#!/usr/bin/env python
# coding: utf-8
import os
import json
import joblib
import numpy as np
from sklearn.ensemble import VotingRegressor
from sklearn.linear_model import LinearRegression
from sklearn.ensemble import RandomForestRegressor
from core.ndvi_data_loader import NDVITimeSeriesDataset

print("=" * 70)
print("🚀 Training Multi-Model Ensemble for NDVI (REAL DATA & CPU)")
print("=" * 70)

dataset = NDVITimeSeriesDataset(sequence_length=5, spatial=False)

X_train, y_train = [], []
for x, y in dataset:
    X_train.append(x.numpy().flatten())
    y_train.append(y.numpy().flatten()[0])

X_train = np.array(X_train)
y_train = np.array(y_train)

print(f"\n[TRAIN] Bắt đầu Training Ensemble trên {len(X_train)} samples...")
# CPU Ensemble
model1 = LinearRegression()
model2 = RandomForestRegressor(n_estimators=50, random_state=42)
ensemble = VotingRegressor([('lr', model1), ('rf', model2)])

ensemble.fit(X_train, y_train)

# Predict and calc error
preds = ensemble.predict(X_train)
mse = np.mean((preds - y_train)**2)

model_dir = "ndvi_forecast_model"
model_path = os.path.join(model_dir, "ndvi_ensemble_real.joblib")
joblib.dump(ensemble, model_path)
print(f"\n[SAVE] Model saved to {model_path}")

with open(os.path.join(model_dir, "ndvi_ensemble_real_info.json"), "w") as f:
    json.dump({
        "model_type": "Multi-Model Ensemble (Real Data & CPU)",
        "target": "NDVI",
        "rmse": float(mse**0.5),
        "mae": float(np.mean(np.abs(preds - y_train)))
    }, f, indent=2)
print("[SAVE] Model info saved.")