simple_xgboost_regression.py

from sklearn.model_selection import train_test_split

X = df.drop(columns=['median_house_value'])
y = df.median_house_value

# split the data
X_train, X_val, y_train, y_val = train_test_split(X, y,  test_size=0.2, random_state=0)
X_train.shape, X_val.shape, y_train.shape, y_val.shape

# make a new regressor model 
regressor = xgb.XGBRegressor(objective ='reg:squarederror', 
                 colsample_bytree = 1, 
                 eta=0.3, 
                 learning_rate = 0.01,
                 max_depth = 5, 
                 alpha = 10, 
                 n_estimators = 500)
# fit on training set
regressor.fit(X_train, y_train) 
# predict on validation set
y_pred = regressor.predict(X_val)

# calculate RMSE
from sklearn.metrics import mean_squared_error

root_mean_squared_error = mean_squared_error(y_val, y_pred, squared=False)
root_mean_squared_error