |
||
| 340 | "y_train.value_counts()/len(y_train)\n", |
||
| 341 | "# to dict as weights\n", |
||
| 342 | "weights = y_train.value_counts(normalize=True).to_dict()\n", |
||
| 343 | "weights" |
||
| 344 | ] |
||
| 345 | }, |
||
| 346 | { |
||
| 347 | "cell_type": "code", |
||
| 348 | "execution_count": 10, |
||
| 349 | "metadata": {}, |
||
| 350 | "outputs": [ |
||
| 351 | { |
||
| 352 | "name": "stderr", |
||
| 353 | "output_type": "stream", |
||
| 354 | "text": [ |
||
| 355 | "No path specified. Models will be saved in: \"AutogluonModels/ag-20240426_034247\"\n", |
||
| 356 | "No presets specified! To achieve strong results with AutoGluon, it is recommended to use the available presets.\n", |
||
| 357 | "\tRecommended Presets (For more details refer to https://auto.gluon.ai/stable/tutorials/tabular/tabular-essentials.html#presets):\n", |
||
| 358 | "\tpresets='best_quality' : Maximize accuracy. Default time_limit=3600.\n", |
||
| 359 | "\tpresets='high_quality' : Strong accuracy with fast inference speed. Default time_limit=3600.\n", |
||
| 360 | "\tpresets='good_quality' : Good accuracy with very fast inference speed. Default time_limit=3600.\n", |
||
| 361 | "\tpresets='medium_quality' : Fast training time, ideal for initial prototyping.\n", |
||
| 362 | "Beginning AutoGluon training ...\n", |
||
| 363 | "AutoGluon will save models to \"AutogluonModels/ag-20240426_034247\"\n", |
||
| 364 | "=================== System Info ===================\n", |
||
| 365 | "AutoGluon Version: 1.1.0\n", |
||
| 366 | "Python Version: 3.10.13\n", |
||
| 367 | "Operating System: Darwin\n", |
||
| 368 | "Platform Machine: arm64\n", |
||
| 369 | "Platform Version: Darwin Kernel Version 23.0.0: Fri Sep 15 14:42:57 PDT 2023; root:xnu-10002.1.13~1/RELEASE_ARM64_T8112\n", |
||
| 370 | "CPU Count: 8\n", |
||
| 371 | "Memory Avail: 1.25 GB / 8.00 GB (15.7%)\n", |
||
| 372 | "Disk Space Avail: 24.83 GB / 228.27 GB (10.9%)\n", |
||
| 373 | "===================================================\n", |
||
| 374 | "Train Data Rows: 10793\n", |
||
| 375 | "Train Data Columns: 20\n", |
||
| 376 | "Label Column: NObeyesdad\n", |
||
| 377 | "AutoGluon infers your prediction problem is: 'multiclass' (because dtype of label-column == int, but few unique label-values observed).\n", |
||
| 378 | "\t7 unique label values: [0, 3, 1, 6, 4, 2, 5]\n", |
||
| 379 | "\tIf 'multiclass' is not the correct problem_type, please manually specify the problem_type parameter during predictor init (You may specify problem_type as one of: ['binary', 'multiclass', 'regression'])\n", |
||
| 380 | "Problem Type: multiclass\n", |
||
| 381 | "Preprocessing data ...\n", |
||
| 382 | "Train Data Class Count: 7\n", |
||
| 383 | "Using Feature Generators to preprocess the data ...\n", |
||
| 384 | "Fitting AutoMLPipelineFeatureGenerator...\n", |
||
| 385 | "\tAvailable Memory: 1285.60 MB\n", |
||
| 386 | "\tTrain Data (Original) Memory Usage: 1.65 MB (0.1% of available memory)\n", |
||
| 387 | "\tInferring data type of each feature based on column values. Set feature_metadata_in to manually specify special dtypes of the features.\n", |
||
| 388 | "\tStage 1 Generators:\n", |
||
| 389 | "\t\tFitting AsTypeFeatureGenerator...\n", |
||
| 390 | "\t\t\tNote: Converting 10 features to boolean dtype as they only contain 2 unique values.\n", |
||
| 391 | "\tStage 2 Generators:\n", |
||
| 392 | "\t\tFitting FillNaFeatureGenerator...\n", |
||
| 393 | "\tStage 3 Generators:\n", |
||
| 394 | "\t\tFitting IdentityFeatureGenerator...\n", |
||
| 395 | "\tStage 4 Generators:\n", |
||
| 396 | "\t\tFitting DropUniqueFeatureGenerator...\n", |
||
| 397 | "\tStage 5 Generators:\n", |
||
| 398 | "\t\tFitting DropDuplicatesFeatureGenerator...\n", |
||
| 399 | "\tTypes of features in original data (raw dtype, special dtypes):\n", |
||
| 400 | "\t\t('float', []) : 8 | ['Age', 'Height', 'Weight', 'FCVC', 'NCP', ...]\n", |
||
| 401 | "\t\t('int', []) : 12 | ['Gender', 'family_history_with_overweight', 'FAVC', 'CAEC', 'SMOKE', ...]\n", |
||
| 402 | "\tTypes of features in processed data (raw dtype, special dtypes):\n", |
||
| 403 | "\t\t('float', []) : 8 | ['Age', 'Height', 'Weight', 'FCVC', 'NCP', ...]\n", |
||
| 404 | "\t\t('int', []) : 2 | ['CAEC', 'CALC']\n", |
||
| 405 | "\t\t('int', ['bool']) : 10 | ['Gender', 'family_history_with_overweight', 'FAVC', 'SMOKE', 'SCC', ...]\n", |
||
| 406 | "\t0.1s = Fit runtime\n", |
||
| 407 | "\t20 features in original data used to generate 20 features in processed data.\n", |
||
| 408 | "\tTrain Data (Processed) Memory Usage: 0.93 MB (0.1% of available memory)\n", |
||
| 409 | "Data preprocessing and feature engineering runtime = 0.07s ...\n", |
||
| 410 | "AutoGluon will gauge predictive performance using evaluation metric: 'accuracy'\n", |
||
| 411 | "\tTo change this, specify the eval_metric parameter of Predictor()\n", |
||
| 412 | "Automatically generating train/validation split with holdout_frac=0.1, Train Rows: 9713, Val Rows: 1080\n", |
||
| 413 | "User-specified model hyperparameters to be fit:\n", |
||
| 414 | "{\n", |
||
| 415 | "\t'NN_TORCH': {},\n", |
||
| 416 | "\t'GBM': [{'extra_trees': True, 'ag_args': {'name_suffix': 'XT'}}, {}, 'GBMLarge'],\n", |
||
| 417 | "\t'CAT': {},\n", |
||
| 418 | "\t'XGB': {},\n", |
||
| 419 | "\t'FASTAI': {},\n", |
||
| 420 | "\t'RF': [{'criterion': 'gini', 'ag_args': {'name_suffix': 'Gini', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'entropy', 'ag_args': {'name_suffix': 'Entr', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'squared_error', 'ag_args': {'name_suffix': 'MSE', 'problem_types': ['regression', 'quantile']}}],\n", |
||
| 421 | "\t'XT': [{'criterion': 'gini', 'ag_args': {'name_suffix': 'Gini', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'entropy', 'ag_args': {'name_suffix': 'Entr', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'squared_error', 'ag_args': {'name_suffix': 'MSE', 'problem_types': ['regression', 'quantile']}}],\n", |
||
| 422 | "\t'KNN': [{'weights': 'uniform', 'ag_args': {'name_suffix': 'Unif'}}, {'weights': 'distance', 'ag_args': {'name_suffix': 'Dist'}}],\n", |
||
| 423 | "}\n", |
||
| 424 | "Fitting 13 L1 models ...\n", |
||
| 425 | "Fitting model: KNeighborsUnif ...\n", |
||
| 426 | "\t0.837\t = Validation score (accuracy)\n", |
||
| 427 | "\t0.04s\t = Training runtime\n", |
||
| 428 | "\t0.02s\t = Validation runtime\n", |
||
| 429 | "Fitting model: KNeighborsDist ...\n", |
||
| 430 | "\t0.8361\t = Validation score (accuracy)\n", |
||
| 431 | "\t0.02s\t = Training runtime\n", |
||
| 432 | "\t0.01s\t = Validation runtime\n", |
||
| 433 | "Fitting model: NeuralNetFastAI ...\n", |
||
| 434 | "\t0.8907\t = Validation score (accuracy)\n", |
||
| 435 | "\t6.55s\t = Training runtime\n", |
||
| 436 | "\t0.02s\t = Validation runtime\n", |
||
| 437 | "Fitting model: LightGBMXT ...\n", |
||
| 438 | "\t0.9019\t = Validation score (accuracy)\n", |
||
| 439 | "\t7.58s\t = Training runtime\n", |
||
| 440 | "\t0.06s\t = Validation runtime\n", |
||
| 441 | "Fitting model: LightGBM ...\n", |
||
| 442 | "\t0.9204\t = Validation score (accuracy)\n", |
||
| 443 | "\t9.07s\t = Training runtime\n", |
||
| 444 | "\t0.03s\t = Validation runtime\n", |
||
| 445 | "Fitting model: RandomForestGini ...\n", |
||
| 446 | "\t0.9037\t = Validation score (accuracy)\n", |
||
| 447 | "\t1.18s\t = Training runtime\n", |
||
| 448 | "\t0.06s\t = Validation runtime\n", |
||
| 449 | "Fitting model: RandomForestEntr ...\n", |
||
| 450 | "\t0.9083\t = Validation score (accuracy)\n", |
||
| 451 | "\t1.13s\t = Training runtime\n", |
||
| 452 | "\t0.05s\t = Validation runtime\n", |
||
| 453 | "Fitting model: CatBoost ...\n", |
||
| 454 | "\t0.913\t = Validation score (accuracy)\n", |
||
| 455 | "\t9.03s\t = Training runtime\n", |
||
| 456 | "\t0.01s\t = Validation runtime\n", |
||
| 457 | "Fitting model: ExtraTreesGini ...\n", |
||
| 458 | "\t0.8778\t = Validation score (accuracy)\n", |
||
| 459 | "\t0.98s\t = Training runtime\n", |
||
| 460 | "\t0.08s\t = Validation runtime\n", |
||
| 461 | "Fitting model: ExtraTreesEntr ...\n", |
||
| 462 | "\t0.875\t = Validation score (accuracy)\n", |
||
| 463 | "\t0.98s\t = Training runtime\n", |
||
| 464 | "\t0.07s\t = Validation runtime\n", |
||
| 465 | "Fitting model: XGBoost ...\n", |
||
| 466 | "\t0.9176\t = Validation score (accuracy)\n", |
||
| 467 | "\t6.6s\t = Training runtime\n", |
||
| 468 | "\t0.02s\t = Validation runtime\n", |
||
| 469 | "Fitting model: NeuralNetTorch ...\n", |
||
| 470 | "\tWarning: Exception caused NeuralNetTorch to fail during training... Skipping this model.\n", |
||
| 471 | "\t\tmodule 'torch.utils._pytree' has no attribute 'register_pytree_node'\n", |
||
| 472 | "Detailed Traceback:\n", |
||
| 473 | "Traceback (most recent call last):\n", |
||
| 474 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/core/trainer/abstract_trainer.py\", line 1904, in _train_and_save\n", |
||
| 475 | " model = self._train_single(X, y, model, X_val, y_val, total_resources=total_resources, **model_fit_kwargs)\n", |
||
| 476 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/core/trainer/abstract_trainer.py\", line 1844, in _train_single\n", |
||
| 477 | " model = model.fit(X=X, y=y, X_val=X_val, y_val=y_val, total_resources=total_resources, **model_fit_kwargs)\n", |
||
| 478 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/core/models/abstract/abstract_model.py\", line 855, in fit\n", |
||
| 479 | " out = self._fit(**kwargs)\n", |
||
| 480 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/tabular/models/tabular_nn/torch/tabular_nn_torch.py\", line 196, in _fit\n", |
||
| 481 | " self.optimizer = self._init_optimizer(**optimizer_kwargs)\n", |
||
| 482 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/tabular/models/tabular_nn/torch/tabular_nn_torch.py\", line 553, in _init_optimizer\n", |
||
| 483 | " optimizer = torch.optim.Adam(params=self.model.parameters(), lr=learning_rate, weight_decay=weight_decay)\n", |
||
| 484 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/optim/adam.py\", line 45, in __init__\n", |
||
| 485 | " super().__init__(params, defaults)\n", |
||
| 486 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/optim/optimizer.py\", line 266, in __init__\n", |
||
| 487 | " self.add_param_group(cast(dict, param_group))\n", |
||
| 488 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/_compile.py\", line 22, in inner\n", |
||
| 489 | " import torch._dynamo\n", |
||
| 490 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/_dynamo/__init__.py\", line 2, in <module>\n", |
||
| 491 | " from . import allowed_functions, convert_frame, eval_frame, resume_execution\n", |
||
| 492 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/_dynamo/allowed_functions.py\", line 26, in <module>\n", |
||
| 493 | " from . import config\n", |
||
| 494 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/_dynamo/config.py\", line 49, in <module>\n", |
||
| 495 | " torch.onnx.is_in_onnx_export: False,\n", |
||
| 496 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/__init__.py\", line 1831, in __getattr__\n", |
||
| 497 | " return importlib.import_module(f\".{name}\", __name__)\n", |
||
| 498 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/importlib/__init__.py\", line 126, in import_module\n", |
||
| 499 | " return _bootstrap._gcd_import(name[level:], package, level)\n", |
||
| 500 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/onnx/__init__.py\", line 46, in <module>\n", |
||
| 501 | " from ._internal.exporter import ( # usort:skip. needs to be last to avoid circular import\n", |
||
| 502 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/onnx/_internal/exporter.py\", line 42, in <module>\n", |
||
| 503 | " from torch.onnx._internal.fx import (\n", |
||
| 504 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/onnx/_internal/fx/__init__.py\", line 1, in <module>\n", |
||
| 505 | " from .patcher import ONNXTorchPatcher\n", |
||
| 506 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/onnx/_internal/fx/patcher.py\", line 11, in <module>\n", |
||
| 507 | " import transformers # type: ignore[import]\n", |
||
| 508 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/transformers/__init__.py\", line 26, in <module>\n", |
||
| 509 | " from . import dependency_versions_check\n", |
||
| 510 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/transformers/dependency_versions_check.py\", line 16, in <module>\n", |
||
| 511 | " from .utils.versions import require_version, require_version_core\n", |
||
| 512 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/transformers/utils/__init__.py\", line 33, in <module>\n", |
||
| 513 | " from .generic import (\n", |
||
| 514 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/transformers/utils/generic.py\", line 455, in <module>\n", |
||
| 515 | " _torch_pytree.register_pytree_node(\n", |
||
| 516 | "AttributeError: module 'torch.utils._pytree' has no attribute 'register_pytree_node'. Did you mean: '_register_pytree_node'?\n", |
||
| 517 | "Fitting model: LightGBMLarge ...\n", |
||
| 518 | "\t0.912\t = Validation score (accuracy)\n", |
||
| 519 | "\t75.08s\t = Training runtime\n", |
||
| 520 | "\t0.09s\t = Validation runtime\n", |
||
| 521 | "Fitting model: WeightedEnsemble_L2 ...\n", |
||
| 522 | "\tEnsemble Weights: {'LightGBM': 0.3, 'RandomForestEntr': 0.3, 'KNeighborsUnif': 0.2, 'NeuralNetFastAI': 0.1, 'XGBoost': 0.1}\n", |
||
| 523 | "\t0.9259\t = Validation score (accuracy)\n", |
||
| 524 | "\t0.13s\t = Training runtime\n", |
||
| 525 | "\t0.0s\t = Validation runtime\n", |
||
| 526 | "AutoGluon training complete, total runtime = 121.18s ... Best model: \"WeightedEnsemble_L2\"\n", |
||
| 527 | "TabularPredictor saved. To load, use: predictor = TabularPredictor.load(\"AutogluonModels/ag-20240426_034247\")\n" |
||
| 528 | ] |
||
| 529 | }, |
||
| 530 | { |
||
