📃 Solution for Exercise M6.01#

The aim of this notebook is to investigate if we can tune the hyperparameters of a bagging regressor and evaluate the gain obtained.

We will load the California housing dataset and split it into a training and a testing set.

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)

Note

If you want a deeper overview regarding this dataset, you can refer to the Appendix - Datasets description section at the end of this MOOC.

Create a BaggingRegressor and provide a DecisionTreeRegressor to its parameter base_estimator. Train the regressor and evaluate its generalization performance on the testing set using the mean absolute error.

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

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

Basic mean absolute error of the bagging regressor:
36.65 k$

Now, create a RandomizedSearchCV instance using the previous model and tune the important parameters of the bagging regressor. Find the best parameters and check if you are able to find a set of parameters that improve the default regressor still using the mean absolute error as a metric.

Tip

You can list the bagging regressor’s parameters using the get_params method.

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

base_estimator__ccp_alpha
base_estimator__criterion
base_estimator__max_depth
base_estimator__max_features
base_estimator__max_leaf_nodes
base_estimator__min_impurity_decrease
base_estimator__min_samples_leaf
base_estimator__min_samples_split
base_estimator__min_weight_fraction_leaf
base_estimator__random_state
base_estimator__splitter
base_estimator
bootstrap
bootstrap_features
max_features
max_samples
n_estimators
n_jobs
oob_score
random_state
verbose
warm_start

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],
    "base_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")

	param_n_estimators	param_max_samples	param_max_features	param_base_estimator__max_depth	mean_test_error	std_test_error
6	24	1.0	0.8	9	38.821404	0.993483
9	28	0.8	0.8	9	38.977671	0.802114
14	22	0.8	1.0	8	41.045770	1.433283
11	26	0.8	0.8	8	41.060876	0.826254
5	17	0.5	1.0	8	41.342266	0.808588
12	12	0.5	1.0	7	43.365408	1.095448
4	28	0.8	0.5	8	45.001969	1.651051
2	18	1.0	0.8	6	45.355027	0.969291
17	10	0.5	0.5	9	46.902308	3.349448
3	29	1.0	1.0	5	48.062688	1.185177
8	24	0.8	1.0	5	48.071241	0.992439
16	25	0.8	1.0	5	48.203451	1.016045
19	20	0.8	0.5	6	50.212784	1.839077
13	19	0.5	0.5	5	51.245127	0.973437
15	13	1.0	0.5	6	51.268143	1.866806
7	12	0.5	1.0	4	51.662910	0.711680
10	29	1.0	0.8	4	51.839849	0.692287
18	10	0.5	0.8	3	56.935565	0.925057
0	19	1.0	0.5	3	60.290096	2.405193
1	11	0.8	0.5	3	61.957899	1.831614

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

Mean absolute error after tuning of the bagging regressor:
39.43 k$

We see that the predictor provided by the bagging regressor does not need much hyperparameter tuning compared to a single decision tree.

Scikit-learn course

📃 Solution for Exercise M6.01

📃 Solution for Exercise M6.01#