Datasets
Models
Downloads: 1
442 lines (441 with data), 18.8 kB
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Global Experiment Setup"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Experiment: artifact_location='/Users/arham/Downloads/Projects/03-Experiments/mlruns/2', creation_time=1713912394972, experiment_id='2', last_update_time=1713912394972, lifecycle_stage='active', name='XGBoost', tags={}>"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import mlflow\n",
"\n",
"\n",
"# Set the MLflow tracking URI to a new SQLite URI\n",
"mlflow.set_tracking_uri(\"sqlite:///new_mlflow.db\")\n",
"mlflow.set_experiment(\"XGBoost\")"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from sklearn.model_selection import train_test_split\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"import numpy as np\n",
"from sklearn.preprocessing import MinMaxScaler\n",
"from sklearn.preprocessing import PolynomialFeatures\n",
"import lightgbm as lgb\n",
"from sklearn.metrics import accuracy_score\n",
"import warnings\n",
"from sklearn.tree import DecisionTreeClassifier\n",
"from sklearn.model_selection import cross_val_score\n",
"from sklearn.metrics import accuracy_score, precision_score, recall_score\n",
"import xgboost as xgb\n",
"from sklearn.metrics import accuracy_score, precision_score, recall_score\n",
"from sklearn.model_selection import cross_val_score\n",
"\n",
"\n",
"def load_data(path):\n",
" df = pd.read_csv(path)\n",
" train_df, test_df = train_test_split(df, test_size=0.35, random_state=42)\n",
" train_df, val_df, = train_test_split(train_df, test_size=0.20, random_state=42)\n",
" train_df = train_df.drop(['id'], axis=1).drop_duplicates().reset_index(drop=True)\n",
" test_df = test_df.drop(['id'], axis=1).drop_duplicates().reset_index(drop=True)\n",
" val_df = val_df.drop(['id'], axis=1).drop_duplicates().reset_index(drop=True)\n",
" return train_df, val_df, test_df\n",
"\n",
"def encode_target(train):\n",
" 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",
" train['NObeyesdad'] = train['NObeyesdad'].map(target_key)\n",
" return train\n",
"\n",
"def make_gender_binary(train):\n",
" train['Gender'] = train['Gender'].map({'Male':0, 'Female':1})\n",
"\n",
"def datatypes(train):\n",
" train['Weight'] = train['Weight'].astype(float)\n",
" train['Age'] = train['Age'].astype(float)\n",
" train['Height'] = train['Height'].astype(float)\n",
" return train\n",
"\n",
"# def age_binning(train_df):\n",
"# # 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",
"# 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",
"# train_df['Age_Group'] = train_df['Age_Group'].astype(int)\n",
"# return train_df\n",
"\n",
"def age_binning(df):\n",
" age_groups = []\n",
" for age in df['Age']:\n",
" if age <= 20:\n",
" age_group = 1\n",
" elif age <= 30:\n",
" age_group = 2\n",
" elif age <= 40:\n",
" age_group = 3\n",
" elif age <= 50:\n",
" age_group = 4\n",
" else:\n",
" age_group = 5\n",
" age_groups.append(age_group)\n",
" df['Age_Group'] = age_groups\n",
" return df\n",
"\n",
"def age_scaling_log(train_df):\n",
" train_df['Age'] = train_df['Age'].astype(float)\n",
" train_df['Log_Age'] = np.log1p(train_df['Age'])\n",
" return train_df\n",
"\n",
"def age_scaling_minmax(train_df):\n",
" train_df['Age'] = train_df['Age'].astype(float)\n",
" scaler_age = MinMaxScaler()\n",
" train_df['Scaled_Age'] = scaler_age.fit_transform(train_df['Age'].values.reshape(-1, 1))\n",
" return train_df, scaler_age\n",
"\n",
"def weight_scaling_log(train_df):\n",
" train_df['Weight'] = train_df['Weight'].astype(float)\n",
" train_df['Log_Weight'] = np.log1p(train_df['Weight'])\n",
" return train_df\n",
"\n",
"def weight_scaling_minmax(train_df):\n",
" train_df['Weight'] = train_df['Weight'].astype(float)\n",
" scaler_weight = MinMaxScaler()\n",