| 531 | "name": "stdout", |
||
| 532 | "output_type": "stream", |
||
| 533 | "text": [ |
||
| 534 | "Recall for class 0: 0.9462025316455697\n", |
||
| 535 | "Recall for class 1: 0.8957219251336899\n", |
||
| 536 | "Recall for class 2: 0.755223880597015\n", |
||
| 537 | "Recall for class 3: 0.8449848024316109\n", |
||
| 538 | "Recall for class 4: 0.8788598574821853\n", |
||
| 539 | "Recall for class 5: 0.9688995215311005\n", |
||
| 540 | "Recall for class 6: 0.9960474308300395\n" |
||
| 541 | ] |
||
| 542 | } |
||
| 543 | ], |
||
| 544 | "source": [ |
||
| 545 | "from autogluon.tabular import TabularDataset, TabularPredictor\n", |
||
| 546 | "from sklearn.metrics import precision_recall_fscore_support\n", |
||
| 547 | "import mlflow\n", |
||
| 548 | "\n", |
||
| 549 | "# Load your data into AutoGluon TabularDataset format\n", |
||
| 550 | "train_data = TabularDataset(X_train.join(y_train))\n", |
||
| 551 | "val_data = TabularDataset(X_val.join(y_val))\n", |
||
| 552 | "\n", |
||
| 553 | "# Define the label column\n", |
||
| 554 | "label_column = Target # Replace 'Target' with your actual label column name\n", |
||
| 555 | "\n", |
||
| 556 | "# Specify the task and run AutoGluon\n", |
||
| 557 | "predictor = TabularPredictor(label=label_column).fit(train_data=train_data)\n", |
||
| 558 | "\n", |
||
| 559 | "# Make predictions on the validation set\n", |
||
| 560 | "y_val_pred_autogluon = predictor.predict(val_data.drop(columns=[label_column]))\n", |
||
| 561 | "\n", |
||
| 562 | "# Evaluate performance\n", |
||
| 563 | "precision, recall, f1, support = precision_recall_fscore_support(y_val, y_val_pred_autogluon, average='weighted')\n", |
||
| 564 | "\n", |
||
| 565 | "# Log metrics and model using MLflow\n", |
||
| 566 | "with mlflow.start_run(run_name=\"AutoGluon_Without_Feature_Engineering\"):\n", |
||
| 567 | " # Log AutoGluon model\n", |
||
| 568 | " mlflow.sklearn.log_model(predictor, \"autogluon_model\")\n", |
||
| 569 | " \n", |
||
| 570 | " # Log metrics\n", |
||
| 571 | " mlflow.log_metric('accuracy', accuracy_score(y_val, y_val_pred_autogluon))\n", |
||
| 572 | " mlflow.log_metric('precision', precision)\n", |
||
| 573 | " mlflow.log_metric('recall', recall)\n", |
||
| 574 | " mlflow.log_metric('f1', f1)\n", |
||
| 575 | "\n", |
||
| 576 | " # Log recall per class\n", |
||
| 577 | " recall_per_class = recall_score(y_val, y_val_pred_autogluon, average=None)\n", |
||
| 578 | " for i, recall_class in enumerate(recall_per_class):\n", |
||
| 579 | " print(f\"Recall for class {i}: {recall_class}\")\n", |
||
| 580 | " mlflow.log_metric(f'recall_class_{i}', recall_class)\n", |
||
| 581 | "\n", |
||
| 582 | " mlflow.set_tag('experiments', 'Arham A.')\n", |
||
| 583 | " mlflow.set_tag('model_name', 'AutoGluon')\n", |
||
| 584 | " mlflow.set_tag('preprocessing', 'Yes')" |
||
| 585 | ] |
||
| 586 | }, |
||
| 587 | { |
||
| 588 | "cell_type": "code", |
||
| 589 | "execution_count": 28, |
||
| 590 | "metadata": {}, |
||
| 591 | "outputs": [ |
||
| 592 | { |
||
| 593 | "name": "stdout", |
||
| 594 | "output_type": "stream", |
||
| 595 | "text": [ |
||
| 596 | "[2024-04-26 05:38:37 -0400] [14055] [INFO] Starting gunicorn 21.2.0\n", |
||
| 597 | "[2024-04-26 05:38:37 -0400] [14055] [INFO] Listening at: http://127.0.0.1:5000 (14055)\n", |
||
| 598 | "[2024-04-26 05:38:37 -0400] [14055] [INFO] Using worker: sync\n", |
||
| 599 | "[2024-04-26 05:38:37 -0400] [14056] [INFO] Booting worker with pid: 14056\n", |
||
| 600 | "[2024-04-26 05:38:37 -0400] [14057] [INFO] Booting worker with pid: 14057\n", |
||
| 601 | "[2024-04-26 05:38:37 -0400] [14058] [INFO] Booting worker with pid: 14058\n", |
||
| 602 | "[2024-04-26 05:38:37 -0400] [14059] [INFO] Booting worker with pid: 14059\n", |
||
| 603 | "[2024-04-26 06:53:19 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:14056)\n", |
||
| 604 | "[2024-04-26 06:53:19 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:14057)\n", |
||
| 605 | "[2024-04-26 06:53:19 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:14058)\n", |
||
| 606 | "[2024-04-26 06:53:19 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:14059)\n", |
||
| 607 | "[2024-04-26 06:53:19 -0400] [14059] [INFO] Worker exiting (pid: 14059)\n", |
||
| 608 | "[2024-04-26 06:53:19 -0400] [14058] [INFO] Worker exiting (pid: 14058)\n", |
||
| 609 | "[2024-04-26 06:53:19 -0400] [14057] [INFO] Worker exiting (pid: 14057)\n", |
||
| 610 | "[2024-04-26 06:53:19 -0400] [14056] [INFO] Worker exiting (pid: 14056)\n", |
||
| 611 | "[2024-04-26 06:53:20 -0400] [14055] [ERROR] Worker (pid:14058) exited with code 1\n", |
||
| 612 | "[2024-04-26 06:53:20 -0400] [14055] [ERROR] Worker (pid:14058) exited with code 1.\n", |
||
| 613 | "[2024-04-26 06:53:20 -0400] [14055] [ERROR] Worker (pid:14059) exited with code 1\n", |
||
| 614 | "[2024-04-26 06:53:20 -0400] [14055] [ERROR] Worker (pid:14059) exited with code 1.\n", |
||
| 615 | "[2024-04-26 06:53:20 -0400] [14055] [ERROR] Worker (pid:14056) exited with code 1\n", |
||
| 616 | "[2024-04-26 06:53:20 -0400] [14055] [ERROR] Worker (pid:14056) exited with code 1.\n", |
||
| 617 | "[2024-04-26 06:53:20 -0400] [14055] [ERROR] Worker (pid:14057) exited with code 1\n", |
||
| 618 | "[2024-04-26 06:53:20 -0400] [14055] [ERROR] Worker (pid:14057) exited with code 1.\n", |
||
| 619 | "[2024-04-26 06:53:20 -0400] [16284] [INFO] Booting worker with pid: 16284\n", |
||
| 620 | "[2024-04-26 06:53:20 -0400] [16285] [INFO] Booting worker with pid: 16285\n", |
||
| 621 | "[2024-04-26 06:53:20 -0400] [16286] [INFO] Booting worker with pid: 16286\n", |
||
| 622 | "[2024-04-26 06:53:20 -0400] [16287] [INFO] Booting worker with pid: 16287\n", |
||
| 623 | "[2024-04-26 07:10:32 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16284)\n", |
||
| 624 | "[2024-04-26 07:10:32 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16285)\n", |
||
| 625 | "[2024-04-26 07:10:32 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16286)\n", |
||
| 626 | "[2024-04-26 07:10:32 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16287)\n", |
||
| 627 | "[2024-04-26 07:10:32 -0400] [16287] [INFO] Worker exiting (pid: 16287)\n", |
||
| 628 | "[2024-04-26 07:10:32 -0400] [16285] [INFO] Worker exiting (pid: 16285)\n", |
||
| 629 | "[2024-04-26 07:10:32 -0400] [16286] [INFO] Worker exiting (pid: 16286)\n", |
||
| 630 | "[2024-04-26 07:10:32 -0400] [16284] [INFO] Worker exiting (pid: 16284)\n", |
||
| 631 | "[2024-04-26 07:10:33 -0400] [14055] [ERROR] Worker (pid:16287) exited with code 1\n", |
||
| 632 | "[2024-04-26 07:10:33 -0400] [14055] [ERROR] Worker (pid:16287) exited with code 1.\n", |
||
| 633 | "[2024-04-26 07:10:33 -0400] [14055] [ERROR] Worker (pid:16284) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 634 | "[2024-04-26 07:10:33 -0400] [14055] [ERROR] Worker (pid:16285) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 635 | "[2024-04-26 07:10:33 -0400] [14055] [ERROR] Worker (pid:16286) exited with code 1\n", |
||
| 636 | "[2024-04-26 07:10:33 -0400] [14055] [ERROR] Worker (pid:16286) exited with code 1.\n", |
||
| 637 | "[2024-04-26 07:10:33 -0400] [16374] [INFO] Booting worker with pid: 16374\n", |
||
| 638 | "[2024-04-26 07:10:33 -0400] [16375] [INFO] Booting worker with pid: 16375\n", |
||
| 639 | "[2024-04-26 07:10:33 -0400] [16376] [INFO] Booting worker with pid: 16376\n", |
||
| 640 | "[2024-04-26 07:10:33 -0400] [16377] [INFO] Booting worker with pid: 16377\n", |
||
| 641 | "[2024-04-26 07:48:01 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16374)\n", |
||
| 642 | "[2024-04-26 07:48:01 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16375)\n", |
||
| 643 | "[2024-04-26 07:48:01 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16376)\n", |
||
| 644 | "[2024-04-26 07:48:01 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16377)\n", |
||
| 645 | "[2024-04-26 07:48:01 -0400] [16376] [INFO] Worker exiting (pid: 16376)\n", |
||
| 646 | "[2024-04-26 07:48:01 -0400] [16377] [INFO] Worker exiting (pid: 16377)\n", |
||
| 647 | "[2024-04-26 07:48:01 -0400] [16375] [INFO] Worker exiting (pid: 16375)\n", |
||
| 648 | "[2024-04-26 07:48:01 -0400] [16374] [INFO] Worker exiting (pid: 16374)\n", |
||
| 649 | "[2024-04-26 07:48:02 -0400] [14055] [ERROR] Worker (pid:16374) exited with code 1\n", |
||
| 650 | "[2024-04-26 07:48:02 -0400] [14055] [ERROR] Worker (pid:16374) exited with code 1.\n", |
||
| 651 | "[2024-04-26 07:48:02 -0400] [16404] [INFO] Booting worker with pid: 16404\n", |
||
| 652 | "[2024-04-26 07:48:02 -0400] [14055] [ERROR] Worker (pid:16375) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 653 | "[2024-04-26 07:48:02 -0400] [14055] [ERROR] Worker (pid:16376) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 654 | "[2024-04-26 07:48:02 -0400] [14055] [ERROR] Worker (pid:16377) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 655 | "[2024-04-26 07:48:02 -0400] [16405] [INFO] Booting worker with pid: 16405\n", |
||
| 656 | "[2024-04-26 07:48:02 -0400] [16406] [INFO] Booting worker with pid: 16406\n", |
||
| 657 | "[2024-04-26 07:48:02 -0400] [16407] [INFO] Booting worker with pid: 16407\n", |
||
| 658 | "[2024-04-26 07:54:51 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16404)\n", |
||
| 659 | "[2024-04-26 07:54:51 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16405)\n", |
||
| 660 | "[2024-04-26 07:54:51 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16406)\n", |
||
| 661 | "[2024-04-26 07:54:51 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16407)\n", |
||
| 662 | "[2024-04-26 07:54:51 -0400] [16406] [INFO] Worker exiting (pid: 16406)\n", |
||
| 663 | "[2024-04-26 07:54:51 -0400] [16405] [INFO] Worker exiting (pid: 16405)\n", |
||
| 664 | "[2024-04-26 07:54:51 -0400] [16404] [INFO] Worker exiting (pid: 16404)\n", |
||
| 665 | "[2024-04-26 07:54:51 -0400] [16407] [INFO] Worker exiting (pid: 16407)\n", |
||
| 666 | "[2024-04-26 07:54:52 -0400] [14055] [ERROR] Worker (pid:16404) exited with code 1\n", |
||
| 667 | "[2024-04-26 07:54:52 -0400] [14055] [ERROR] Worker (pid:16404) exited with code 1.\n", |
||
| 668 | "[2024-04-26 07:54:52 -0400] [14055] [ERROR] Worker (pid:16407) exited with code 1\n", |
||
| 669 | "[2024-04-26 07:54:52 -0400] [14055] [ERROR] Worker (pid:16407) exited with code 1.\n", |
||
| 670 | "[2024-04-26 07:54:52 -0400] [14055] [ERROR] Worker (pid:16406) exited with code 1\n", |
||
| 671 | "[2024-04-26 07:54:52 -0400] [14055] [ERROR] Worker (pid:16406) exited with code 1.\n", |
||
| 672 | "[2024-04-26 07:54:52 -0400] [16450] [INFO] Booting worker with pid: 16450\n", |
||
| 673 | "[2024-04-26 07:54:52 -0400] [14055] [ERROR] Worker (pid:16405) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 674 | "[2024-04-26 07:54:52 -0400] [16451] [INFO] Booting worker with pid: 16451\n", |
||
| 675 | "[2024-04-26 07:54:52 -0400] [16452] [INFO] Booting worker with pid: 16452\n", |
||
| 676 | "[2024-04-26 07:54:52 -0400] [16453] [INFO] Booting worker with pid: 16453\n", |
||
| 677 | "[2024-04-26 08:04:43 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16450)\n", |
||
| 678 | "[2024-04-26 08:04:43 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16451)\n", |
||
| 679 | "[2024-04-26 08:04:43 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16452)\n", |
||
| 680 | "[2024-04-26 08:04:43 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16453)\n", |
||
| 681 | "[2024-04-26 08:04:43 -0400] [16450] [INFO] Worker exiting (pid: 16450)\n", |
||
| 682 | "[2024-04-26 08:04:43 -0400] [16451] [INFO] Worker exiting (pid: 16451)\n", |
||
| 683 | "[2024-04-26 08:04:43 -0400] [16453] [INFO] Worker exiting (pid: 16453)\n", |
||
| 684 | "[2024-04-26 08:04:43 -0400] [16452] [INFO] Worker exiting (pid: 16452)\n", |
||
| 685 | "[2024-04-26 08:04:44 -0400] [14055] [ERROR] Worker (pid:16453) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 686 | "[2024-04-26 08:04:44 -0400] [16510] [INFO] Booting worker with pid: 16510\n", |
||
| 687 | "[2024-04-26 08:04:44 -0400] [14055] [ERROR] Worker (pid:16452) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 688 | "[2024-04-26 08:04:44 -0400] [14055] [ERROR] Worker (pid:16451) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 689 | "[2024-04-26 08:04:44 -0400] [14055] [ERROR] Worker (pid:16450) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 690 | "[2024-04-26 08:04:44 -0400] [16511] [INFO] Booting worker with pid: 16511\n", |
||
| 691 | "[2024-04-26 08:04:44 -0400] [16512] [INFO] Booting worker with pid: 16512\n", |
||
| 692 | "[2024-04-26 08:04:44 -0400] [16514] [INFO] Booting worker with pid: 16514\n", |
||
| 693 | "[2024-04-26 08:23:29 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16510)\n", |
||
| 694 | "[2024-04-26 08:23:29 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16511)\n", |
||
| 695 | "[2024-04-26 08:23:29 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16512)\n", |
||
| 696 | "[2024-04-26 08:23:29 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16514)\n", |
||
| 697 | "[2024-04-26 08:23:29 -0400] [16514] [INFO] Worker exiting (pid: 16514)\n", |
||
| 698 | "[2024-04-26 08:23:29 -0400] [16511] [INFO] Worker exiting (pid: 16511)\n", |
||
| 699 | "[2024-04-26 08:23:29 -0400] [16512] [INFO] Worker exiting (pid: 16512)\n", |
||
| 700 | "[2024-04-26 08:23:29 -0400] [16510] [INFO] Worker exiting (pid: 16510)\n", |
||
| 701 | "[2024-04-26 08:23:29 -0400] [14055] [ERROR] Worker (pid:16514) exited with code 1\n", |
||
| 702 | "[2024-04-26 08:23:29 -0400] [14055] [ERROR] Worker (pid:16514) exited with code 1.\n", |
||
| 703 | "[2024-04-26 08:23:29 -0400] [14055] [ERROR] Worker (pid:16512) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 704 | "[2024-04-26 08:23:29 -0400] [14055] [ERROR] Worker (pid:16511) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 705 | "[2024-04-26 08:23:29 -0400] [14055] [ERROR] Worker (pid:16510) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 706 | "[2024-04-26 08:23:29 -0400] [16747] [INFO] Booting worker with pid: 16747\n", |
