from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split

data, target = fetch_california_housing(as_frame=True, return_X_y=True)
target *= 100  # rescale the target in k$
data_train, data_test, target_train, target_test = train_test_split(
    data, target, random_state=0, test_size=0.5
)

# solution
from sklearn.metrics import mean_absolute_error
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import BaggingRegressor

tree = DecisionTreeRegressor()
bagging = BaggingRegressor(estimator=tree, n_jobs=2)
bagging.fit(data_train, target_train)
target_predicted = bagging.predict(data_test)
print(
    "Basic mean absolute error of the bagging regressor:\n"
    f"{mean_absolute_error(target_test, target_predicted):.2f} k$"
)

# solution
for param in bagging.get_params().keys():
    print(param)

from scipy.stats import randint
from sklearn.model_selection import RandomizedSearchCV

param_grid = {
    "n_estimators": randint(10, 30),
    "max_samples": [0.5, 0.8, 1.0],
    "max_features": [0.5, 0.8, 1.0],
    "estimator__max_depth": randint(3, 10),
}
search = RandomizedSearchCV(
    bagging, param_grid, n_iter=20, scoring="neg_mean_absolute_error"
)
_ = search.fit(data_train, target_train)

import pandas as pd

columns = [f"param_{name}" for name in param_grid.keys()]
columns += ["mean_test_error", "std_test_error"]
cv_results = pd.DataFrame(search.cv_results_)
cv_results["mean_test_error"] = -cv_results["mean_test_score"]
cv_results["std_test_error"] = cv_results["std_test_score"]
cv_results[columns].sort_values(by="mean_test_error")

target_predicted = search.predict(data_test)
print(
    "Mean absolute error after tuning of the bagging regressor:\n"
    f"{mean_absolute_error(target_test, target_predicted):.2f} k$"
)