" train_df['Scaled_Weight'] = scaler_weight.fit_transform(train_df['Weight'].values.reshape(-1, 1))\n",
" return train_df, scaler_weight\n",
"\n",
"def height_scaling_log(train_df):\n",
" train_df['Log_Height'] = np.log1p(train_df['Height'])\n",
" return train_df\n",
"\n",
"def height_scaling_minmax(train_df):\n",
" scaler_height = MinMaxScaler()\n",
" train_df['Scaled_Height'] = scaler_height.fit_transform(train_df['Height'].values.reshape(-1, 1))\n",
" return train_df, scaler_height\n",
"\n",
"def make_gender_binary(train):\n",
" train['Gender'] = train['Gender'].map({'Female':1, 'Male':0})\n",
" return train\n",
"\n",
"def fix_binary_columns(train):\n",
" Binary_Cols = ['family_history_with_overweight','FAVC', 'SCC','SMOKE']\n",
" # if yes then 1 else 0\n",
" for col in Binary_Cols:\n",
" train[col] = train[col].map({'yes': 1, 'no': 0})\n",
" # column datatype integer\n",
" train[col] = train[col].astype(int)\n",
" return train\n",
"\n",
"def freq_cat_cols(train):\n",
" # One hot encoding\n",
" cat_cols = ['CAEC', 'CALC']\n",
" for col in cat_cols:\n",
" train[col] = train[col].map({'no': 0, 'Sometimes': 1, 'Frequently': 2, 'Always': 3})\n",
" return train\n",
"\n",
"def Mtrans(train):\n",
" \"\"\"\n",
" Public_Transportation 8692\n",
" Automobile 1835\n",
" Walking 231\n",
" Motorbike 19\n",
" Bike 16\n",
" \"\"\"\n",
" # train['MTRANS'] = train['MTRANS'].map({'Public_Transportation': 3, 'Automobile': 5, 'Walking': 1, 'Motorbike': 4, 'Bike': 2})\n",
" # dummify column\n",
" train = pd.get_dummies(train, columns=['MTRANS'])\n",
" # convert these columns to integer\n",
" train['MTRANS_Automobile'] = train['MTRANS_Automobile'].astype(int)\n",
" train['MTRANS_Walking'] = train['MTRANS_Walking'].astype(int)\n",
" train['MTRANS_Motorbike'] = train['MTRANS_Motorbike'].astype(int)\n",
" train['MTRANS_Bike'] = train['MTRANS_Bike'].astype(int)\n",
" train['MTRANS_Public_Transportation'] = train['MTRANS_Public_Transportation'].astype(int)\n",
" return train\n",
"\n",
"\n",
"def other_features(train):\n",
" train['BMI'] = train['Weight'] / (train['Height'] ** 2)\n",
" # train['Age'*'Gender'] = train['Age'] * train['Gender']\n",
" polynomial_features = PolynomialFeatures(degree=2)\n",
" X_poly = polynomial_features.fit_transform(train[['Age', 'BMI']])\n",
" poly_features_df = pd.DataFrame(X_poly, columns=['Age^2', 'Age^3', 'BMI^2', 'Age * BMI', 'Age * BMI^2', 'Age^2 * BMI^2'])\n",
" train = pd.concat([train, poly_features_df], axis=1)\n",
" return train\n",
"\n",
"\n",
"def test_pipeline(test, scaler_age, scaler_weight, scaler_height):\n",
" test = datatypes(test)\n",
" test = encode_target(test)\n",
" test = age_binning(test)\n",
" test = age_scaling_log(test)\n",
" test['Scaled_Age'] = scaler_age.transform(test['Age'].values.reshape(-1, 1))\n",
" test = weight_scaling_log(test)\n",
" test['Scaled_Weight'] = scaler_weight.transform(test['Weight'].values.reshape(-1, 1))\n",
" test = height_scaling_log(test)\n",
" test['Scaled_Height'] = scaler_height.transform(test['Height'].values.reshape(-1, 1))\n",
" test = make_gender_binary(test)\n",
" test = fix_binary_columns(test)\n",
" test = freq_cat_cols(test)\n",
" test = Mtrans(test)\n",
" test = other_features(test)\n",
"\n",
" return test\n",
"\n",
"def train_model(params, X_train, y_train):\n",
" lgb_train = lgb.Dataset(X_train, y_train)\n",
" model = lgb.train(params, lgb_train, num_boost_round=1000)\n",
" return model\n",
"\n",
"def evaluate_model(model, X_val, y_val):\n",
" y_pred = model.predict(X_val)\n",
" y_pred = [np.argmax(y) for y in y_pred]\n",
" accuracy = accuracy_score(y_val, y_pred)\n",
" return accuracy\n",
"\n",
"def objective(trial, X_train, y_train):\n",
" params = {\n",
" 'objective': 'multiclass',\n",
" 'num_class': 7,\n",
" 'metric': 'multi_logloss',\n",
" 'boosting_type': 'gbdt',\n",
" 'learning_rate': trial.suggest_loguniform('learning_rate', 0.005, 0.5),\n",