||
| 707 | "[2024-04-26 08:23:29 -0400] [16748] [INFO] Booting worker with pid: 16748\n", |
||
| 708 | "[2024-04-26 08:23:29 -0400] [16749] [INFO] Booting worker with pid: 16749\n", |
||
| 709 | "[2024-04-26 08:23:29 -0400] [16750] [INFO] Booting worker with pid: 16750\n", |
||
| 710 | "[2024-04-26 08:31:37 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16747)\n", |
||
| 711 | "[2024-04-26 08:31:37 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16748)\n", |
||
| 712 | "[2024-04-26 08:31:37 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16749)\n", |
||
| 713 | "[2024-04-26 08:31:37 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16750)\n", |
||
| 714 | "[2024-04-26 08:31:37 -0400] [16749] [INFO] Worker exiting (pid: 16749)\n", |
||
| 715 | "[2024-04-26 08:31:37 -0400] [16750] [INFO] Worker exiting (pid: 16750)\n", |
||
| 716 | "[2024-04-26 08:31:37 -0400] [16747] [INFO] Worker exiting (pid: 16747)\n", |
||
| 717 | "[2024-04-26 08:31:37 -0400] [16748] [INFO] Worker exiting (pid: 16748)\n", |
||
| 718 | "[2024-04-26 08:31:37 -0400] [14055] [ERROR] Worker (pid:16750) exited with code 1\n", |
||
| 719 | "[2024-04-26 08:31:37 -0400] [14055] [ERROR] Worker (pid:16750) exited with code 1.\n", |
||
| 720 | "[2024-04-26 08:31:37 -0400] [16768] [INFO] Booting worker with pid: 16768\n", |
||
| 721 | "[2024-04-26 08:31:37 -0400] [14055] [ERROR] Worker (pid:16748) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 722 | "[2024-04-26 08:31:37 -0400] [14055] [ERROR] Worker (pid:16747) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 723 | "[2024-04-26 08:31:37 -0400] [14055] [ERROR] Worker (pid:16749) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 724 | "[2024-04-26 08:31:37 -0400] [16769] [INFO] Booting worker with pid: 16769\n", |
||
| 725 | "[2024-04-26 08:31:37 -0400] [16771] [INFO] Booting worker with pid: 16771\n", |
||
| 726 | "[2024-04-26 08:31:37 -0400] [16772] [INFO] Booting worker with pid: 16772\n", |
||
| 727 | "[2024-04-26 08:37:33 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16768)\n", |
||
| 728 | "[2024-04-26 08:37:33 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16769)\n", |
||
| 729 | "[2024-04-26 08:37:33 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16771)\n", |
||
| 730 | "[2024-04-26 08:37:33 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16772)\n", |
||
| 731 | "[2024-04-26 08:37:33 -0400] [16769] [INFO] Worker exiting (pid: 16769)\n", |
||
| 732 | "[2024-04-26 08:37:33 -0400] [16768] [INFO] Worker exiting (pid: 16768)\n", |
||
| 733 | "[2024-04-26 08:37:33 -0400] [16771] [INFO] Worker exiting (pid: 16771)\n", |
||
| 734 | "[2024-04-26 08:37:33 -0400] [16772] [INFO] Worker exiting (pid: 16772)\n", |
||
| 735 | "[2024-04-26 08:37:33 -0400] [14055] [ERROR] Worker (pid:16772) exited with code 1\n", |
||
| 736 | "[2024-04-26 08:37:33 -0400] [14055] [ERROR] Worker (pid:16772) exited with code 1.\n", |
||
| 737 | "[2024-04-26 08:37:33 -0400] [14055] [ERROR] Worker (pid:16771) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 738 | "[2024-04-26 08:37:33 -0400] [14055] [ERROR] Worker (pid:16768) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 739 | "[2024-04-26 08:37:33 -0400] [14055] [ERROR] Worker (pid:16769) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 740 | "[2024-04-26 08:37:33 -0400] [16901] [INFO] Booting worker with pid: 16901\n", |
||
| 741 | "[2024-04-26 08:37:33 -0400] [16902] [INFO] Booting worker with pid: 16902\n", |
||
| 742 | "[2024-04-26 08:37:33 -0400] [16903] [INFO] Booting worker with pid: 16903\n", |
||
| 743 | "[2024-04-26 08:37:33 -0400] [16904] [INFO] Booting worker with pid: 16904\n", |
||
| 744 | "[2024-04-26 08:38:21 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16901)\n", |
||
| 745 | "[2024-04-26 08:38:21 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16902)\n", |
||
| 746 | "[2024-04-26 08:38:21 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16903)\n", |
||
| 747 | "[2024-04-26 08:38:21 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16904)\n", |
||
| 748 | "[2024-04-26 08:38:21 -0400] [16901] [INFO] Worker exiting (pid: 16901)\n", |
||
| 749 | "[2024-04-26 08:38:21 -0400] [16902] [INFO] Worker exiting (pid: 16902)\n", |
||
| 750 | "[2024-04-26 08:38:21 -0400] [16903] [INFO] Worker exiting (pid: 16903)\n", |
||
| 751 | "[2024-04-26 08:38:21 -0400] [16904] [INFO] Worker exiting (pid: 16904)\n", |
||
| 752 | "[2024-04-26 08:38:21 -0400] [14055] [ERROR] Worker (pid:16904) exited with code 1\n", |
||
| 753 | "[2024-04-26 08:38:21 -0400] [14055] [ERROR] Worker (pid:16904) exited with code 1.\n", |
||
| 754 | "[2024-04-26 08:38:21 -0400] [14055] [ERROR] Worker (pid:16902) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 755 | "[2024-04-26 08:38:21 -0400] [16965] [INFO] Booting worker with pid: 16965\n", |
||
| 756 | "[2024-04-26 08:38:21 -0400] [14055] [ERROR] Worker (pid:16901) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 757 | "[2024-04-26 08:38:21 -0400] [14055] [ERROR] Worker (pid:16903) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 758 | "[2024-04-26 08:38:21 -0400] [16966] [INFO] Booting worker with pid: 16966\n", |
||
| 759 | "[2024-04-26 08:38:21 -0400] [16967] [INFO] Booting worker with pid: 16967\n", |
||
| 760 | "[2024-04-26 08:38:21 -0400] [16968] [INFO] Booting worker with pid: 16968\n", |
||
| 761 | "[2024-04-26 08:39:34 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16965)\n", |
||
| 762 | "[2024-04-26 08:39:34 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16966)\n", |
||
| 763 | "[2024-04-26 08:39:34 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16967)\n", |
||
| 764 | "[2024-04-26 08:39:34 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:16968)\n", |
||
| 765 | "[2024-04-26 08:39:34 -0400] [16965] [INFO] Worker exiting (pid: 16965)\n", |
||
| 766 | "[2024-04-26 08:39:34 -0400] [16966] [INFO] Worker exiting (pid: 16966)\n", |
||
| 767 | "[2024-04-26 08:39:34 -0400] [16967] [INFO] Worker exiting (pid: 16967)\n", |
||
| 768 | "[2024-04-26 08:39:34 -0400] [16968] [INFO] Worker exiting (pid: 16968)\n", |
||
| 769 | "[2024-04-26 08:39:34 -0400] [14055] [ERROR] Worker (pid:16965) exited with code 1\n", |
||
| 770 | "[2024-04-26 08:39:34 -0400] [14055] [ERROR] Worker (pid:16965) exited with code 1.\n", |
||
| 771 | "[2024-04-26 08:39:34 -0400] [17085] [INFO] Booting worker with pid: 17085\n", |
||
| 772 | "[2024-04-26 08:39:34 -0400] [14055] [ERROR] Worker (pid:16966) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 773 | "[2024-04-26 08:39:34 -0400] [14055] [ERROR] Worker (pid:16967) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 774 | "[2024-04-26 08:39:34 -0400] [14055] [ERROR] Worker (pid:16968) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 775 | "[2024-04-26 08:39:34 -0400] [17086] [INFO] Booting worker with pid: 17086\n", |
||
| 776 | "[2024-04-26 08:39:34 -0400] [17087] [INFO] Booting worker with pid: 17087\n", |
||
| 777 | "[2024-04-26 08:39:34 -0400] [17088] [INFO] Booting worker with pid: 17088\n", |
||
| 778 | "[2024-04-26 08:40:44 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:17085)\n", |
||
| 779 | "[2024-04-26 08:40:44 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:17086)\n", |
||
| 780 | "[2024-04-26 08:40:44 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:17087)\n", |
||
| 781 | "[2024-04-26 08:40:44 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:17088)\n", |
||
| 782 | "[2024-04-26 08:40:44 -0400] [17086] [INFO] Worker exiting (pid: 17086)\n", |
||
| 783 | "[2024-04-26 08:40:44 -0400] [17087] [INFO] Worker exiting (pid: 17087)\n", |
||
| 784 | "[2024-04-26 08:40:44 -0400] [17085] [INFO] Worker exiting (pid: 17085)\n", |
||
| 785 | "[2024-04-26 08:40:44 -0400] [17088] [INFO] Worker exiting (pid: 17088)\n", |
||
| 786 | "[2024-04-26 08:40:44 -0400] [14055] [ERROR] Worker (pid:17086) exited with code 1\n", |
||
| 787 | "[2024-04-26 08:40:44 -0400] [14055] [ERROR] Worker (pid:17086) exited with code 1.\n", |
||
| 788 | "[2024-04-26 08:40:44 -0400] [17139] [INFO] Booting worker with pid: 17139\n", |
||
| 789 | "[2024-04-26 08:40:44 -0400] [14055] [ERROR] Worker (pid:17088) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 790 | "[2024-04-26 08:40:44 -0400] [14055] [ERROR] Worker (pid:17085) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 791 | "[2024-04-26 08:40:44 -0400] [14055] [ERROR] Worker (pid:17087) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 792 | "[2024-04-26 08:40:44 -0400] [17140] [INFO] Booting worker with pid: 17140\n", |
||
| 793 | "[2024-04-26 08:40:44 -0400] [17141] [INFO] Booting worker with pid: 17141\n", |
||
| 794 | "[2024-04-26 08:40:44 -0400] [17142] [INFO] Booting worker with pid: 17142\n", |
||
| 795 | "[2024-04-26 08:41:32 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:17139)\n", |
||
| 796 | "[2024-04-26 08:41:32 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:17140)\n", |
||
| 797 | "[2024-04-26 08:41:32 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:17141)\n", |
||
| 798 | "[2024-04-26 08:41:32 -0400] [14055] [CRITICAL] WORKER TIMEOUT (pid:17142)\n", |
||
| 799 | "[2024-04-26 08:41:32 -0400] [17142] [INFO] Worker exiting (pid: 17142)\n", |
||
| 800 | "[2024-04-26 08:41:32 -0400] [17140] [INFO] Worker exiting (pid: 17140)\n", |
||
| 801 | "[2024-04-26 08:41:32 -0400] [17141] [INFO] Worker exiting (pid: 17141)\n", |
||
| 802 | "[2024-04-26 08:41:32 -0400] [17139] [INFO] Worker exiting (pid: 17139)\n", |
||
| 803 | "[2024-04-26 08:41:32 -0400] [14055] [ERROR] Worker (pid:17140) exited with code 1\n", |
||
| 804 | "[2024-04-26 08:41:32 -0400] [14055] [ERROR] Worker (pid:17140) exited with code 1.\n", |
||
| 805 | "[2024-04-26 08:41:32 -0400] [14055] [ERROR] Worker (pid:17139) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 806 | "[2024-04-26 08:41:32 -0400] [14055] [ERROR] Worker (pid:17141) exited with code 1\n", |
||
| 807 | "[2024-04-26 08:41:32 -0400] [14055] [ERROR] Worker (pid:17141) exited with code 1.\n", |
||
| 808 | "[2024-04-26 08:41:32 -0400] [14055] [ERROR] Worker (pid:17142) was sent SIGKILL! Perhaps out of memory?\n", |
||
| 809 | "[2024-04-26 08:41:32 -0400] [17204] [INFO] Booting worker with pid: 17204\n", |
||
| 810 | "[2024-04-26 08:41:32 -0400] [17205] [INFO] Booting worker with pid: 17205\n", |
||
| 811 | "[2024-04-26 08:41:33 -0400] [17206] [INFO] Booting worker with pid: 17206\n", |
||
| 812 | "[2024-04-26 08:41:33 -0400] [17207] [INFO] Booting worker with pid: 17207\n", |
||
| 813 | "^C\n", |
||
| 814 | "[2024-04-26 08:55:21 -0400] [14055] [INFO] Handling signal: int\n", |
||
| 815 | "[2024-04-26 08:55:21 -0400] [17207] [INFO] Worker exiting (pid: 17207)\n", |
||
| 816 | "[2024-04-26 08:55:21 -0400] [17205] [INFO] Worker exiting (pid: 17205)\n", |
||
| 817 | "[2024-04-26 08:55:21 -0400] [17206] [INFO] Worker exiting (pid: 17206)\n", |
||
| 818 | "[2024-04-26 08:55:21 -0400] [17204] [INFO] Worker exiting (pid: 17204)\n" |
||
| 819 | ] |
||
| 820 | } |
||
| 821 | ], |
||
| 822 | "source": [ |
||
| 823 | "!mlflow ui --backend-store-uri \"sqlite:////Users/arham/Downloads/Projects/03-Experiments/new_mlflow.db\"" |
||
| 824 | ] |
||
| 825 | }, |
||
| 826 | { |
||
| 827 | "cell_type": "markdown", |
||
| 828 | "metadata": {}, |
||
| 829 | "source": [ |
||
| 830 | "## Saving probabilities for stacked model later" |
||
| 831 | ] |
||
| 832 | }, |
||
| 833 | { |
||
| 834 | "cell_type": "code", |
||
| 835 | "execution_count": 8, |
||
| 836 | "metadata": {}, |
||
| 837 | "outputs": [], |
||
| 838 | "source": [ |
||
| 839 | "# Make predictions on train, validation, and test data\n", |
||
| 840 | "y_pred_train = predictor.predict(tr)\n", |
||
| 841 | "y_pred_va = predictor.predict(va)\n", |
||
| 842 | "y_pred_test = predictor.predict(te)\n", |
||
| 843 | "\n", |
||
| 844 | "# Get prediction probabilities for each class\n", |
||
| 845 | "y_probabilities_train = predictor.predict_proba(tr)\n", |
||
| 846 | "y_probabilities_va = predictor.predict_proba(va)\n", |
||
| 847 | "y_probabilities_test = predictor.predict_proba(te)\n", |
||
| 848 | "\n", |
||
| 849 | "# add to tr, te, va\n", |
||
| 850 | "test = pd.concat([te, y_probabilities_test.iloc[:, -7:]], axis=1)\n", |
||
| 851 | "train = pd.concat([tr, y_probabilities_train.iloc[:, -7:]], axis=1)\n", |
||
| 852 | "val = pd.concat([va, y_probabilities_va.iloc[:, -7:]], axis=1)\n" |
||
| 853 | ] |
||
| 854 | }, |
||
| 855 | { |
||
| 856 | "cell_type": "code", |
||
| 857 | "execution_count": 9, |
||
| 858 | "metadata": {}, |
||
| 859 | "outputs": [ |
||
| 860 | { |
||
| 861 | "data": { |
||
| 862 | "text/html": [ |
||
| 863 | "<div>\n", |
||
| 864 | "<style scoped>\n", |
||
| 865 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 866 | " vertical-align: middle;\n", |
||
| 867 | " }\n", |
||
| 868 | "\n", |
||
| 869 | " .dataframe tbody tr th {\n", |
||
| 870 | " vertical-align: top;\n", |
||
| 871 | " }\n", |
||
| 872 | "\n", |
||
| 873 | " .dataframe thead th {\n", |
||
| 874 | " text-align: right;\n", |
||
| 875 | " }\n", |
||
| 876 | "</style>\n", |
||
| 877 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 878 | " <thead>\n", |
||
| 879 | " <tr style=\"text-align: right;\">\n", |
||
| 880 | " <th></th>\n", |
||
| 881 | " <th>Gender</th>\n", |
||
| 882 | " <th>Age</th>\n", |
||
| 883 | " <th>Height</th>\n", |
||
| 884 | " <th>Weight</th>\n", |
||
| 885 | " <th>family_history_with_overweight</th>\n", |
||
| 886 | " <th>FAVC</th>\n", |
||
| 887 | " <th>FCVC</th>\n", |
||
| 888 | " <th>NCP</th>\n", |
||
| 889 | " <th>CAEC</th>\n", |
||
| 890 | " <th>SMOKE</th>\n", |
||
| 891 | " <th>...</th>\n", |
||
| 892 | " <th>Age * BMI^2</th>\n", |
||
| 893 | " <th>Age^2 * BMI^2</th>\n", |
||
| 894 | " <th>NObeyesdad</th>\n", |
||
| 895 | " <th>0</th>\n", |
||
