# train_rf.py
import pandas as pd
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
import joblib
import os

# Sample dataset
X = [[1], [2], [3], [4], [5], [6], [7], [8], [9], [10]]
y = [35, 45, 55, 65, 75, 80, 82, 88, 92, 95]

# Convert to DataFrame
df = pd.DataFrame(X, columns=['Hours'])
df['Score'] = y

# Split data
X_train, X_test, y_train, y_test = train_test_split(df[['Hours']], df['Score'], test_size=0.2, random_state=42)

# Train model
model = RandomForestRegressor(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

# Save the model
os.makedirs('Models', exist_ok=True)
joblib.dump(model, 'Models/rf_model.pkl')
print("✅ Random Forest Regressor trained and saved.")