""" train_model.py ============== Trains a Random Forest Classifier to predict healthy vs unhealthy lifestyle status using the Sleep Health and Lifestyle dataset. Saves the trained pipeline model as lifestyle_model.pkl. """ import os import joblib import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from sklearn.ensemble import RandomForestClassifier from sklearn.compose import ColumnTransformer from sklearn.preprocessing import OrdinalEncoder from sklearn.pipeline import Pipeline from sklearn.metrics import accuracy_score, classification_report, confusion_matrix DATASET_PATH = "Sleep_health_and_lifestyle_dataset.csv" MODEL_PATH = "lifestyle_model.pkl" def load_and_preprocess_data(dataset_path: str): """Loads the dataset, engineer features and target variable.""" if not os.path.exists(dataset_path): raise FileNotFoundError(f"Dataset not found at {dataset_path}") print(f"Loading dataset from: {dataset_path} ...") df = pd.read_csv(dataset_path) print(f"Dataset shape: {df.shape}") # 1. Define Binary Target Variable 'Is_Healthy' # Healthy (1) if: # - Sleep Duration >= 7.0 hours (recommended minimum for adults) # - Quality of Sleep >= 7 (on 1-10 scale) # - Physical Activity Level >= 60 (minutes/day) # - Stress Level <= 5 (low to moderate stress) # Otherwise Unhealthy (0) df["Is_Healthy"] = ( (df["Sleep Duration"] >= 7.0) & (df["Quality of Sleep"] >= 7) & (df["Physical Activity Level"] >= 60) & (df["Stress Level"] <= 5) ).astype(int) target_counts = df["Is_Healthy"].value_counts().to_dict() print(f"Target distribution: 0 (Unhealthy): {target_counts.get(0, 0)}, 1 (Healthy): {target_counts.get(1, 0)}") # 2. Preprocess Blood Pressure into numeric Systolic_BP and Diastolic_BP df[["Systolic_BP", "Diastolic_BP"]] = ( df["Blood Pressure"].str.split("/", expand=True).astype(int) ) # 3. Exclude BMI Category (to keep features clean and unconfounded) # Also drop Person ID (identifier) and Sleep Disorder (outcome diagnosis with NaNs) feature_cols = [ "Gender", "Age", "Occupation", "Sleep Duration", "Quality of Sleep", "Physical Activity Level", "Stress Level", "Heart Rate", "Daily Steps", "Systolic_BP", "Diastolic_BP", ] X = df[feature_cols].copy() y = df["Is_Healthy"].copy() return X, y, feature_cols def build_pipeline(categorical_cols, numerical_cols): """Creates a Scikit-Learn Pipeline with preprocessor and RandomForestClassifier.""" preprocessor = ColumnTransformer( transformers=[ ( "cat", OrdinalEncoder( handle_unknown="use_encoded_value", unknown_value=-1 ), categorical_cols, ), ("num", "passthrough", numerical_cols), ] ) pipeline = Pipeline( steps=[ ("preprocessor", preprocessor), ( "classifier", RandomForestClassifier( n_estimators=100, max_depth=6, random_state=42, class_weight="balanced", ), ), ] ) return pipeline def main(): print("=" * 60) print(" Sleep Health & Lifestyle AI Classifier - Training Pipeline ") print("=" * 60) X, y, feature_cols = load_and_preprocess_data(DATASET_PATH) categorical_cols = ["Gender", "Occupation"] numerical_cols = [col for col in feature_cols if col not in categorical_cols] print(f"Categorical features: {categorical_cols}") print(f"Numerical features: {numerical_cols}") # Train / Test Split for Evaluation X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.2, random_state=42, stratify=y ) print(f"\nTraining set size: {len(X_train)} samples") print(f"Testing set size: {len(X_test)} samples") # Evaluate Model eval_pipeline = build_pipeline(categorical_cols, numerical_cols) eval_pipeline.fit(X_train, y_train) y_pred = eval_pipeline.predict(X_test) accuracy = accuracy_score(y_test, y_pred) print("\n" + "=" * 60) print(" EVALUATION RESULTS (Holdout Test Set) ") print("=" * 60) print(f"Accuracy Score: {accuracy * 100:.2f}%\n") print("Classification Report:") print( classification_report( y_test, y_pred, target_names=["Unhealthy (0)", "Healthy (1)"] ) ) print("Confusion Matrix:") print(confusion_matrix(y_test, y_pred)) # Train final model on full dataset for production deployment print("\n" + "=" * 60) print(" Training Final Model on Full Dataset for Deployment ") print("=" * 60) final_pipeline = build_pipeline(categorical_cols, numerical_cols) final_pipeline.fit(X, y) # Save trained pipeline model joblib.dump(final_pipeline, MODEL_PATH) print(f"Successfully saved trained model to: {MODEL_PATH}") # Verify model artifact can be reloaded loaded_model = joblib.load(MODEL_PATH) sample_pred = loaded_model.predict(X.iloc[:2]) print(f"Verification test prediction on first 2 samples: {sample_pred}") print("Model training and packaging completed successfully!") if __name__ == "__main__": main()