| 896 | " <th>1</th>\n", |
||
| 897 | " <th>2</th>\n", |
||
| 898 | " <th>3</th>\n", |
||
| 899 | " <th>4</th>\n", |
||
| 900 | " <th>5</th>\n", |
||
| 901 | " <th>6</th>\n", |
||
| 902 | " </tr>\n", |
||
| 903 | " </thead>\n", |
||
| 904 | " <tbody>\n", |
||
| 905 | " <tr>\n", |
||
| 906 | " <th>0</th>\n", |
||
| 907 | " <td>1</td>\n", |
||
| 908 | " <td>21.000000</td>\n", |
||
| 909 | " <td>1.550000</td>\n", |
||
| 910 | " <td>51.000000</td>\n", |
||
| 911 | " <td>0</td>\n", |
||
| 912 | " <td>1</td>\n", |
||
| 913 | " <td>3.000000</td>\n", |
||
| 914 | " <td>1.0</td>\n", |
||
| 915 | " <td>2</td>\n", |
||
| 916 | " <td>0</td>\n", |
||
| 917 | " <td>...</td>\n", |
||
| 918 | " <td>445.785640</td>\n", |
||
| 919 | " <td>450.623213</td>\n", |
||
| 920 | " <td>0</td>\n", |
||
| 921 | " <td>0.797175</td>\n", |
||
| 922 | " <td>0.196596</td>\n", |
||
| 923 | " <td>0.005617</td>\n", |
||
| 924 | " <td>0.000520</td>\n", |
||
| 925 | " <td>0.000032</td>\n", |
||
| 926 | " <td>0.000019</td>\n", |
||
| 927 | " <td>0.000040</td>\n", |
||
| 928 | " </tr>\n", |
||
| 929 | " <tr>\n", |
||
| 930 | " <th>1</th>\n", |
||
| 931 | " <td>0</td>\n", |
||
| 932 | " <td>20.000000</td>\n", |
||
| 933 | " <td>1.700000</td>\n", |
||
| 934 | " <td>80.000000</td>\n", |
||
| 935 | " <td>1</td>\n", |
||
| 936 | " <td>1</td>\n", |
||
| 937 | " <td>2.000000</td>\n", |
||
| 938 | " <td>3.0</td>\n", |
||
| 939 | " <td>1</td>\n", |
||
| 940 | " <td>0</td>\n", |
||
| 941 | " <td>...</td>\n", |
||
| 942 | " <td>553.633218</td>\n", |
||
| 943 | " <td>766.274350</td>\n", |
||
| 944 | " <td>3</td>\n", |
||
| 945 | " <td>0.000041</td>\n", |
||
| 946 | " <td>0.001926</td>\n", |
||
| 947 | " <td>0.047782</td>\n", |
||
| 948 | " <td>0.948167</td>\n", |
||
| 949 | " <td>0.002041</td>\n", |
||
| 950 | " <td>0.000018</td>\n", |
||
| 951 | " <td>0.000025</td>\n", |
||
| 952 | " </tr>\n", |
||
| 953 | " <tr>\n", |
||
| 954 | " <th>2</th>\n", |
||
| 955 | " <td>1</td>\n", |
||
| 956 | " <td>18.000000</td>\n", |
||
| 957 | " <td>1.600000</td>\n", |
||
| 958 | " <td>60.000000</td>\n", |
||
| 959 | " <td>1</td>\n", |
||
| 960 | " <td>1</td>\n", |
||
| 961 | " <td>2.000000</td>\n", |
||
| 962 | " <td>3.0</td>\n", |
||
| 963 | " <td>1</td>\n", |
||
| 964 | " <td>0</td>\n", |
||
| 965 | " <td>...</td>\n", |
||
| 966 | " <td>421.875000</td>\n", |
||
| 967 | " <td>549.316406</td>\n", |
||
| 968 | " <td>1</td>\n", |
||
| 969 | " <td>0.011628</td>\n", |
||
| 970 | " <td>0.953612</td>\n", |
||
| 971 | " <td>0.033047</td>\n", |
||
| 972 | " <td>0.001538</td>\n", |
||
| 973 | " <td>0.000150</td>\n", |
||
| 974 | " <td>0.000005</td>\n", |
||
| 975 | " <td>0.000020</td>\n", |
||
| 976 | " </tr>\n", |
||
| 977 | " <tr>\n", |
||
| 978 | " <th>3</th>\n", |
||
| 979 | " <td>1</td>\n", |
||
| 980 | " <td>26.000000</td>\n", |
||
| 981 | " <td>1.632983</td>\n", |
||
| 982 | " <td>111.720238</td>\n", |
||
| 983 | " <td>1</td>\n", |
||
| 984 | " <td>1</td>\n", |
||
| 985 | " <td>3.000000</td>\n", |
||
| 986 | " <td>3.0</td>\n", |
||
| 987 | " <td>1</td>\n", |
||
| 988 | " <td>0</td>\n", |
||
| 989 | " <td>...</td>\n", |
||
| 990 | " <td>1089.285877</td>\n", |
||
| 991 | " <td>1755.242193</td>\n", |
||
| 992 | " <td>6</td>\n", |
||
| 993 | " <td>0.000001</td>\n", |
||
| 994 | " <td>0.000002</td>\n", |
||
| 995 | " <td>0.000008</td>\n", |
||
| 996 | " <td>0.000018</td>\n", |
||
| 997 | " <td>0.000172</td>\n", |
||
| 998 | " <td>0.000040</td>\n", |
||
| 999 | " <td>0.999759</td>\n", |
||
| 1000 | " </tr>\n", |
||
| 1001 | " <tr>\n", |
||
| 1002 | " <th>4</th>\n", |
||
| 1003 | " <td>1</td>\n", |
||
| 1004 | " <td>21.682636</td>\n", |
||
| 1005 | " <td>1.748524</td>\n", |
||
| 1006 | " <td>133.845064</td>\n", |
||
| 1007 | " <td>1</td>\n", |
||
| 1008 | " <td>1</td>\n", |
||
| 1009 | " <td>3.000000</td>\n", |
||
| 1010 | " <td>3.0</td>\n", |
||
| 1011 | " <td>1</td>\n", |
||
| 1012 | " <td>0</td>\n", |
||
| 1013 | " <td>...</td>\n", |
||
| 1014 | " <td>949.229536</td>\n", |
||
| 1015 | " <td>1916.541944</td>\n", |
||
| 1016 | " <td>6</td>\n", |
||
| 1017 | " <td>0.000001</td>\n", |
||
| 1018 | " <td>0.000001</td>\n", |
||
| 1019 | " <td>0.000004</td>\n", |
||
| 1020 | " <td>0.000012</td>\n", |
||
| 1021 | " <td>0.000092</td>\n", |
||
| 1022 | " <td>0.000058</td>\n", |
||
| 1023 | " <td>0.999831</td>\n", |
||
| 1024 | " </tr>\n", |
||
| 1025 | " <tr>\n", |
||
| 1026 | " <th>...</th>\n", |
||
| 1027 | " <td>...</td>\n", |
||
| 1028 | " <td>...</td>\n", |
||
| 1029 | " <td>...</td>\n", |
||
| 1030 | " <td>...</td>\n", |
||
| 1031 | " <td>...</td>\n", |
||
| 1032 | " <td>...</td>\n", |
||
| 1033 | " <td>...</td>\n", |
||
| 1034 | " <td>...</td>\n", |
||
| 1035 | " <td>...</td>\n", |
||
| 1036 | " <td>...</td>\n", |
||
| 1037 | " <td>...</td>\n", |
||
| 1038 | " <td>...</td>\n", |
||
| 1039 | " <td>...</td>\n", |
||
| 1040 | " <td>...</td>\n", |
||
| 1041 | " <td>...</td>\n", |
||
| 1042 | " <td>...</td>\n", |
||
| 1043 | " <td>...</td>\n", |
||
| 1044 | " <td>...</td>\n", |
||
| 1045 | " <td>...</td>\n", |
||
| 1046 | " <td>...</td>\n", |
||
| 1047 | " <td>...</td>\n", |
||
| 1048 | " </tr>\n", |
||
| 1049 | " <tr>\n", |
||
| 1050 | " <th>10788</th>\n", |
||
| 1051 | " <td>0</td>\n", |
||
| 1052 | " <td>18.000000</td>\n", |
||
| 1053 | " <td>1.780000</td>\n", |
||
| 1054 | " <td>108.000000</td>\n", |
||
| 1055 | " <td>1</td>\n", |
||
| 1056 | " <td>1</td>\n", |
||
| 1057 | " <td>2.000000</td>\n", |
||
| 1058 | " <td>3.0</td>\n", |
||
| 1059 | " <td>1</td>\n", |
||
| 1060 | " <td>0</td>\n", |
||
| 1061 | " <td>...</td>\n", |
||
| 1062 | " <td>613.558894</td>\n", |
||
| 1063 | " <td>1161.896656</td>\n", |
||
| 1064 | " <td>4</td>\n", |
||
| 1065 | " <td>0.000007</td>\n", |
||
| 1066 | " <td>0.000014</td>\n", |
||
| 1067 | " <td>0.000035</td>\n", |
||
| 1068 | " <td>0.000287</td>\n", |
||
| 1069 | " <td>0.998704</td>\n", |
||
| 1070 | " <td>0.000949</td>\n", |
||
| 1071 | " <td>0.000005</td>\n", |
||
| 1072 | " </tr>\n", |
||
| 1073 | " <tr>\n", |
||
| 1074 | " <th>10789</th>\n", |
||
| 1075 | " <td>1</td>\n", |
||
| 1076 | " <td>26.000000</td>\n", |
||
| 1077 | " <td>1.641601</td>\n", |
||
| 1078 | " <td>111.830924</td>\n", |
||
| 1079 | " <td>1</td>\n", |
||
| 1080 | " <td>1</td>\n", |
||
| 1081 | " <td>3.000000</td>\n", |
||
| 1082 | " <td>3.0</td>\n", |
||
| 1083 | " <td>1</td>\n", |
||
| 1084 | " <td>0</td>\n", |
||
| 1085 | " <td>...</td>\n", |
||
| 1086 | " <td>1078.946835</td>\n", |
||
| 1087 | " <td>1722.080284</td>\n", |
||
| 1088 | " <td>6</td>\n", |
||
| 1089 | " <td>0.000001</td>\n", |
||
| 1090 | " <td>0.000002</td>\n", |
||
| 1091 | " <td>0.000007</td>\n", |
||
| 1092 | " <td>0.000020</td>\n", |
||
| 1093 | " <td>0.000154</td>\n", |
||
| 1094 | " <td>0.000059</td>\n", |
||
| 1095 | " <td>0.999757</td>\n", |
||
| 1096 | " </tr>\n", |
||
| 1097 | " <tr>\n", |
||
| 1098 | " <th>10790</th>\n", |
||
| 1099 | " <td>0</td>\n", |
||
| 1100 | " <td>21.000000</td>\n", |
||
| 1101 | " <td>1.770000</td>\n", |
||
| 1102 | " <td>75.000000</td>\n", |
||
| 1103 | " <td>0</td>\n", |
||
| 1104 | " <td>1</td>\n", |
||
| 1105 | " <td>3.000000</td>\n", |
||
| 1106 | " <td>3.0</td>\n", |
||
| 1107 | " <td>2</td>\n", |
||
| 1108 | " <td>0</td>\n", |
||
| 1109 | " <td>...</td>\n", |
||
| 1110 | " <td>502.729101</td>\n", |
||
| 1111 | " <td>573.098750</td>\n", |
||
| 1112 | " <td>2</td>\n", |
||
| 1113 | " <td>0.000212</td>\n", |
||
| 1114 | " <td>0.341897</td>\n", |
||
| 1115 | " <td>0.657261</td>\n", |
||
| 1116 | " <td>0.000391</td>\n", |
||
| 1117 | " <td>0.000052</td>\n", |
||
| 1118 | " <td>0.000019</td>\n", |
||
| 1119 | " <td>0.000168</td>\n", |
||
| 1120 | " </tr>\n", |
||
| 1121 | " <tr>\n", |
||
| 1122 | " <th>10791</th>\n", |
||
| 1123 | " <td>0</td>\n", |
||
| 1124 | " <td>29.669219</td>\n", |
||
| 1125 | " <td>1.774644</td>\n", |
||
| 1126 | " <td>105.966894</td>\n", |
||
| 1127 | " <td>1</td>\n", |
||
| 1128 | " <td>1</td>\n", |
||
| 1129 | " <td>2.934671</td>\n", |
||
| 1130 | " <td>3.0</td>\n", |
||
| 1131 | " <td>1</td>\n", |
||
| 1132 | " <td>0</td>\n", |
||
| 1133 | " <td>...</td>\n", |
||
| 1134 | " <td>998.283353</td>\n", |
||
| 1135 | " <td>1132.127734</td>\n", |
||
| 1136 | " <td>4</td>\n", |
||
| 1137 | " <td>0.000621</td>\n", |
||
| 1138 | " <td>0.000067</td>\n", |
||
| 1139 | " <td>0.000338</td>\n", |
||
| 1140 | " <td>0.004232</td>\n", |
||
| 1141 | " <td>0.936736</td>\n", |
||
| 1142 | " <td>0.057409</td>\n", |
||
| 1143 | " <td>0.000597</td>\n", |
||
| 1144 | " </tr>\n", |
||
| 1145 | " <tr>\n", |
||
| 1146 | " <th>10792</th>\n", |
||
| 1147 | " <td>1</td>\n", |
||
| 1148 | " <td>26.000000</td>\n", |
||
| 1149 | " <td>1.656504</td>\n", |
||
| 1150 | " <td>111.884535</td>\n", |
||
| 1151 | " <td>1</td>\n", |
||
| 1152 | " <td>1</td>\n", |
||
| 1153 | " <td>3.000000</td>\n", |
||
| 1154 | " <td>3.0</td>\n", |
||
| 1155 | " <td>1</td>\n", |
||
| 1156 | " <td>0</td>\n", |
||
| 1157 | " <td>...</td>\n", |
||
| 1158 | " <td>1060.128308</td>\n", |
||
| 1159 | " <td>1662.532588</td>\n", |
||
| 1160 | " <td>6</td>\n", |
||
| 1161 | " <td>0.000001</td>\n", |
||
| 1162 | " <td>0.000002</td>\n", |
||
| 1163 | " <td>0.000007</td>\n", |
||
| 1164 | " <td>0.000021</td>\n", |
||
| 1165 | " <td>0.000173</td>\n", |
||
| 1166 | " <td>0.000076</td>\n", |
||
| 1167 | " <td>0.999719</td>\n", |
||
| 1168 | " </tr>\n", |
||
| 1169 | " </tbody>\n", |
||
| 1170 | "</table>\n", |
||
| 1171 | "<p>10793 rows × 36 columns</p>\n", |
||
| 1172 | "</div>" |
||
| 1173 | ], |
||
| 1174 | "text/plain": [ |
||
| 1175 | " Gender Age Height Weight \\\n", |
||
| 1176 | "0 1 21.000000 1.550000 51.000000 \n", |
||
| 1177 | "1 0 20.000000 1.700000 80.000000 \n", |
||
| 1178 | "2 1 18.000000 1.600000 60.000000 \n", |
||
| 1179 | "3 1 26.000000 1.632983 111.720238 \n", |
||
| 1180 | "4 1 21.682636 1.748524 133.845064 \n", |
||
| 1181 | "... ... ... ... ... \n", |
||
| 1182 | "10788 0 18.000000 1.780000 108.000000 \n", |
||
| 1183 | "10789 1 26.000000 1.641601 111.830924 \n", |
||
| 1184 | "10790 0 21.000000 1.770000 75.000000 \n", |
||
| 1185 | "10791 0 29.669219 1.774644 105.966894 \n", |
||
| 1186 | "10792 1 26.000000 1.656504 111.884535 \n", |
||
| 1187 | "\n", |
||
| 1188 | " family_history_with_overweight FAVC FCVC NCP CAEC SMOKE ... \\\n", |
||
| 1189 | "0 0 1 3.000000 1.0 2 0 ... \n", |
||
| 1190 | "1 1 1 2.000000 3.0 1 0 ... \n", |
||
| 1191 | "2 1 1 2.000000 3.0 1 0 ... \n", |
||
| 1192 | "3 1 1 3.000000 3.0 1 0 ... \n", |
||
| 1193 | "4 1 1 3.000000 3.0 1 0 ... \n", |
||
| 1194 | "... ... ... ... ... ... ... ... \n", |
||
| 1195 | "10788 1 1 2.000000 3.0 1 0 ... \n", |
||
| 1196 | "10789 1 1 3.000000 3.0 1 0 ... \n", |
||
| 1197 | "10790 0 1 3.000000 3.0 2 0 ... \n", |
||
| 1198 | "10791 1 1 2.934671 3.0 1 0 ... \n", |
||
| 1199 | "10792 1 1 3.000000 3.0 1 0 ... \n", |
||
| 1200 | "\n", |
||
| 1201 | " Age * BMI^2 Age^2 * BMI^2 NObeyesdad 0 1 2 \\\n", |
||
| 1202 | "0 445.785640 450.623213 0 0.797175 0.196596 0.005617 \n", |
||
| 1203 | "1 553.633218 766.274350 3 0.000041 0.001926 0.047782 \n", |
||
| 1204 | "2 421.875000 549.316406 1 0.011628 0.953612 0.033047 \n", |
||
| 1205 | "3 1089.285877 1755.242193 6 0.000001 0.000002 0.000008 \n", |
||
| 1206 | "4 949.229536 1916.541944 6 0.000001 0.000001 0.000004 \n", |
||
| 1207 | "... ... ... ... ... ... ... \n", |
||
| 1208 | "10788 613.558894 1161.896656 4 0.000007 0.000014 0.000035 \n", |
||
| 1209 | "10789 1078.946835 1722.080284 6 0.000001 0.000002 0.000007 \n", |
||
| 1210 | "10790 502.729101 573.098750 2 0.000212 0.341897 0.657261 \n", |
||
| 1211 | "10791 998.283353 1132.127734 4 0.000621 0.000067 0.000338 \n", |
||
| 1212 | "10792 1060.128308 1662.532588 6 0.000001 0.000002 0.000007 \n", |
||
| 1213 | "\n", |
||
| 1214 | " 3 4 5 6 \n", |
||
| 1215 | "0 0.000520 0.000032 0.000019 0.000040 \n", |
||
| 1216 | "1 0.948167 0.002041 0.000018 0.000025 \n", |
||
| 1217 | "2 0.001538 0.000150 0.000005 0.000020 \n", |
||
| 1218 | "3 0.000018 0.000172 0.000040 0.999759 \n", |
||
| 1219 | "4 0.000012 0.000092 0.000058 0.999831 \n", |
||
| 1220 | "... ... ... ... ... \n", |
||
| 1221 | "10788 0.000287 0.998704 0.000949 0.000005 \n", |
||
| 1222 | "10789 0.000020 0.000154 0.000059 0.999757 \n", |
||
| 1223 | "10790 0.000391 0.000052 0.000019 0.000168 \n", |
||
| 1224 | "10791 0.004232 0.936736 0.057409 0.000597 \n", |
||
| 1225 | "10792 0.000021 0.000173 0.000076 0.999719 \n", |
||
| 1226 | "\n", |
||
| 1227 | "[10793 rows x 36 columns]" |
||
| 1228 | ] |
||
| 1229 | }, |
||
| 1230 | "execution_count": 9, |
||
| 1231 | "metadata": {}, |
||
| 1232 | "output_type": "execute_result" |
||
| 1233 | } |
||
| 1234 | ], |
||
| 1235 | "source": [ |
||
| 1236 | "train" |
||
| 1237 | ] |
||
| 1238 | }, |
||
| 1239 | { |
||
| 1240 | "cell_type": "code", |
||
| 1241 | "execution_count": 27, |
||
| 1242 | "metadata": {}, |
||
| 1243 | "outputs": [ |
||
| 1244 | { |
||
| 1245 | "data": { |
||
| 1246 | "text/html": [ |
||
| 1247 | "<style type=\"text/css\">\n", |
||
| 1248 | "#T_960f5_row8_col1 {\n", |
||
| 1249 | " background-color: lightgreen;\n", |
||
| 1250 | "}\n", |
||
| 1251 | "</style>\n", |
||
| 1252 | "<table id=\"T_960f5\">\n", |
||
| 1253 | " <thead>\n", |
||
| 1254 | " <tr>\n", |
||
| 1255 | " <th class=\"blank level0\" > </th>\n", |
||
| 1256 | " <th id=\"T_960f5_level0_col0\" class=\"col_heading level0 col0\" >Description</th>\n", |
||
| 1257 | " <th id=\"T_960f5_level0_col1\" class=\"col_heading level0 col1\" >Value</th>\n", |
||
| 1258 | " </tr>\n", |
||
| 1259 | " </thead>\n", |
||
| 1260 | " <tbody>\n", |
||
| 1261 | " <tr>\n", |
||
| 1262 | " <th id=\"T_960f5_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n", |
||
| 1263 | " <td id=\"T_960f5_row0_col0\" class=\"data row0 col0\" >Session id</td>\n", |
||
| 1264 | " <td id=\"T_960f5_row0_col1\" class=\"data row0 col1\" >5119</td>\n", |
||
| 1265 | " </tr>\n", |
||
| 1266 | " <tr>\n", |
||
