main.py

import warnings
warnings.filterwarnings("ignore")

from src.data.loader import load_data
from src.modeling.train import train_and_compare_models
from src.modeling.evaluate import evaluate_model
from src.visualization.plots import plot_feature_importance
from src.config import MODEL_DIR

def main():
    print("=== Student Placement Prediction ===")
    
    df = load_data()
    
    results_df, best = train_and_compare_models(df)
    
    if best["Model"] in ["RandomForest", "XGBoost"]:
        plot_feature_importance(best["Pipeline"], save_path=MODEL_DIR / "feature_importance.png")
    
    best_model_path = MODEL_DIR / f"{best['Model']}_pipeline.pkl"
    metrics = evaluate_model(df, model_path=best_model_path)
    
    print("\n✅ Training complete! Check 'models/' for saved artifacts.")
if __name__ == "__main__":
    main()