Scikit-Learn RandomizedSearchCV HistGradientBoostingClassifier

Hyperparameter tuning is essential for optimizing machine learning models. In this example, we’ll demonstrate how to use scikit-learn’s RandomizedSearchCV for hyperparameter tuning of a HistGradientBoostingClassifier, a powerful algorithm for binary classification tasks.

Random search is a method for evaluating different combinations of model hyperparameters. Unlike grid search, it samples a fixed number of hyperparameter combinations from a specified distribution, making it more efficient when searching over a large hyperparameter space.

HistGradientBoostingClassifier is a scalable implementation of gradient boosting for binary classification tasks. It is optimized for speed and efficiency, making it suitable for large datasets. The model iteratively trains decision trees on the residuals of previous iterations to improve accuracy.

Key hyperparameters for HistGradientBoostingClassifier include the number of boosting iterations (max_iter), which determines how many trees are built; the learning rate (learning_rate), which controls the contribution of each tree; and the maximum depth of individual estimators (max_depth), which limits the complexity of the trees.

from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split, RandomizedSearchCV
from sklearn.ensemble import HistGradientBoostingClassifier
from scipy.stats import randint, uniform

# Generate synthetic binary classification dataset
X, y = make_classification(n_samples=100, n_features=20, n_informative=10, n_redundant=10, 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 the model
model = HistGradientBoostingClassifier(random_state=42)

# Define hyperparameter distribution
param_dist = {
    'max_iter': randint(10, 50),
    'learning_rate': uniform(0.01, 0.3),
    'max_depth': randint(3, 10)
}

# Perform random search
random_search = RandomizedSearchCV(estimator=model,
                                   param_distributions=param_dist,
                                   n_iter=50,
                                   cv=5,
                                   scoring='accuracy',
                                   random_state=42)
random_search.fit(X_train, y_train)

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

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

Running the example gives an output like:

Best score: 0.800
Best parameters: {'learning_rate': 0.28279612062363463, 'max_depth': 6, 'max_iter': 49}
Test set accuracy: 0.850

The steps are as follows:

1. Generate a synthetic binary classification dataset using scikit-learn’s make_classification function.
2. Split the dataset into train and test sets using train_test_split.
3. Define the model as HistGradientBoostingClassifier.
4. Define the hyperparameter distribution with different values for max_iter, learning_rate, and max_depth hyperparameters.
5. Perform random search using RandomizedSearchCV, specifying the HistGradientBoostingClassifier model, hyperparameter distribution, 100 iterations, 5-fold cross-validation, and accuracy scoring metric.
6. Report the best cross-validation score and best set of hyperparameters found by random search.
7. Evaluate the best model on the hold-out test set and report the accuracy.

By using RandomizedSearchCV, we can efficiently 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 HistGradientBoostingClassifier model.