| 1267 | " <th id=\"T_960f5_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n", |
||
| 1268 | " <td id=\"T_960f5_row1_col0\" class=\"data row1 col0\" >Target</td>\n", |
||
| 1269 | " <td id=\"T_960f5_row1_col1\" class=\"data row1 col1\" >NObeyesdad</td>\n", |
||
| 1270 | " </tr>\n", |
||
| 1271 | " <tr>\n", |
||
| 1272 | " <th id=\"T_960f5_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n", |
||
| 1273 | " <td id=\"T_960f5_row2_col0\" class=\"data row2 col0\" >Target type</td>\n", |
||
| 1274 | " <td id=\"T_960f5_row2_col1\" class=\"data row2 col1\" >Multiclass</td>\n", |
||
| 1275 | " </tr>\n", |
||
| 1276 | " <tr>\n", |
||
| 1277 | " <th id=\"T_960f5_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n", |
||
| 1278 | " <td id=\"T_960f5_row3_col0\" class=\"data row3 col0\" >Original data shape</td>\n", |
||
| 1279 | " <td id=\"T_960f5_row3_col1\" class=\"data row3 col1\" >(10793, 35)</td>\n", |
||
| 1280 | " </tr>\n", |
||
| 1281 | " <tr>\n", |
||
| 1282 | " <th id=\"T_960f5_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n", |
||
| 1283 | " <td id=\"T_960f5_row4_col0\" class=\"data row4 col0\" >Transformed data shape</td>\n", |
||
| 1284 | " <td id=\"T_960f5_row4_col1\" class=\"data row4 col1\" >(10793, 35)</td>\n", |
||
| 1285 | " </tr>\n", |
||
| 1286 | " <tr>\n", |
||
| 1287 | " <th id=\"T_960f5_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n", |
||
| 1288 | " <td id=\"T_960f5_row5_col0\" class=\"data row5 col0\" >Transformed train set shape</td>\n", |
||
| 1289 | " <td id=\"T_960f5_row5_col1\" class=\"data row5 col1\" >(7555, 35)</td>\n", |
||
| 1290 | " </tr>\n", |
||
| 1291 | " <tr>\n", |
||
| 1292 | " <th id=\"T_960f5_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n", |
||
| 1293 | " <td id=\"T_960f5_row6_col0\" class=\"data row6 col0\" >Transformed test set shape</td>\n", |
||
| 1294 | " <td id=\"T_960f5_row6_col1\" class=\"data row6 col1\" >(3238, 35)</td>\n", |
||
| 1295 | " </tr>\n", |
||
| 1296 | " <tr>\n", |
||
| 1297 | " <th id=\"T_960f5_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n", |
||
| 1298 | " <td id=\"T_960f5_row7_col0\" class=\"data row7 col0\" >Numeric features</td>\n", |
||
| 1299 | " <td id=\"T_960f5_row7_col1\" class=\"data row7 col1\" >34</td>\n", |
||
| 1300 | " </tr>\n", |
||
| 1301 | " <tr>\n", |
||
| 1302 | " <th id=\"T_960f5_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n", |
||
| 1303 | " <td id=\"T_960f5_row8_col0\" class=\"data row8 col0\" >Preprocess</td>\n", |
||
| 1304 | " <td id=\"T_960f5_row8_col1\" class=\"data row8 col1\" >True</td>\n", |
||
| 1305 | " </tr>\n", |
||
| 1306 | " <tr>\n", |
||
| 1307 | " <th id=\"T_960f5_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n", |
||
| 1308 | " <td id=\"T_960f5_row9_col0\" class=\"data row9 col0\" >Imputation type</td>\n", |
||
| 1309 | " <td id=\"T_960f5_row9_col1\" class=\"data row9 col1\" >simple</td>\n", |
||
| 1310 | " </tr>\n", |
||
| 1311 | " <tr>\n", |
||
| 1312 | " <th id=\"T_960f5_level0_row10\" class=\"row_heading level0 row10\" >10</th>\n", |
||
| 1313 | " <td id=\"T_960f5_row10_col0\" class=\"data row10 col0\" >Numeric imputation</td>\n", |
||
| 1314 | " <td id=\"T_960f5_row10_col1\" class=\"data row10 col1\" >mean</td>\n", |
||
| 1315 | " </tr>\n", |
||
| 1316 | " <tr>\n", |
||
| 1317 | " <th id=\"T_960f5_level0_row11\" class=\"row_heading level0 row11\" >11</th>\n", |
||
| 1318 | " <td id=\"T_960f5_row11_col0\" class=\"data row11 col0\" >Categorical imputation</td>\n", |
||
| 1319 | " <td id=\"T_960f5_row11_col1\" class=\"data row11 col1\" >mode</td>\n", |
||
| 1320 | " </tr>\n", |
||
| 1321 | " <tr>\n", |
||
| 1322 | " <th id=\"T_960f5_level0_row12\" class=\"row_heading level0 row12\" >12</th>\n", |
||
| 1323 | " <td id=\"T_960f5_row12_col0\" class=\"data row12 col0\" >Fold Generator</td>\n", |
||
| 1324 | " <td id=\"T_960f5_row12_col1\" class=\"data row12 col1\" >StratifiedKFold</td>\n", |
||
| 1325 | " </tr>\n", |
||
| 1326 | " <tr>\n", |
||
| 1327 | " <th id=\"T_960f5_level0_row13\" class=\"row_heading level0 row13\" >13</th>\n", |
||
| 1328 | " <td id=\"T_960f5_row13_col0\" class=\"data row13 col0\" >Fold Number</td>\n", |
||
| 1329 | " <td id=\"T_960f5_row13_col1\" class=\"data row13 col1\" >10</td>\n", |
||
| 1330 | " </tr>\n", |
||
| 1331 | " <tr>\n", |
||
| 1332 | " <th id=\"T_960f5_level0_row14\" class=\"row_heading level0 row14\" >14</th>\n", |
||
| 1333 | " <td id=\"T_960f5_row14_col0\" class=\"data row14 col0\" >CPU Jobs</td>\n", |
||
| 1334 | " <td id=\"T_960f5_row14_col1\" class=\"data row14 col1\" >-1</td>\n", |
||
| 1335 | " </tr>\n", |
||
| 1336 | " <tr>\n", |
||
| 1337 | " <th id=\"T_960f5_level0_row15\" class=\"row_heading level0 row15\" >15</th>\n", |
||
| 1338 | " <td id=\"T_960f5_row15_col0\" class=\"data row15 col0\" >Use GPU</td>\n", |
||
| 1339 | " <td id=\"T_960f5_row15_col1\" class=\"data row15 col1\" >False</td>\n", |
||
| 1340 | " </tr>\n", |
||
| 1341 | " <tr>\n", |
||
| 1342 | " <th id=\"T_960f5_level0_row16\" class=\"row_heading level0 row16\" >16</th>\n", |
||
| 1343 | " <td id=\"T_960f5_row16_col0\" class=\"data row16 col0\" >Log Experiment</td>\n", |
||
| 1344 | " <td id=\"T_960f5_row16_col1\" class=\"data row16 col1\" >False</td>\n", |
||
| 1345 | " </tr>\n", |
||
| 1346 | " <tr>\n", |
||
| 1347 | " <th id=\"T_960f5_level0_row17\" class=\"row_heading level0 row17\" >17</th>\n", |
||
| 1348 | " <td id=\"T_960f5_row17_col0\" class=\"data row17 col0\" >Experiment Name</td>\n", |
||
| 1349 | " <td id=\"T_960f5_row17_col1\" class=\"data row17 col1\" >clf-default-name</td>\n", |
||
| 1350 | " </tr>\n", |
||
| 1351 | " <tr>\n", |
||
| 1352 | " <th id=\"T_960f5_level0_row18\" class=\"row_heading level0 row18\" >18</th>\n", |
||
| 1353 | " <td id=\"T_960f5_row18_col0\" class=\"data row18 col0\" >USI</td>\n", |
||
| 1354 | " <td id=\"T_960f5_row18_col1\" class=\"data row18 col1\" >2ccb</td>\n", |
||
| 1355 | " </tr>\n", |
||
| 1356 | " </tbody>\n", |
||
| 1357 | "</table>\n" |
||
| 1358 | ], |
||
| 1359 | "text/plain": [ |
||
| 1360 | "<pandas.io.formats.style.Styler at 0x143ae0a90>" |
||
| 1361 | ] |
||
| 1362 | }, |
||
| 1363 | "metadata": {}, |
||
| 1364 | "output_type": "display_data" |
||
| 1365 | }, |
||
| 1366 | { |
||
| 1367 | "data": { |
||
| 1368 | "text/html": [], |
||
| 1369 | "text/plain": [ |
||
| 1370 | "<IPython.core.display.HTML object>" |
||
| 1371 | ] |
||
| 1372 | }, |
||
| 1373 | "metadata": {}, |
||
| 1374 | "output_type": "display_data" |
||
| 1375 | }, |
||
| 1376 | { |
||
| 1377 | "data": { |
||
| 1378 | "text/html": [ |
||
| 1379 | "<style type=\"text/css\">\n", |
||
| 1380 | "#T_d099c_row10_col0, #T_d099c_row10_col1, #T_d099c_row10_col2, #T_d099c_row10_col3, #T_d099c_row10_col4, #T_d099c_row10_col5, #T_d099c_row10_col6 {\n", |
||
| 1381 | " background: yellow;\n", |
||
| 1382 | "}\n", |
||
| 1383 | "</style>\n", |
||
| 1384 | "<table id=\"T_d099c\">\n", |
||
| 1385 | " <thead>\n", |
||
| 1386 | " <tr>\n", |
||
| 1387 | " <th class=\"blank level0\" > </th>\n", |
||
| 1388 | " <th id=\"T_d099c_level0_col0\" class=\"col_heading level0 col0\" >Accuracy</th>\n", |
||
| 1389 | " <th id=\"T_d099c_level0_col1\" class=\"col_heading level0 col1\" >AUC</th>\n", |
||
| 1390 | " <th id=\"T_d099c_level0_col2\" class=\"col_heading level0 col2\" >Recall</th>\n", |
||
| 1391 | " <th id=\"T_d099c_level0_col3\" class=\"col_heading level0 col3\" >Prec.</th>\n", |
||
| 1392 | " <th id=\"T_d099c_level0_col4\" class=\"col_heading level0 col4\" >F1</th>\n", |
||
| 1393 | " <th id=\"T_d099c_level0_col5\" class=\"col_heading level0 col5\" >Kappa</th>\n", |
||
| 1394 | " <th id=\"T_d099c_level0_col6\" class=\"col_heading level0 col6\" >MCC</th>\n", |
||
| 1395 | " </tr>\n", |
||
| 1396 | " <tr>\n", |
||
| 1397 | " <th class=\"index_name level0\" >Fold</th>\n", |
||
| 1398 | " <th class=\"blank col0\" > </th>\n", |
||
| 1399 | " <th class=\"blank col1\" > </th>\n", |
||
| 1400 | " <th class=\"blank col2\" > </th>\n", |
||
| 1401 | " <th class=\"blank col3\" > </th>\n", |
||
| 1402 | " <th class=\"blank col4\" > </th>\n", |
||
| 1403 | " <th class=\"blank col5\" > </th>\n", |
||
| 1404 | " <th class=\"blank col6\" > </th>\n", |
||
| 1405 | " </tr>\n", |
||
| 1406 | " </thead>\n", |
||
| 1407 | " <tbody>\n", |
||
| 1408 | " <tr>\n", |
||
| 1409 | " <th id=\"T_d099c_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n", |
||
| 1410 | " <td id=\"T_d099c_row0_col0\" class=\"data row0 col0\" >0.8307</td>\n", |
||
| 1411 | " <td id=\"T_d099c_row0_col1\" class=\"data row0 col1\" >0.9024</td>\n", |
||
| 1412 | " <td id=\"T_d099c_row0_col2\" class=\"data row0 col2\" >0.8307</td>\n", |
||
| 1413 | " <td id=\"T_d099c_row0_col3\" class=\"data row0 col3\" >0.8307</td>\n", |
||
| 1414 | " <td id=\"T_d099c_row0_col4\" class=\"data row0 col4\" >0.8304</td>\n", |
||
| 1415 | " <td id=\"T_d099c_row0_col5\" class=\"data row0 col5\" >0.8013</td>\n", |
||
| 1416 | " <td id=\"T_d099c_row0_col6\" class=\"data row0 col6\" >0.8014</td>\n", |
||
| 1417 | " </tr>\n", |
||
| 1418 | " <tr>\n", |
||
| 1419 | " <th id=\"T_d099c_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n", |
||
| 1420 | " <td id=\"T_d099c_row1_col0\" class=\"data row1 col0\" >0.8241</td>\n", |
||
| 1421 | " <td id=\"T_d099c_row1_col1\" class=\"data row1 col1\" >0.8991</td>\n", |
||
| 1422 | " <td id=\"T_d099c_row1_col2\" class=\"data row1 col2\" >0.8241</td>\n", |
||
| 1423 | " <td id=\"T_d099c_row1_col3\" class=\"data row1 col3\" >0.8259</td>\n", |
||
| 1424 | " <td id=\"T_d099c_row1_col4\" class=\"data row1 col4\" >0.8248</td>\n", |
||
| 1425 | " <td id=\"T_d099c_row1_col5\" class=\"data row1 col5\" >0.7937</td>\n", |
||
| 1426 | " <td id=\"T_d099c_row1_col6\" class=\"data row1 col6\" >0.7938</td>\n", |
||
| 1427 | " </tr>\n", |
||
| 1428 | " <tr>\n", |
||
| 1429 | " <th id=\"T_d099c_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n", |
||
| 1430 | " <td id=\"T_d099c_row2_col0\" class=\"data row2 col0\" >0.8571</td>\n", |
||
| 1431 | " <td id=\"T_d099c_row2_col1\" class=\"data row2 col1\" >0.9178</td>\n", |
||
| 1432 | " <td id=\"T_d099c_row2_col2\" class=\"data row2 col2\" >0.8571</td>\n", |
||
| 1433 | " <td id=\"T_d099c_row2_col3\" class=\"data row2 col3\" >0.8616</td>\n", |
||
| 1434 | " <td id=\"T_d099c_row2_col4\" class=\"data row2 col4\" >0.8588</td>\n", |
||
| 1435 | " <td id=\"T_d099c_row2_col5\" class=\"data row2 col5\" >0.8324</td>\n", |
||
| 1436 | " <td id=\"T_d099c_row2_col6\" class=\"data row2 col6\" >0.8325</td>\n", |
||
| 1437 | " </tr>\n", |
||
| 1438 | " <tr>\n", |
||
| 1439 | " <th id=\"T_d099c_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n", |
||
| 1440 | " <td id=\"T_d099c_row3_col0\" class=\"data row3 col0\" >0.8347</td>\n", |
||
| 1441 | " <td id=\"T_d099c_row3_col1\" class=\"data row3 col1\" >0.9048</td>\n", |
||
| 1442 | " <td id=\"T_d099c_row3_col2\" class=\"data row3 col2\" >0.8347</td>\n", |
||
| 1443 | " <td id=\"T_d099c_row3_col3\" class=\"data row3 col3\" >0.8336</td>\n", |
||
| 1444 | " <td id=\"T_d099c_row3_col4\" class=\"data row3 col4\" >0.8334</td>\n", |
||
| 1445 | " <td id=\"T_d099c_row3_col5\" class=\"data row3 col5\" >0.8059</td>\n", |
||
| 1446 | " <td id=\"T_d099c_row3_col6\" class=\"data row3 col6\" >0.8061</td>\n", |
||
| 1447 | " </tr>\n", |
||
| 1448 | " <tr>\n", |
||
| 1449 | " <th id=\"T_d099c_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n", |
||
| 1450 | " <td id=\"T_d099c_row4_col0\" class=\"data row4 col0\" >0.8254</td>\n", |
||
| 1451 | " <td id=\"T_d099c_row4_col1\" class=\"data row4 col1\" >0.8996</td>\n", |
||
| 1452 | " <td id=\"T_d099c_row4_col2\" class=\"data row4 col2\" >0.8254</td>\n", |
||
| 1453 | " <td id=\"T_d099c_row4_col3\" class=\"data row4 col3\" >0.8254</td>\n", |
||
| 1454 | " <td id=\"T_d099c_row4_col4\" class=\"data row4 col4\" >0.8253</td>\n", |
||
| 1455 | " <td id=\"T_d099c_row4_col5\" class=\"data row4 col5\" >0.7951</td>\n", |
||
| 1456 | " <td id=\"T_d099c_row4_col6\" class=\"data row4 col6\" >0.7951</td>\n", |
||
| 1457 | " </tr>\n", |
||
| 1458 | " <tr>\n", |
||
| 1459 | " <th id=\"T_d099c_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n", |
||
| 1460 | " <td id=\"T_d099c_row5_col0\" class=\"data row5 col0\" >0.8477</td>\n", |
||
| 1461 | " <td id=\"T_d099c_row5_col1\" class=\"data row5 col1\" >0.9123</td>\n", |
||
| 1462 | " <td id=\"T_d099c_row5_col2\" class=\"data row5 col2\" >0.8477</td>\n", |
||
| 1463 | " <td id=\"T_d099c_row5_col3\" class=\"data row5 col3\" >0.8471</td>\n", |
||
| 1464 | " <td id=\"T_d099c_row5_col4\" class=\"data row5 col4\" >0.8473</td>\n", |
||
| 1465 | " <td id=\"T_d099c_row5_col5\" class=\"data row5 col5\" >0.8213</td>\n", |
||
| 1466 | " <td id=\"T_d099c_row5_col6\" class=\"data row5 col6\" >0.8213</td>\n", |
||
| 1467 | " </tr>\n", |
||
| 1468 | " <tr>\n", |
||
| 1469 | " <th id=\"T_d099c_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n", |
||
| 1470 | " <td id=\"T_d099c_row6_col0\" class=\"data row6 col0\" >0.8278</td>\n", |
||
| 1471 | " <td id=\"T_d099c_row6_col1\" class=\"data row6 col1\" >0.9007</td>\n", |
||
| 1472 | " <td id=\"T_d099c_row6_col2\" class=\"data row6 col2\" >0.8278</td>\n", |
||
| 1473 | " <td id=\"T_d099c_row6_col3\" class=\"data row6 col3\" >0.8268</td>\n", |
||
| 1474 | " <td id=\"T_d099c_row6_col4\" class=\"data row6 col4\" >0.8271</td>\n", |
||
| 1475 | " <td id=\"T_d099c_row6_col5\" class=\"data row6 col5\" >0.7979</td>\n", |
||
| 1476 | " <td id=\"T_d099c_row6_col6\" class=\"data row6 col6\" >0.7980</td>\n", |
||
| 1477 | " </tr>\n", |
||
| 1478 | " <tr>\n", |
||
| 1479 | " <th id=\"T_d099c_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n", |
||
| 1480 | " <td id=\"T_d099c_row7_col0\" class=\"data row7 col0\" >0.8291</td>\n", |
||
| 1481 | " <td id=\"T_d099c_row7_col1\" class=\"data row7 col1\" >0.9019</td>\n", |
||
| 1482 | " <td id=\"T_d099c_row7_col2\" class=\"data row7 col2\" >0.8291</td>\n", |
||
