Scikit-Learn GridSearchCV VotingRegressor

Hyperparameter tuning is a crucial step in optimizing machine learning models for best performance. In this example, we’ll demonstrate how to use scikit-learn’s GridSearchCV to perform hyperparameter tuning for VotingRegressor, a powerful ensemble method for regression tasks.

Grid search is a method for evaluating different combinations of model hyperparameters to find the best performing configuration. It exhaustively searches through a specified parameter grid, trains and evaluates the model for each combination using cross-validation, and selects the hyperparameters that yield the best performance metric.

VotingRegressor is an ensemble method that combines predictions from multiple regression models to improve overall performance. By averaging the predictions of individual models, it leverages their strengths and mitigates their weaknesses.

The key hyperparameters for VotingRegressor include the list of estimators and their individual hyperparameters. These parameters control the configuration of each model within the ensemble and their contribution to the final prediction.

from sklearn.datasets import make_regression
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.linear_model import LinearRegression
from sklearn.tree import DecisionTreeRegressor
from sklearn.neighbors import KNeighborsRegressor
from sklearn.ensemble import VotingRegressor

# Generate synthetic regression dataset
X, y = make_regression(n_samples=1000, n_features=20, noise=0.1, random_state=42)

# Split into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Define individual regressors
reg1 = LinearRegression()
reg2 = DecisionTreeRegressor(random_state=42)
reg3 = KNeighborsRegressor()

# Define Voting Regressor
voting_regressor = VotingRegressor(estimators=[('lr', reg1), ('dt', reg2), ('knn', reg3)])

# Define parameter grid
param_grid = {
    'lr__fit_intercept': [True, False],
    'dt__max_depth': [None, 10, 20],
    'knn__n_neighbors': [5, 10, 15]
}

# Perform grid search
grid_search = GridSearchCV(estimator=voting_regressor,
                           param_grid=param_grid,
                           cv=5,
                           scoring='neg_mean_squared_error')
grid_search.fit(X_train, y_train)

# Report best score and parameters
print(f"Best score: {grid_search.best_score_:.3f}")
print(f"Best parameters: {grid_search.best_params_}")

# Evaluate on test set
best_model = grid_search.best_estimator_
test_score = best_model.score(X_test, y_test)
print(f"Test set score: {test_score:.3f}")

Running the example gives an output like:

Best score: -5820.681
Best parameters: {'dt__max_depth': None, 'knn__n_neighbors': 5, 'lr__fit_intercept': True}
Test set score: 0.866

The steps are as follows:

1. Generate a synthetic regression dataset using scikit-learn’s make_regression function.
2. Split the dataset into train and test sets using train_test_split.
3. Define individual regressors: LinearRegression, DecisionTreeRegressor, and KNeighborsRegressor.
4. Create a VotingRegressor combining these individual regressors.
5. Define the parameter grid with different values for fit_intercept for LinearRegression, max_depth for DecisionTreeRegressor, and n_neighbors for KNeighborsRegressor.
6. Perform grid search using GridSearchCV, specifying the VotingRegressor, parameter grid, 5-fold cross-validation, and neg_mean_squared_error scoring metric.
7. Report the best cross-validation score and best set of hyperparameters found by grid search.
8. Evaluate the best model on the hold-out test set and report the score.

By using GridSearchCV, we can easily explore different hyperparameter settings and find the combination that maximizes the model’s performance. This automated approach saves time and effort compared to manual hyperparameter tuning and helps ensure we select the best configuration for our VotingRegressor.