" 'num_leaves': trial.suggest_int('num_leaves', 10, 1000),\n",
" 'max_depth': trial.suggest_int('max_depth', -1, 20),\n",
" 'bagging_fraction': trial.suggest_uniform('bagging_fraction', 0.6, 0.95),\n",
" 'feature_fraction': trial.suggest_uniform('feature_fraction', 0.6, 0.95),\n",
" 'verbosity': -1\n",
" }\n",
"\n",
" n_splits = 5\n",
" kf = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=42)\n",
" scores = []\n",
"\n",
" for train_index, val_index in kf.split(X_train, y_train):\n",
" X_tr, X_val = X_train.iloc[train_index], X_train.iloc[val_index]\n",
" y_tr, y_val = y_train.iloc[train_index], y_train.iloc[val_index]\n",
"\n",
" model = train_model(params, X_tr, y_tr)\n",
" accuracy = evaluate_model(model, X_val, y_val)\n",
" scores.append(accuracy)\n",
"\n",
" return np.mean(scores)\n",
"\n",
"def optimize_hyperparameters(X_train, y_train, n_trials=2):\n",
" study = optuna.create_study(direction='maximize')\n",
" study.optimize(lambda trial: objective(trial, X_train, y_train), n_trials=n_trials)\n",
" return study.best_params\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### XGB With Feature Engineering"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"\n",
"path = '/Users/arham/Downloads/Projects/01-Dataset/01-Data-for-model-building/train.csv'\n",
"train_df, val_df, test_df = load_data(path)\n",
"\n",
"train_df = datatypes(train_df)\n",
"train_df = encode_target(train_df)\n",
"train_df = age_binning(train_df)\n",
"train_df, scaler_age = age_scaling_minmax(train_df)\n",
"train_df = age_scaling_log(train_df)\n",
"train_df, scaler_weight = weight_scaling_minmax(train_df)\n",
"train_df = weight_scaling_log(train_df)\n",
"train_df, scaler_height = height_scaling_minmax(train_df)\n",
"train_df = height_scaling_log(train_df)\n",
"train_df = make_gender_binary(train_df)\n",
"train_df = fix_binary_columns(train_df)\n",
"train_df = freq_cat_cols(train_df)\n",
"train_df = Mtrans(train_df)\n",
"train_df = other_features(train_df)\n",
"\n",
"val_df = test_pipeline(val_df, scaler_age, scaler_weight, scaler_height)\n",
"test_df = test_pipeline(test_df, scaler_age, scaler_weight, scaler_height)\n",
"\n",
"Target = 'NObeyesdad'\n",
"# features = train_df.columns.drop(Target)\n",
"features = ['Gender', 'Age', 'Height', 'Weight', 'family_history_with_overweight',\n",
" 'FAVC', 'FCVC', 'NCP', 'CAEC', 'SMOKE', 'CH2O', 'SCC', 'FAF', 'TUE',\n",
" 'CALC', 'Age_Group', \n",
" 'MTRANS_Automobile', 'MTRANS_Bike', 'MTRANS_Motorbike',\n",
" 'MTRANS_Public_Transportation', 'MTRANS_Walking', 'BMI', 'Age^2',\n",
" 'Age^3', 'BMI^2', 'Age * BMI', 'Age * BMI^2', 'Age^2 * BMI^2'] \n",
"\n",
" #'Scaled_Age', 'Log_Age', 'Scaled_Weight', 'Log_Weight', 'Scaled_Height', 'Log_Height',\n",
"\n",
"\n",
"X_train = train_df[features]\n",
"y_train = train_df[Target]\n",
"X_val = val_df[features]\n",
"y_val = val_df[Target]\n",
"X_test = test_df[features]\n",
"y_test = test_df[Target]\n",
"\n",
"# save X_train, y_train, X_val, X_test, y_test\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Target Drift For Each Class [0.004943133623686147, 0.011990707821925795, -0.0087675011457998, -0.001077949504617301, -0.017190035106736085, -0.00032756263090533144, 0.01042920694244659]\n",
"Cross-validation Scores (XGBoost): [0.90597499 0.90736452 0.89671144 0.89620019 0.90222428]\n",
"Mean CV Accuracy (XGBoost): 0.9016950833225661\n",
"\n",
"Accuracy (XGBoost): 0.9036680251945165\n",
"Precision (XGBoost): 0.9042803910684232\n",
"Recall (XGBoost): 0.9036680251945165\n",
"F1 (XGBoost): 0.9039741044249812\n",
"Recall for class 0: 0.9240506329113924\n",
"Recall for class 1: 0.9064171122994652\n",
"Recall for class 2: 0.7582089552238805\n",
"Recall for class 3: 0.8449848024316109\n",
"Recall for class 4: 0.8741092636579573\n",
"Recall for class 5: 0.9665071770334929\n",
