import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.metrics import mean_squared_error, r2_score
# Load data
df = pd.read_csv("california_housing.csv")
# Split features and target variable
X = df.drop("MedHouseVal", axis=1)
y = df["MedHouseVal"]
# Split training and testing sets
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)
# Train gradient boosting regression model
model = GradientBoostingRegressor(
    n_estimators=200, max_depth=5, learning_rate=0.1, random_state=42
)
model.fit(X_train, y_train)
# Predict and evaluate
y_pred = model.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)
print(f"Mean Squared Error (MSE): {mse:.4f}")
print(f"R² Score: {r2:.4f}")