313 lines (312 with data), 12.9 kB

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Expeirment Setup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "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",
    "\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",
    "    return train_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",
    "    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",
    "    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"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Code"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from pycaret.classification import *\n",
    "\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",
    "# Split data\n",
    "Target = 'NObeyesdad'\n",
    "features = ['Gender', 'Age', 'Height', 'Weight', 'family_history_with_overweight',\n",
    "            'FAVC', 'FCVC', 'NCP', 'CAEC', 'SMOKE', 'CH2O', 'SCC', 'FAF', 'TUE',\n",
    "            'CALC', 'Age_Group', '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",
    "            'Scaled_Age', 'Log_Age', 'Scaled_Weight', 'Log_Weight', 'Scaled_Height', 'Log_Height']\n",
    "\n",
    "train_data = train_df[features + [Target]]\n",
    "val_data = val_df[features + [Target]]\n",
    "test_data = test_df[features + [Target]]\n",
    "\n",
    "# Initialize PyCaret setup\n",
    "exp1 = setup(data=train_data, target=Target, session_id=123)\n",
    "\n",
    "# Compare models\n",
    "best_model = compare_models()\n",
    "\n",
    "# Tune model\n",
    "tuned_model = tune_model(best_model)\n",
    "\n",
    "# Finalize model\n",
    "final_model = finalize_model(tuned_model)\n",
    "\n",
    "# Save model\n",
    "save_model(final_model, 'model_name')\n",
    "\n",
    "# # load model\n",
    "# final_model = load_model('model_name')\n",
    "\n",
    "\n",
    "predictions = predict_model(final_model, data=val_data)\n",
    "\n",
    "predictions\n",
    "# # Evaluate performance\n",
    "from sklearn.metrics import precision_recall_fscore_support\n",
    "\n",
    "precision, recall, f1, support = precision_recall_fscore_support(predictions['NObeyesdad'], predictions['prediction_label'], average='weighted')\n",
    "print(f\"Precision: {precision}, Recall: {recall}, F1 Score: {f1}\")\n",
    "\n",
    "# Log performance metrics\n",
    "import mlflow\n",
    "with mlflow.start_run(run_name=\"PyCaret_With_Extended_Engineering\"):\n",
    "    # Log PyCaret model\n",
    "    mlflow.pyfunc.log_model(artifact_path=\"pycaret_model\", python_model=final_model)\n",
    "    \n",
    "    # Log metrics\n",
    "    mlflow.log_metric('accuracy', accuracy_score(predictions[Target], predictions['Label']))\n",
    "    mlflow.log_metric('precision', precision)\n",
    "    mlflow.log_metric('recall', recall)\n",
    "    mlflow.log_metric('f1', f1)\n",
    "\n",
    "    # Log recall per class\n",
    "    recall_per_class = recall_score(predictions['NObeyesdad'], predictions['prediction_label'], average=None)\n",
    "    for i, recall_class in enumerate(recall_per_class):\n",
    "        print(f\"Recall for class {i}: {recall_class}\")\n",
    "        mlflow.log_metric(f'recall_class_{i}', recall_class)\n",
    "\n",
    "    mlflow.set_tag('experiments', 'Arham A.')\n",
    "    mlflow.set_tag('model_name', 'PyCaret')\n",
    "    mlflow.set_tag('preprocessing', 'Yes')\n"
   ]
  }
 ],
 "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
}