📃 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 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(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$"
)

Basic mean absolute error of the bagging regressor:
36.89 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)

bootstrap
bootstrap_features
estimator__ccp_alpha
estimator__criterion
estimator__max_depth
estimator__max_features
estimator__max_leaf_nodes
estimator__min_impurity_decrease
estimator__min_samples_leaf
estimator__min_samples_split
estimator__min_weight_fraction_leaf
estimator__monotonic_cst
estimator__random_state
estimator__splitter
estimator
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],
    "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_estimator__max_depth	mean_test_error	std_test_error
6	26	0.8	0.8	9	38.744822	0.820730
1	25	1.0	1.0	9	39.199503	1.262572
16	17	0.8	1.0	9	39.516545	1.206744
11	16	0.5	0.8	9	40.312757	1.155289
14	18	0.5	0.8	7	42.267199	0.964222
17	12	1.0	1.0	6	45.278605	1.337975
0	22	1.0	0.5	8	45.590140	1.924398
12	10	1.0	1.0	6	45.612139	1.437821
19	20	1.0	0.5	9	46.228952	2.377679
9	21	0.5	1.0	5	47.843261	1.139545
5	12	0.8	0.5	8	48.053938	2.231738
4	18	0.5	0.5	6	50.683869	2.880660
2	17	0.8	0.8	4	52.376981	1.506407
7	21	1.0	0.8	4	52.738827	0.935594
10	23	1.0	0.5	4	55.681169	1.181115
18	23	1.0	1.0	3	56.662008	1.020801
8	12	0.8	1.0	3	57.160400	1.155378
13	27	0.5	0.8	3	58.060659	1.051121
15	26	1.0	0.5	3	60.376695	1.263127
3	11	0.5	0.5	3	60.706643	1.903773

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$"
)

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

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