"Recall for class 6: 0.9960474308300395\n"
]
}
],
"source": [
"\n",
"import xgboost as xgb\n",
"from sklearn.model_selection import cross_val_score\n",
"from sklearn.metrics import accuracy_score, precision_score, recall_score\n",
"import mlflow\n",
"import warnings\n",
"warnings.filterwarnings(\"ignore\")\n",
"# import precision_recall_fscore_support\n",
"from sklearn.metrics import precision_recall_fscore_support\n",
"\n",
"mlflow.sklearn.autolog(disable=True)\n",
"\n",
"with mlflow.start_run(run_name=\"XGB_with_Feature_Engineering\"):\n",
" class_counts_train = [y_train[y_train == i].count() / y_train.count() for i in range(7)]\n",
" class_counts_val = [y_val[y_val == i].count() / y_val.count() for i in range(7)]\n",
" target_drift = [(train_count - val_count) for train_count, val_count in zip(class_counts_train, class_counts_val)]\n",
" print(f\"Target Drift For Each Class {target_drift}\")\n",
" mlflow.log_params({'Target_Drift_' + str(i): freq for i, freq in enumerate(target_drift)})\n",
"\n",
" xgb_classifier = xgb.XGBClassifier()\n",
" cv_scores_xgb = cross_val_score(xgb_classifier, X_train, y_train, cv=5, scoring='accuracy')\n",
" print(\"Cross-validation Scores (XGBoost):\", cv_scores_xgb)\n",
" print(\"Mean CV Accuracy (XGBoost):\", cv_scores_xgb.mean())\n",
" xgb_classifier.fit(X_train, y_train)\n",
" y_val_pred_xgb = xgb_classifier.predict(X_val)\n",
" accuracy_xgb = accuracy_score(y_val, y_val_pred_xgb)\n",
" precision_xgb = precision_score(y_val, y_val_pred_xgb, average='weighted')\n",
" recall_xgb = recall_score(y_val, y_val_pred_xgb, average='weighted')\n",
" f1_xgb = 2 * (precision_xgb * recall_xgb) / (precision_xgb + recall_xgb)\n",
" print(\"\\nAccuracy (XGBoost):\", accuracy_xgb)\n",
" print(\"Precision (XGBoost):\", precision_xgb)\n",
" print(\"Recall (XGBoost):\", recall_xgb)\n",
" print(\"F1 (XGBoost):\", f1_xgb)\n",
" mlflow.log_metric('accuracy', accuracy_xgb)\n",
" mlflow.log_metric('precision', precision_xgb)\n",
" mlflow.log_metric('recall', recall_xgb)\n",
" mlflow.log_metric('f1', f1_xgb)\n",
"\n",
" precision_per_class, recall_per_class, f1_per_class, support_per_class = precision_recall_fscore_support(y_val, y_val_pred_xgb, average=None)\n",
" for i in range(len(recall_per_class)):\n",
" print(f\"Recall for class {i}: {recall_per_class[i]}\")\n",
" mlflow.log_metric(f'recall_class_{i}', recall_per_class[i])\n",
"\n",
" mlflow.xgboost.log_model(xgb_classifier, 'model')\n",
" mlflow.set_tag('experiments', 'Arham A.')\n",
" mlflow.set_tag('model_name', 'XGBoost')\n",
" mlflow.set_tag('preprocessing', 'Yes')\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2024-04-25 14:13:00 -0400] [8930] [INFO] Starting gunicorn 21.2.0\n",
"[2024-04-25 14:13:00 -0400] [8930] [INFO] Listening at: http://127.0.0.1:5000 (8930)\n",
"[2024-04-25 14:13:00 -0400] [8930] [INFO] Using worker: sync\n",
"[2024-04-25 14:13:00 -0400] [8931] [INFO] Booting worker with pid: 8931\n",
"[2024-04-25 14:13:01 -0400] [8932] [INFO] Booting worker with pid: 8932\n",
"[2024-04-25 14:13:01 -0400] [8933] [INFO] Booting worker with pid: 8933\n",
"[2024-04-25 14:13:01 -0400] [8934] [INFO] Booting worker with pid: 8934\n",
"^C\n",
"[2024-04-25 14:15:17 -0400] [8930] [INFO] Handling signal: int\n",
"[2024-04-25 14:15:18 -0400] [8934] [INFO] Worker exiting (pid: 8934)\n",
"[2024-04-25 14:15:18 -0400] [8933] [INFO] Worker exiting (pid: 8933)\n",
"[2024-04-25 14:15:18 -0400] [8932] [INFO] Worker exiting (pid: 8932)\n",
"[2024-04-25 14:15:18 -0400] [8931] [INFO] Worker exiting (pid: 8931)\n"
]
}
],
"source": [
"!mlflow ui --backend-store-uri \"sqlite:////Users/arham/Downloads/Projects/03-Experiments/new_mlflow.db\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "DataScience",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.13"
}
},
"nbformat": 4,
"nbformat_minor": 2
}