| 1483 | " <td id=\"T_d099c_row7_col3\" class=\"data row7 col3\" >0.8330</td>\n", |
||
| 1484 | " <td id=\"T_d099c_row7_col4\" class=\"data row7 col4\" >0.8298</td>\n", |
||
| 1485 | " <td id=\"T_d099c_row7_col5\" class=\"data row7 col5\" >0.7997</td>\n", |
||
| 1486 | " <td id=\"T_d099c_row7_col6\" class=\"data row7 col6\" >0.8002</td>\n", |
||
| 1487 | " </tr>\n", |
||
| 1488 | " <tr>\n", |
||
| 1489 | " <th id=\"T_d099c_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n", |
||
| 1490 | " <td id=\"T_d099c_row8_col0\" class=\"data row8 col0\" >0.8424</td>\n", |
||
| 1491 | " <td id=\"T_d099c_row8_col1\" class=\"data row8 col1\" >0.9093</td>\n", |
||
| 1492 | " <td id=\"T_d099c_row8_col2\" class=\"data row8 col2\" >0.8424</td>\n", |
||
| 1493 | " <td id=\"T_d099c_row8_col3\" class=\"data row8 col3\" >0.8451</td>\n", |
||
| 1494 | " <td id=\"T_d099c_row8_col4\" class=\"data row8 col4\" >0.8434</td>\n", |
||
| 1495 | " <td id=\"T_d099c_row8_col5\" class=\"data row8 col5\" >0.8151</td>\n", |
||
| 1496 | " <td id=\"T_d099c_row8_col6\" class=\"data row8 col6\" >0.8152</td>\n", |
||
| 1497 | " </tr>\n", |
||
| 1498 | " <tr>\n", |
||
| 1499 | " <th id=\"T_d099c_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n", |
||
| 1500 | " <td id=\"T_d099c_row9_col0\" class=\"data row9 col0\" >0.8331</td>\n", |
||
| 1501 | " <td id=\"T_d099c_row9_col1\" class=\"data row9 col1\" >0.9038</td>\n", |
||
| 1502 | " <td id=\"T_d099c_row9_col2\" class=\"data row9 col2\" >0.8331</td>\n", |
||
| 1503 | " <td id=\"T_d099c_row9_col3\" class=\"data row9 col3\" >0.8334</td>\n", |
||
| 1504 | " <td id=\"T_d099c_row9_col4\" class=\"data row9 col4\" >0.8329</td>\n", |
||
| 1505 | " <td id=\"T_d099c_row9_col5\" class=\"data row9 col5\" >0.8041</td>\n", |
||
| 1506 | " <td id=\"T_d099c_row9_col6\" class=\"data row9 col6\" >0.8043</td>\n", |
||
| 1507 | " </tr>\n", |
||
| 1508 | " <tr>\n", |
||
| 1509 | " <th id=\"T_d099c_level0_row10\" class=\"row_heading level0 row10\" >Mean</th>\n", |
||
| 1510 | " <td id=\"T_d099c_row10_col0\" class=\"data row10 col0\" >0.8352</td>\n", |
||
| 1511 | " <td id=\"T_d099c_row10_col1\" class=\"data row10 col1\" >0.9052</td>\n", |
||
| 1512 | " <td id=\"T_d099c_row10_col2\" class=\"data row10 col2\" >0.8352</td>\n", |
||
| 1513 | " <td id=\"T_d099c_row10_col3\" class=\"data row10 col3\" >0.8363</td>\n", |
||
| 1514 | " <td id=\"T_d099c_row10_col4\" class=\"data row10 col4\" >0.8353</td>\n", |
||
| 1515 | " <td id=\"T_d099c_row10_col5\" class=\"data row10 col5\" >0.8066</td>\n", |
||
| 1516 | " <td id=\"T_d099c_row10_col6\" class=\"data row10 col6\" >0.8068</td>\n", |
||
| 1517 | " </tr>\n", |
||
| 1518 | " <tr>\n", |
||
| 1519 | " <th id=\"T_d099c_level0_row11\" class=\"row_heading level0 row11\" >Std</th>\n", |
||
| 1520 | " <td id=\"T_d099c_row11_col0\" class=\"data row11 col0\" >0.0101</td>\n", |
||
| 1521 | " <td id=\"T_d099c_row11_col1\" class=\"data row11 col1\" >0.0058</td>\n", |
||
| 1522 | " <td id=\"T_d099c_row11_col2\" class=\"data row11 col2\" >0.0101</td>\n", |
||
| 1523 | " <td id=\"T_d099c_row11_col3\" class=\"data row11 col3\" >0.0110</td>\n", |
||
| 1524 | " <td id=\"T_d099c_row11_col4\" class=\"data row11 col4\" >0.0105</td>\n", |
||
| 1525 | " <td id=\"T_d099c_row11_col5\" class=\"data row11 col5\" >0.0119</td>\n", |
||
| 1526 | " <td id=\"T_d099c_row11_col6\" class=\"data row11 col6\" >0.0119</td>\n", |
||
| 1527 | " </tr>\n", |
||
| 1528 | " </tbody>\n", |
||
| 1529 | "</table>\n" |
||
| 1530 | ], |
||
| 1531 | "text/plain": [ |
||
| 1532 | "<pandas.io.formats.style.Styler at 0x143b24130>" |
||
| 1533 | ] |
||
| 1534 | }, |
||
| 1535 | "metadata": {}, |
||
| 1536 | "output_type": "display_data" |
||
| 1537 | }, |
||
| 1538 | { |
||
| 1539 | "data": { |
||
| 1540 | "text/html": [], |
||
| 1541 | "text/plain": [ |
||
| 1542 | "<IPython.core.display.HTML object>" |
||
| 1543 | ] |
||
| 1544 | }, |
||
| 1545 | "metadata": {}, |
||
| 1546 | "output_type": "display_data" |
||
| 1547 | }, |
||
| 1548 | { |
||
| 1549 | "data": { |
||
| 1550 | "text/html": [ |
||
| 1551 | "<style type=\"text/css\">\n", |
||
| 1552 | "</style>\n", |
||
| 1553 | "<table id=\"T_d319f\">\n", |
||
| 1554 | " <thead>\n", |
||
| 1555 | " <tr>\n", |
||
| 1556 | " <th class=\"blank level0\" > </th>\n", |
||
| 1557 | " <th id=\"T_d319f_level0_col0\" class=\"col_heading level0 col0\" >Model</th>\n", |
||
| 1558 | " <th id=\"T_d319f_level0_col1\" class=\"col_heading level0 col1\" >Accuracy</th>\n", |
||
| 1559 | " <th id=\"T_d319f_level0_col2\" class=\"col_heading level0 col2\" >AUC</th>\n", |
||
| 1560 | " <th id=\"T_d319f_level0_col3\" class=\"col_heading level0 col3\" >Recall</th>\n", |
||
| 1561 | " <th id=\"T_d319f_level0_col4\" class=\"col_heading level0 col4\" >Prec.</th>\n", |
||
| 1562 | " <th id=\"T_d319f_level0_col5\" class=\"col_heading level0 col5\" >F1</th>\n", |
||
| 1563 | " <th id=\"T_d319f_level0_col6\" class=\"col_heading level0 col6\" >Kappa</th>\n", |
||
| 1564 | " <th id=\"T_d319f_level0_col7\" class=\"col_heading level0 col7\" >MCC</th>\n", |
||
| 1565 | " </tr>\n", |
||
| 1566 | " </thead>\n", |
||
| 1567 | " <tbody>\n", |
||
| 1568 | " <tr>\n", |
||
| 1569 | " <th id=\"T_d319f_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n", |
||
| 1570 | " <td id=\"T_d319f_row0_col0\" class=\"data row0 col0\" >Decision Tree Classifier</td>\n", |
||
| 1571 | " <td id=\"T_d319f_row0_col1\" class=\"data row0 col1\" >0.8222</td>\n", |
||
| 1572 | " <td id=\"T_d319f_row0_col2\" class=\"data row0 col2\" >0.8973</td>\n", |
||
| 1573 | " <td id=\"T_d319f_row0_col3\" class=\"data row0 col3\" >0.8222</td>\n", |
||
| 1574 | " <td id=\"T_d319f_row0_col4\" class=\"data row0 col4\" >0.8227</td>\n", |
||
| 1575 | " <td id=\"T_d319f_row0_col5\" class=\"data row0 col5\" >0.8222</td>\n", |
||
| 1576 | " <td id=\"T_d319f_row0_col6\" class=\"data row0 col6\" >0.7916</td>\n", |
||
| 1577 | " <td id=\"T_d319f_row0_col7\" class=\"data row0 col7\" >0.7917</td>\n", |
||
| 1578 | " </tr>\n", |
||
| 1579 | " </tbody>\n", |
||
| 1580 | "</table>\n" |
||
| 1581 | ], |
||
| 1582 | "text/plain": [ |
||
| 1583 | "<pandas.io.formats.style.Styler at 0x28324fa90>" |
||
| 1584 | ] |
||
| 1585 | }, |
||
| 1586 | "metadata": {}, |
||
| 1587 | "output_type": "display_data" |
||
| 1588 | }, |
||
| 1589 | { |
||
| 1590 | "ename": "ValueError", |
||
| 1591 | "evalue": "Classification metrics can't handle a mix of multiclass and continuous-multioutput targets", |
||
| 1592 | "output_type": "error", |
||
| 1593 | "traceback": [ |
||
| 1594 | "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", |
||
| 1595 | "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", |
||
| 1596 | "Cell \u001b[0;32mIn[27], line 64\u001b[0m\n\u001b[1;32m 61\u001b[0m y_val_pred_pycaret \u001b[38;5;241m=\u001b[39m predict_model(model, data\u001b[38;5;241m=\u001b[39mval_data)\n\u001b[1;32m 63\u001b[0m \u001b[38;5;66;03m# Evaluate performance\u001b[39;00m\n\u001b[0;32m---> 64\u001b[0m precision, recall, f1, support \u001b[38;5;241m=\u001b[39m \u001b[43mprecision_recall_fscore_support\u001b[49m\u001b[43m(\u001b[49m\u001b[43my_val\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_val_pred_pycaret\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maverage\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mweighted\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 66\u001b[0m \u001b[38;5;66;03m# Log metrics and model using MLflow\u001b[39;00m\n\u001b[1;32m 67\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m mlflow\u001b[38;5;241m.\u001b[39mstart_run(run_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPyCaret_Extended_Engineering\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[1;32m 68\u001b[0m \u001b[38;5;66;03m# Log PyCaret model\u001b[39;00m\n", |
||
| 1597 | "File \u001b[0;32m~/anaconda3/envs/DataScience/lib/python3.10/site-packages/sklearn/utils/_param_validation.py:213\u001b[0m, in \u001b[0;36mvalidate_params.<locals>.decorator.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 207\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 208\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\n\u001b[1;32m 209\u001b[0m skip_parameter_validation\u001b[38;5;241m=\u001b[39m(\n\u001b[1;32m 210\u001b[0m prefer_skip_nested_validation \u001b[38;5;129;01mor\u001b[39;00m global_skip_validation\n\u001b[1;32m 211\u001b[0m )\n\u001b[1;32m 212\u001b[0m ):\n\u001b[0;32m--> 213\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 214\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m InvalidParameterError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 215\u001b[0m \u001b[38;5;66;03m# When the function is just a wrapper around an estimator, we allow\u001b[39;00m\n\u001b[1;32m 216\u001b[0m \u001b[38;5;66;03m# the function to delegate validation to the estimator, but we replace\u001b[39;00m\n\u001b[1;32m 217\u001b[0m \u001b[38;5;66;03m# the name of the estimator by the name of the function in the error\u001b[39;00m\n\u001b[1;32m 218\u001b[0m \u001b[38;5;66;03m# message to avoid confusion.\u001b[39;00m\n\u001b[1;32m 219\u001b[0m msg \u001b[38;5;241m=\u001b[39m re\u001b[38;5;241m.\u001b[39msub(\n\u001b[1;32m 220\u001b[0m \u001b[38;5;124mr\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparameter of \u001b[39m\u001b[38;5;124m\\\u001b[39m\u001b[38;5;124mw+ must be\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 221\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparameter of \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfunc\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__qualname__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m must be\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 222\u001b[0m \u001b[38;5;28mstr\u001b[39m(e),\n\u001b[1;32m 223\u001b[0m )\n", |
||
| 1598 | "File \u001b[0;32m~/anaconda3/envs/DataScience/lib/python3.10/site-packages/sklearn/metrics/_classification.py:1755\u001b[0m, in \u001b[0;36mprecision_recall_fscore_support\u001b[0;34m(y_true, y_pred, beta, labels, pos_label, average, warn_for, sample_weight, zero_division)\u001b[0m\n\u001b[1;32m 1592\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Compute precision, recall, F-measure and support for each class.\u001b[39;00m\n\u001b[1;32m 1593\u001b[0m \n\u001b[1;32m 1594\u001b[0m \u001b[38;5;124;03mThe precision is the ratio ``tp / (tp + fp)`` where ``tp`` is the number of\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1752\u001b[0m \u001b[38;5;124;03m array([2, 2, 2]))\u001b[39;00m\n\u001b[1;32m 1753\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 1754\u001b[0m _check_zero_division(zero_division)\n\u001b[0;32m-> 1755\u001b[0m labels \u001b[38;5;241m=\u001b[39m \u001b[43m_check_set_wise_labels\u001b[49m\u001b[43m(\u001b[49m\u001b[43my_true\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_pred\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maverage\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlabels\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpos_label\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1757\u001b[0m \u001b[38;5;66;03m# Calculate tp_sum, pred_sum, true_sum ###\u001b[39;00m\n\u001b[1;32m 1758\u001b[0m samplewise \u001b[38;5;241m=\u001b[39m average \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msamples\u001b[39m\u001b[38;5;124m\"\u001b[39m\n", |
||
| 1599 | "File \u001b[0;32m~/anaconda3/envs/DataScience/lib/python3.10/site-packages/sklearn/metrics/_classification.py:1527\u001b[0m, in \u001b[0;36m_check_set_wise_labels\u001b[0;34m(y_true, y_pred, average, labels, pos_label)\u001b[0m\n\u001b[1;32m 1524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m average \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m average_options \u001b[38;5;129;01mand\u001b[39;00m average \u001b[38;5;241m!=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbinary\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m 1525\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124maverage has to be one of \u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m \u001b[38;5;28mstr\u001b[39m(average_options))\n\u001b[0;32m-> 1527\u001b[0m y_type, y_true, y_pred \u001b[38;5;241m=\u001b[39m \u001b[43m_check_targets\u001b[49m\u001b[43m(\u001b[49m\u001b[43my_true\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_pred\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1528\u001b[0m \u001b[38;5;66;03m# Convert to Python primitive type to avoid NumPy type / Python str\u001b[39;00m\n\u001b[1;32m 1529\u001b[0m \u001b[38;5;66;03m# comparison. See https://github.com/numpy/numpy/issues/6784\u001b[39;00m\n\u001b[1;32m 1530\u001b[0m present_labels \u001b[38;5;241m=\u001b[39m unique_labels(y_true, y_pred)\u001b[38;5;241m.\u001b[39mtolist()\n", |
||
| 1600 | "File \u001b[0;32m~/anaconda3/envs/DataScience/lib/python3.10/site-packages/sklearn/metrics/_classification.py:94\u001b[0m, in \u001b[0;36m_check_targets\u001b[0;34m(y_true, y_pred)\u001b[0m\n\u001b[1;32m 91\u001b[0m y_type \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmulticlass\u001b[39m\u001b[38;5;124m\"\u001b[39m}\n\u001b[1;32m 93\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(y_type) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m---> 94\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 95\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mClassification metrics can\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt handle a mix of \u001b[39m\u001b[38;5;132;01m{0}\u001b[39;00m\u001b[38;5;124m and \u001b[39m\u001b[38;5;132;01m{1}\u001b[39;00m\u001b[38;5;124m targets\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mformat(\n\u001b[1;32m 96\u001b[0m type_true, type_pred\n\u001b[1;32m 97\u001b[0m )\n\u001b[1;32m 98\u001b[0m )\n\u001b[1;32m 100\u001b[0m \u001b[38;5;66;03m# We can't have more than one value on y_type => The set is no more needed\u001b[39;00m\n\u001b[1;32m 101\u001b[0m y_type \u001b[38;5;241m=\u001b[39m y_type\u001b[38;5;241m.\u001b[39mpop()\n", |
