src/models/train.py

import mlflow
import mlflow.sklearn
import pandas as pd
from src.utils.mlflow_utils import setup_mlflow

from sklearn.pipeline import Pipeline
from sklearn.linear_model import LinearRegression, Ridge, Lasso
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error, r2_score

from src.models.prepare import prepare_data


def train_models(df: pd.DataFrame):

    X_train, X_test, y_train, y_test, preprocessor = prepare_data(df)

    models = {
        "LinearRegression": LinearRegression(),
        "Ridge": Ridge(),
        "Lasso": Lasso(),
        "RandomForest": RandomForestRegressor(random_state=42, n_jobs=-1)
    }


    setup_mlflow("AQI_Prediction")

    results = {}

    for name, model in models.items():

        with mlflow.start_run(run_name=name):

            pipeline = Pipeline([
                ("preprocessor", preprocessor),
                ("model", model)
            ])

            pipeline.fit(X_train, y_train)
            y_pred = pipeline.predict(X_test)

            rmse = mean_squared_error(y_test, y_pred)
            r2 = r2_score(y_test, y_pred)

            mlflow.log_param("model", name)
            mlflow.log_metric("rmse", rmse)
            mlflow.log_metric("r2_score", r2)

            mlflow.sklearn.log_model(pipeline, "model")

            results[name] = {"RMSE": rmse, "R2": r2}

            print(f"{name} → RMSE: {rmse:.2f}, R2: {r2:.4f}")

    return results