||
| 1601 | "\u001b[0;31mValueError\u001b[0m: Classification metrics can't handle a mix of multiclass and continuous-multioutput targets" |
||
| 1602 | ] |
||
| 1603 | } |
||
| 1604 | ], |
||
| 1605 | "source": [ |
||
| 1606 | "path = '/Users/arham/Downloads/Projects/01-Dataset/01-Data-for-model-building/train.csv'\n", |
||
| 1607 | "train_df, val_df, test_df = load_data(path)\n", |
||
| 1608 | "\n", |
||
| 1609 | "train_df = datatypes(train_df)\n", |
||
| 1610 | "train_df = encode_target(train_df)\n", |
||
| 1611 | "train_df = age_binning(train_df)\n", |
||
| 1612 | "train_df, scaler_age = age_scaling_minmax(train_df)\n", |
||
| 1613 | "train_df = age_scaling_log(train_df)\n", |
||
| 1614 | "train_df, scaler_weight = weight_scaling_minmax(train_df)\n", |
||
| 1615 | "train_df = weight_scaling_log(train_df)\n", |
||
| 1616 | "train_df, scaler_height = height_scaling_minmax(train_df)\n", |
||
| 1617 | "train_df = height_scaling_log(train_df)\n", |
||
| 1618 | "train_df = make_gender_binary(train_df)\n", |
||
| 1619 | "train_df = fix_binary_columns(train_df)\n", |
||
| 1620 | "train_df = freq_cat_cols(train_df)\n", |
||
| 1621 | "train_df = Mtrans(train_df)\n", |
||
| 1622 | "train_df = other_features(train_df)\n", |
||
| 1623 | "\n", |
||
| 1624 | "val_df = test_pipeline(val_df, scaler_age, scaler_weight, scaler_height)\n", |
||
| 1625 | "test_df = test_pipeline(test_df, scaler_age, scaler_weight, scaler_height)\n", |
||
| 1626 | "\n", |
||
| 1627 | "Target = 'NObeyesdad'\n", |
||
| 1628 | "features = train_df.columns.drop(Target)\n", |
||
| 1629 | "\n", |
||
| 1630 | "features = ['Gender', 'Age', 'Height', 'Weight', 'family_history_with_overweight',\n", |
||
| 1631 | " 'FAVC', 'FCVC', 'NCP', 'CAEC', 'SMOKE', 'CH2O', 'SCC', 'FAF', 'TUE',\n", |
||
| 1632 | " 'CALC', 'Age_Group', \n", |
||
| 1633 | " 'MTRANS_Automobile', 'MTRANS_Bike', 'MTRANS_Motorbike',\n", |
||
| 1634 | " 'MTRANS_Public_Transportation', 'MTRANS_Walking', 'BMI', 'Age^2',\n", |
||
| 1635 | " 'Age^3', 'BMI^2', 'Age * BMI', 'Age * BMI^2', 'Age^2 * BMI^2', \n", |
||
| 1636 | " 'Scaled_Age', 'Log_Age', 'Scaled_Weight', 'Log_Weight', 'Scaled_Height', 'Log_Height']\n", |
||
| 1637 | "#'Scaled_Age', 'Log_Age', 'Scaled_Weight', 'Log_Weight', 'Scaled_Height', 'Log_Height',\n", |
||
| 1638 | "\n", |
||
| 1639 | "X_train = train_df[features]\n", |
||
| 1640 | "y_train = train_df[Target]\n", |
||
| 1641 | "X_val = val_df[features]\n", |
||
| 1642 | "y_val = val_df[Target]\n", |
||
| 1643 | "X_test = test_df[features]\n", |
||
| 1644 | "y_test = test_df[Target]\n", |
||
| 1645 | "\n", |
||
| 1646 | "#combine X_train and y_train as one dataframe\n", |
||
| 1647 | "tr = pd.concat([X_train, y_train], axis=1)\n", |
||
| 1648 | "te = pd.concat([X_test, y_test], axis =1)\n", |
||
| 1649 | "va = pd.concat([X_val, y_val], axis = 1)\n" |
||
| 1650 | ] |
||
| 1651 | }, |
||
| 1652 | { |
||
| 1653 | "cell_type": "markdown", |
||
| 1654 | "metadata": {}, |
||
| 1655 | "source": [ |
||
| 1656 | "### Zero Shot Learning" |
||
| 1657 | ] |
||
| 1658 | }, |
||
| 1659 | { |
||
| 1660 | "cell_type": "code", |
||
| 1661 | "execution_count": 20, |
||
| 1662 | "metadata": {}, |
||
| 1663 | "outputs": [ |
||
| 1664 | { |
||
| 1665 | "name": "stderr", |
||
| 1666 | "output_type": "stream", |
||
| 1667 | "text": [ |
||
| 1668 | "No path specified. Models will be saved in: \"AutogluonModels/ag-20240426_052138\"\n", |
||
| 1669 | "No presets specified! To achieve strong results with AutoGluon, it is recommended to use the available presets.\n", |
||
| 1670 | "\tRecommended Presets (For more details refer to https://auto.gluon.ai/stable/tutorials/tabular/tabular-essentials.html#presets):\n", |
||
| 1671 | "\tpresets='best_quality' : Maximize accuracy. Default time_limit=3600.\n", |
||
| 1672 | "\tpresets='high_quality' : Strong accuracy with fast inference speed. Default time_limit=3600.\n", |
||
| 1673 | "\tpresets='good_quality' : Good accuracy with very fast inference speed. Default time_limit=3600.\n", |
||
| 1674 | "\tpresets='medium_quality' : Fast training time, ideal for initial prototyping.\n", |
||
| 1675 | "Beginning AutoGluon training ...\n", |
||
| 1676 | "AutoGluon will save models to \"AutogluonModels/ag-20240426_052138\"\n", |
||
| 1677 | "=================== System Info ===================\n", |
||
| 1678 | "AutoGluon Version: 1.1.0\n", |
||
| 1679 | "Python Version: 3.10.13\n", |
||
| 1680 | "Operating System: Darwin\n", |
||
| 1681 | "Platform Machine: arm64\n", |
||
| 1682 | "Platform Version: Darwin Kernel Version 23.0.0: Fri Sep 15 14:42:57 PDT 2023; root:xnu-10002.1.13~1/RELEASE_ARM64_T8112\n", |
||
| 1683 | "CPU Count: 8\n", |
||
| 1684 | "Memory Avail: 1.23 GB / 8.00 GB (15.3%)\n", |
||
| 1685 | "Disk Space Avail: 14.94 GB / 228.27 GB (6.5%)\n", |
||
| 1686 | "===================================================\n", |
||
| 1687 | "Train Data Rows: 10793\n", |
||
| 1688 | "Train Data Columns: 34\n", |
||
| 1689 | "Label Column: NObeyesdad\n", |
||
| 1690 | "AutoGluon infers your prediction problem is: 'multiclass' (because dtype of label-column == int, but few unique label-values observed).\n", |
||
| 1691 | "\t7 unique label values: [0, 3, 1, 6, 4, 2, 5]\n", |
||
| 1692 | "\tIf 'multiclass' is not the correct problem_type, please manually specify the problem_type parameter during predictor init (You may specify problem_type as one of: ['binary', 'multiclass', 'regression'])\n", |
||
| 1693 | "Problem Type: multiclass\n", |
||
| 1694 | "Preprocessing data ...\n", |
||
| 1695 | "Train Data Class Count: 7\n", |
||
| 1696 | "Using Feature Generators to preprocess the data ...\n", |
||
| 1697 | "Fitting AutoMLPipelineFeatureGenerator...\n", |
||
| 1698 | "\tAvailable Memory: 1252.16 MB\n", |
||
| 1699 | "\tTrain Data (Original) Memory Usage: 2.80 MB (0.2% of available memory)\n", |
||
| 1700 | "\tInferring data type of each feature based on column values. Set feature_metadata_in to manually specify special dtypes of the features.\n", |
||
| 1701 | "\tStage 1 Generators:\n", |
||
| 1702 | "\t\tFitting AsTypeFeatureGenerator...\n", |
||
| 1703 | "\t\t\tNote: Converting 10 features to boolean dtype as they only contain 2 unique values.\n", |
||
| 1704 | "\tStage 2 Generators:\n", |
||
| 1705 | "\t\tFitting FillNaFeatureGenerator...\n", |
||
| 1706 | "\tStage 3 Generators:\n", |
||
| 1707 | "\t\tFitting IdentityFeatureGenerator...\n", |
||
| 1708 | "\tStage 4 Generators:\n", |
||
| 1709 | "\t\tFitting DropUniqueFeatureGenerator...\n", |
||
| 1710 | "\tStage 5 Generators:\n", |
||
| 1711 | "\t\tFitting DropDuplicatesFeatureGenerator...\n", |
||
| 1712 | "\tUseless Original Features (Count: 1): ['Age^2']\n", |
||
| 1713 | "\t\tThese features carry no predictive signal and should be manually investigated.\n", |
||
| 1714 | "\t\tThis is typically a feature which has the same value for all rows.\n", |
||
| 1715 | "\t\tThese features do not need to be present at inference time.\n", |
||
| 1716 | "\tUnused Original Features (Count: 2): ['Age^3', 'BMI^2']\n", |
||
| 1717 | "\t\tThese features were not used to generate any of the output features. Add a feature generator compatible with these features to utilize them.\n", |
||
| 1718 | "\t\tFeatures can also be unused if they carry very little information, such as being categorical but having almost entirely unique values or being duplicates of other features.\n", |
||
| 1719 | "\t\tThese features do not need to be present at inference time.\n", |
||
| 1720 | "\t\t('float', []) : 2 | ['Age^3', 'BMI^2']\n", |
||
| 1721 | "\tTypes of features in original data (raw dtype, special dtypes):\n", |
||
| 1722 | "\t\t('float', []) : 18 | ['Age', 'Height', 'Weight', 'FCVC', 'NCP', ...]\n", |
||
| 1723 | "\t\t('int', []) : 13 | ['Gender', 'family_history_with_overweight', 'FAVC', 'CAEC', 'SMOKE', ...]\n", |
||
| 1724 | "\tTypes of features in processed data (raw dtype, special dtypes):\n", |
||
| 1725 | "\t\t('float', []) : 18 | ['Age', 'Height', 'Weight', 'FCVC', 'NCP', ...]\n", |
||
| 1726 | "\t\t('int', []) : 3 | ['CAEC', 'CALC', 'Age_Group']\n", |
||
| 1727 | "\t\t('int', ['bool']) : 10 | ['Gender', 'family_history_with_overweight', 'FAVC', 'SMOKE', 'SCC', ...]\n", |
||
| 1728 | "\t0.6s = Fit runtime\n", |
||
| 1729 | "\t31 features in original data used to generate 31 features in processed data.\n", |
||
| 1730 | "\tTrain Data (Processed) Memory Usage: 1.83 MB (0.1% of available memory)\n", |
||
| 1731 | "Data preprocessing and feature engineering runtime = 0.67s ...\n", |
||
| 1732 | "AutoGluon will gauge predictive performance using evaluation metric: 'accuracy'\n", |
||
| 1733 | "\tTo change this, specify the eval_metric parameter of Predictor()\n", |
||
| 1734 | "Automatically generating train/validation split with holdout_frac=0.1, Train Rows: 9713, Val Rows: 1080\n", |
||
| 1735 | "User-specified model hyperparameters to be fit:\n", |
||
| 1736 | "{\n", |
||
| 1737 | "\t'NN_TORCH': {},\n", |
||
| 1738 | "\t'GBM': [{'extra_trees': True, 'ag_args': {'name_suffix': 'XT'}}, {}, 'GBMLarge'],\n", |
||
| 1739 | "\t'CAT': {},\n", |
||
| 1740 | "\t'XGB': {},\n", |
||
| 1741 | "\t'FASTAI': {},\n", |
||
| 1742 | "\t'RF': [{'criterion': 'gini', 'ag_args': {'name_suffix': 'Gini', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'entropy', 'ag_args': {'name_suffix': 'Entr', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'squared_error', 'ag_args': {'name_suffix': 'MSE', 'problem_types': ['regression', 'quantile']}}],\n", |
||
| 1743 | "\t'XT': [{'criterion': 'gini', 'ag_args': {'name_suffix': 'Gini', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'entropy', 'ag_args': {'name_suffix': 'Entr', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'squared_error', 'ag_args': {'name_suffix': 'MSE', 'problem_types': ['regression', 'quantile']}}],\n", |
||
| 1744 | "\t'KNN': [{'weights': 'uniform', 'ag_args': {'name_suffix': 'Unif'}}, {'weights': 'distance', 'ag_args': {'name_suffix': 'Dist'}}],\n", |
||
| 1745 | "}\n", |
||
| 1746 | "Fitting 13 L1 models ...\n", |
||
| 1747 | "Fitting model: KNeighborsUnif ...\n", |
||
| 1748 | "\tWarning: Exception caused KNeighborsUnif to fail during training... Skipping this model.\n", |
||
| 1749 | "\t\t'NoneType' object has no attribute 'split'\n", |
||
| 1750 | "Detailed Traceback:\n", |
||
| 1751 | "Traceback (most recent call last):\n", |
||
| 1752 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/core/trainer/abstract_trainer.py\", line 1926, in _train_and_save\n", |
||
| 1753 | " y_pred_proba_val = model.predict_proba(X_val)\n", |
||
| 1754 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/core/models/abstract/abstract_model.py\", line 950, in predict_proba\n", |
||
| 1755 | " y_pred_proba = self._predict_proba(X=X, **kwargs)\n", |
||
| 1756 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/core/models/abstract/abstract_model.py\", line 992, in _predict_proba\n", |
||
| 1757 | " y_pred_proba = self.model.predict_proba(X)\n", |
||
| 1758 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/sklearn/neighbors/_classification.py\", line 366, in predict_proba\n", |
||
| 1759 | " neigh_ind = self.kneighbors(X, return_distance=False)\n", |
||
| 1760 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/sklearn/neighbors/_base.py\", line 850, in kneighbors\n", |
||
| 1761 | " results = ArgKmin.compute(\n", |
||
| 1762 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/sklearn/metrics/_pairwise_distances_reduction/_dispatcher.py\", line 279, in compute\n", |
||
| 1763 | " return ArgKmin32.compute(\n", |
||
| 1764 | " File \"sklearn/metrics/_pairwise_distances_reduction/_argkmin.pyx\", line 575, in sklearn.metrics._pairwise_distances_reduction._argkmin.ArgKmin32.compute\n", |
||
| 1765 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/sklearn/utils/fixes.py\", line 94, in threadpool_limits\n", |
||
| 1766 | " return threadpoolctl.threadpool_limits(limits=limits, user_api=user_api)\n", |
||
| 1767 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 171, in __init__\n", |
||
| 1768 | " self._original_info = self._set_threadpool_limits()\n", |
||
| 1769 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 268, in _set_threadpool_limits\n", |
||
| 1770 | " modules = _ThreadpoolInfo(prefixes=self._prefixes,\n", |
||
| 1771 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 340, in __init__\n", |
||
| 1772 | " self._load_modules()\n", |
||
| 1773 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 371, in _load_modules\n", |
||
| 1774 | " self._find_modules_with_dyld()\n", |
||
| 1775 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 428, in _find_modules_with_dyld\n", |
||
| 1776 | " self._make_module_from_path(filepath)\n", |
||
| 1777 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 515, in _make_module_from_path\n", |
||
| 1778 | " module = module_class(filepath, prefix, user_api, internal_api)\n", |
||
| 1779 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 606, in __init__\n", |
||
| 1780 | " self.version = self.get_version()\n", |
||
| 1781 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 646, in get_version\n", |
||
| 1782 | " config = get_config().split()\n", |
||
| 1783 | "AttributeError: 'NoneType' object has no attribute 'split'\n", |
||
| 1784 | "Fitting model: KNeighborsDist ...\n", |
||
| 1785 | "\tWarning: Exception caused KNeighborsDist to fail during training... Skipping this model.\n", |
||
| 1786 | "\t\t'NoneType' object has no attribute 'split'\n", |
||
| 1787 | "Detailed Traceback:\n", |
||
| 1788 | "Traceback (most recent call last):\n", |
||
| 1789 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/core/trainer/abstract_trainer.py\", line 1926, in _train_and_save\n", |
||
| 1790 | " y_pred_proba_val = model.predict_proba(X_val)\n", |
||
| 1791 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/core/models/abstract/abstract_model.py\", line 950, in predict_proba\n", |
||
| 1792 | " y_pred_proba = self._predict_proba(X=X, **kwargs)\n", |
||
| 1793 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/core/models/abstract/abstract_model.py\", line 992, in _predict_proba\n", |
||
| 1794 | " y_pred_proba = self.model.predict_proba(X)\n", |
||
| 1795 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/sklearn/neighbors/_classification.py\", line 369, in predict_proba\n", |
||
| 1796 | " neigh_dist, neigh_ind = self.kneighbors(X)\n", |
||
| 1797 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/sklearn/neighbors/_base.py\", line 850, in kneighbors\n", |
||
| 1798 | " results = ArgKmin.compute(\n", |
||
| 1799 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/sklearn/metrics/_pairwise_distances_reduction/_dispatcher.py\", line 279, in compute\n", |
||
| 1800 | " return ArgKmin32.compute(\n", |
||
| 1801 | " File \"sklearn/metrics/_pairwise_distances_reduction/_argkmin.pyx\", line 575, in sklearn.metrics._pairwise_distances_reduction._argkmin.ArgKmin32.compute\n", |
||
| 1802 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/sklearn/utils/fixes.py\", line 94, in threadpool_limits\n", |
||
| 1803 | " return threadpoolctl.threadpool_limits(limits=limits, user_api=user_api)\n", |
||
| 1804 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 171, in __init__\n", |
||
| 1805 | " self._original_info = self._set_threadpool_limits()\n", |
||
| 1806 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 268, in _set_threadpool_limits\n", |
||
| 1807 | " modules = _ThreadpoolInfo(prefixes=self._prefixes,\n", |
||
| 1808 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 340, in __init__\n", |
||
| 1809 | " self._load_modules()\n", |
||
| 1810 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 371, in _load_modules\n", |
||
| 1811 | " self._find_modules_with_dyld()\n", |
||
| 1812 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 428, in _find_modules_with_dyld\n", |
||
| 1813 | " self._make_module_from_path(filepath)\n", |
||
| 1814 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 515, in _make_module_from_path\n", |
||
| 1815 | " module = module_class(filepath, prefix, user_api, internal_api)\n", |
||
| 1816 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 606, in __init__\n", |
||
| 1817 | " self.version = self.get_version()\n", |
||
| 1818 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/threadpoolctl.py\", line 646, in get_version\n", |
||
| 1819 | " config = get_config().split()\n", |
||
| 1820 | "AttributeError: 'NoneType' object has no attribute 'split'\n", |
||
| 1821 | "Fitting model: NeuralNetFastAI ...\n", |
||
| 1822 | "\t0.8944\t = Validation score (accuracy)\n", |
||
| 1823 | "\t8.91s\t = Training runtime\n", |
||
| 1824 | "\t0.03s\t = Validation runtime\n", |
||
| 1825 | "Fitting model: LightGBMXT ...\n", |
||
| 1826 | "\t0.9148\t = Validation score (accuracy)\n", |
||
| 1827 | "\t17.49s\t = Training runtime\n", |
||
| 1828 | "\t0.03s\t = Validation runtime\n", |
||
| 1829 | "Fitting model: LightGBM ...\n", |
||
| 1830 | "\t0.9139\t = Validation score (accuracy)\n", |
||
| 1831 | "\t28.87s\t = Training runtime\n", |
||
| 1832 | "\t0.05s\t = Validation runtime\n", |
||
| 1833 | "Fitting model: RandomForestGini ...\n", |
||
| 1834 | "\t0.9093\t = Validation score (accuracy)\n", |
||
| 1835 | "\t2.86s\t = Training runtime\n", |
||
| 1836 | "\t0.08s\t = Validation runtime\n", |
||
| 1837 | "Fitting model: RandomForestEntr ...\n", |
||
| 1838 | "\t0.9028\t = Validation score (accuracy)\n", |
||
| 1839 | "\t2.62s\t = Training runtime\n", |
||
| 1840 | "\t0.08s\t = Validation runtime\n", |
||
| 1841 | "Fitting model: CatBoost ...\n", |
||
| 1842 | "\t0.9102\t = Validation score (accuracy)\n", |
||
| 1843 | "\t12.96s\t = Training runtime\n", |
||
| 1844 | "\t0.01s\t = Validation runtime\n", |
||
| 1845 | "Fitting model: ExtraTreesGini ...\n", |
||
| 1846 | "\t0.9065\t = Validation score (accuracy)\n", |
||
| 1847 | "\t1.1s\t = Training runtime\n", |
||
| 1848 | "\t0.09s\t = Validation runtime\n", |
||
| 1849 | "Fitting model: ExtraTreesEntr ...\n", |
||
| 1850 | "\t0.9083\t = Validation score (accuracy)\n", |
||
| 1851 | "\t0.94s\t = Training runtime\n", |
||
| 1852 | "\t0.06s\t = Validation runtime\n", |
||
| 1853 | "Fitting model: XGBoost ...\n", |
||
| 1854 | "\t0.9111\t = Validation score (accuracy)\n", |
||
| 1855 | "\t15.38s\t = Training runtime\n", |
||
| 1856 | "\t0.05s\t = Validation runtime\n", |
||
| 1857 | "Fitting model: NeuralNetTorch ...\n", |
||
| 1858 | "\tWarning: Exception caused NeuralNetTorch to fail during training... Skipping this model.\n", |
||
| 1859 | "\t\tmodule 'torch.utils._pytree' has no attribute 'register_pytree_node'\n", |
||
| 1860 | "Detailed Traceback:\n", |
||
| 1861 | "Traceback (most recent call last):\n", |
||
| 1862 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/core/trainer/abstract_trainer.py\", line 1904, in _train_and_save\n", |
||
| 1863 | " model = self._train_single(X, y, model, X_val, y_val, total_resources=total_resources, **model_fit_kwargs)\n", |
||
| 1864 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/core/trainer/abstract_trainer.py\", line 1844, in _train_single\n", |
||
| 1865 | " model = model.fit(X=X, y=y, X_val=X_val, y_val=y_val, total_resources=total_resources, **model_fit_kwargs)\n", |
||
| 1866 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/core/models/abstract/abstract_model.py\", line 855, in fit\n", |
||
| 1867 | " out = self._fit(**kwargs)\n", |
||
| 1868 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/tabular/models/tabular_nn/torch/tabular_nn_torch.py\", line 196, in _fit\n", |
||
| 1869 | " self.optimizer = self._init_optimizer(**optimizer_kwargs)\n", |
||
| 1870 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/autogluon/tabular/models/tabular_nn/torch/tabular_nn_torch.py\", line 553, in _init_optimizer\n", |
||
| 1871 | " optimizer = torch.optim.Adam(params=self.model.parameters(), lr=learning_rate, weight_decay=weight_decay)\n", |
||
| 1872 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/optim/adam.py\", line 45, in __init__\n", |
||
| 1873 | " super().__init__(params, defaults)\n", |
||
| 1874 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/optim/optimizer.py\", line 266, in __init__\n", |
||
| 1875 | " self.add_param_group(cast(dict, param_group))\n", |
||
| 1876 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/_compile.py\", line 22, in inner\n", |
||
| 1877 | " import torch._dynamo\n", |
||
| 1878 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/_dynamo/__init__.py\", line 2, in <module>\n", |
||
| 1879 | " from . import allowed_functions, convert_frame, eval_frame, resume_execution\n", |
||
| 1880 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/_dynamo/allowed_functions.py\", line 26, in <module>\n", |
||
| 1881 | " from . import config\n", |
||
| 1882 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/_dynamo/config.py\", line 49, in <module>\n", |
||
| 1883 | " torch.onnx.is_in_onnx_export: False,\n", |
||
| 1884 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/__init__.py\", line 1831, in __getattr__\n", |
||
| 1885 | " return importlib.import_module(f\".{name}\", __name__)\n", |
||
| 1886 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/importlib/__init__.py\", line 126, in import_module\n", |
||
| 1887 | " return _bootstrap._gcd_import(name[level:], package, level)\n", |
||
| 1888 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/onnx/__init__.py\", line 46, in <module>\n", |
||
| 1889 | " from ._internal.exporter import ( # usort:skip. needs to be last to avoid circular import\n", |
||
| 1890 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/onnx/_internal/exporter.py\", line 42, in <module>\n", |
||
| 1891 | " from torch.onnx._internal.fx import (\n", |
||
| 1892 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/onnx/_internal/fx/__init__.py\", line 1, in <module>\n", |
||
| 1893 | " from .patcher import ONNXTorchPatcher\n", |
||
| 1894 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/torch/onnx/_internal/fx/patcher.py\", line 11, in <module>\n", |
||
| 1895 | " import transformers # type: ignore[import]\n", |
||
| 1896 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/transformers/__init__.py\", line 26, in <module>\n", |
||
| 1897 | " from . import dependency_versions_check\n", |
||
| 1898 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/transformers/dependency_versions_check.py\", line 16, in <module>\n", |
||
| 1899 | " from .utils.versions import require_version, require_version_core\n", |
||
| 1900 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/transformers/utils/__init__.py\", line 33, in <module>\n", |
||
| 1901 | " from .generic import (\n", |
||
| 1902 | " File \"/Users/arham/anaconda3/envs/DataScience/lib/python3.10/site-packages/transformers/utils/generic.py\", line 455, in <module>\n", |
||
| 1903 | " _torch_pytree.register_pytree_node(\n", |
||
| 1904 | "AttributeError: module 'torch.utils._pytree' has no attribute 'register_pytree_node'. Did you mean: '_register_pytree_node'?\n", |
||
| 1905 | "Fitting model: LightGBMLarge ...\n", |
||
| 1906 | "\t0.913\t = Validation score (accuracy)\n", |
||
| 1907 | "\t95.73s\t = Training runtime\n", |
||
| 1908 | "\t0.23s\t = Validation runtime\n", |
||
| 1909 | "Fitting model: WeightedEnsemble_L2 ...\n", |
||
| 1910 | "\tEnsemble Weights: {'ExtraTreesGini': 0.286, 'NeuralNetFastAI': 0.19, 'LightGBMXT': 0.19, 'CatBoost': 0.143, 'XGBoost': 0.143, 'LightGBMLarge': 0.048}\n", |
||
| 1911 | "\t0.9204\t = Validation score (accuracy)\n", |
||
| 1912 | "\t0.21s\t = Training runtime\n", |
||
| 1913 | "\t0.0s\t = Validation runtime\n", |
||
| 1914 | "AutoGluon training complete, total runtime = 194.17s ... Best model: \"WeightedEnsemble_L2\"\n", |
||
| 1915 | "TabularPredictor saved. To load, use: predictor = TabularPredictor.load(\"AutogluonModels/ag-20240426_052138\")\n" |
||
| 1916 | ] |
||
| 1917 | }, |
||
| 1918 | { |
||
| 1919 | "name": "stdout", |
||
| 1920 | "output_type": "stream", |
||
| 1921 | "text": [ |
||
| 1922 | "Recall for class 0: 0.9335443037974683\n", |
||
| 1923 | "Recall for class 1: 0.8983957219251337\n", |
||
| 1924 | "Recall for class 2: 0.7582089552238805\n", |
||
| 1925 | "Recall for class 3: 0.8389057750759878\n", |
||
| 1926 | "Recall for class 4: 0.8646080760095012\n", |
||
| 1927 | "Recall for class 5: 0.9641148325358851\n", |
||
| 1928 | "Recall for class 6: 0.9960474308300395\n" |
||
| 1929 | ] |
||
| 1930 | } |
||
| 1931 | ], |
||
| 1932 | "source": [ |
||
| 1933 | "from autogluon.tabular import TabularDataset, TabularPredictor\n", |
||
| 1934 | "from sklearn.metrics import precision_recall_fscore_support\n", |
||
| 1935 | "import mlflow\n", |
||
| 1936 | "\n", |
||
| 1937 | "# Load your data into AutoGluon TabularDataset format\n", |
||
| 1938 | "train_data = TabularDataset(X_train.join(y_train))\n", |
||
| 1939 | "val_data = TabularDataset(X_val.join(y_val))\n", |
||
| 1940 | "\n", |
||
| 1941 | "# Define the label column\n", |
||
| 1942 | "label_column = Target # Replace 'Target' with your actual label column name\n", |
||
| 1943 | "\n", |
||
| 1944 | "# Specify the task and run AutoGluon\n", |
||
| 1945 | "predictor = TabularPredictor(label=label_column).fit(train_data=train_data)\n", |
||
| 1946 | "\n", |
||
| 1947 | "# Make predictions on the validation set\n", |
||
| 1948 | "y_val_pred_autogluon = predictor.predict(val_data.drop(columns=[label_column]))\n", |
||
| 1949 | "\n", |
||
| 1950 | "# Evaluate performance\n", |
||
| 1951 | "precision, recall, f1, support = precision_recall_fscore_support(y_val, y_val_pred_autogluon, average='weighted')\n", |
||
| 1952 | "\n", |
||
| 1953 | "# Log metrics and model using MLflow\n", |
||
| 1954 | "with mlflow.start_run(run_name=\"AutoGluon_Without_Feature_Engineering\"):\n", |
||
| 1955 | " # Log AutoGluon model\n", |
||
| 1956 | " mlflow.sklearn.log_model(predictor, \"autogluon_model\")\n", |
||
| 1957 | " \n", |
||
| 1958 | " # Log metrics\n", |
||
| 1959 | " mlflow.log_metric('accuracy', accuracy_score(y_val, y_val_pred_autogluon))\n", |
||
| 1960 | " mlflow.log_metric('precision', precision)\n", |
||
| 1961 | " mlflow.log_metric('recall', recall)\n", |
||
| 1962 | " mlflow.log_metric('f1', f1)\n", |
||
| 1963 | "\n", |
||
| 1964 | " # Log recall per class\n", |
||
| 1965 | " recall_per_class = recall_score(y_val, y_val_pred_autogluon, average=None)\n", |
||
| 1966 | " for i, recall_class in enumerate(recall_per_class):\n", |
||
| 1967 | " print(f\"Recall for class {i}: {recall_class}\")\n", |
||
| 1968 | " mlflow.log_metric(f'recall_class_{i}', recall_class)\n", |
||
| 1969 | "\n", |
||
| 1970 | " mlflow.set_tag('experiments', 'Arham A.')\n", |
||
| 1971 | " mlflow.set_tag('model_name', 'AutoGluon')\n", |
||
| 1972 | " mlflow.set_tag('preprocessing', 'Yes')\n" |
||
| 1973 | ] |
||
| 1974 | }, |
||
| 1975 | { |
||
| 1976 | "cell_type": "code", |
||
| 1977 | "execution_count": null, |
||
| 1978 | "metadata": {}, |
||
| 1979 | "outputs": [], |
||
| 1980 | "source": [] |
||
| 1981 | } |
||
| 1982 | ], |
||
| 1983 | "metadata": { |
||
| 1984 | "kernelspec": { |
||
| 1985 | "display_name": "DataScience", |
||
| 1986 | "language": "python", |
||
| 1987 | "name": "python3" |
||
| 1988 | }, |
||
| 1989 | "language_info": { |
||
| 1990 | "codemirror_mode": { |
||
| 1991 | "name": "ipython", |
||
| 1992 | "version": 3 |
||
| 1993 | }, |
||
| 1994 | "file_extension": ".py", |
||
| 1995 | "mimetype": "text/x-python", |
||
| 1996 | "name": "python", |
||
| 1997 | "nbconvert_exporter": "python", |
||
| 1998 | "pygments_lexer": "ipython3", |
||
| 1999 | "version": "3.10.13" |
||
| 2000 | } |
||
| 2001 | }, |
||
| 2002 | "nbformat": 4, |
||
| 2003 | "nbformat_minor": 2 |
||
| 2004 | } |