Scikit-Learn RandomizedSearchCV ExtraTreesClassifier

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 an ExtraTreesClassifier, a powerful ensemble method for 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.

ExtraTreesClassifier is an ensemble learning method that builds multiple decision trees and averages their predictions to improve accuracy and control overfitting. The model is trained by creating several unpruned decision trees and aggregating their results.

Key hyperparameters for ExtraTreesClassifier include the number of trees in the forest (n_estimators), which impacts model stability and performance; the number of features considered for splitting at each node (max_features), which affects model complexity and diversity; the minimum number of samples required to split an internal node (min_samples_split), which influences tree growth; and the minimum number of samples required to be at a leaf node (min_samples_leaf), which helps prevent overfitting.

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

# 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 = ExtraTreesClassifier(random_state=42)

# Define hyperparameter distribution
param_dist = {
    'n_estimators': randint(10, 50),
    'max_features': randint(1, 20),
    'min_samples_split': randint(2, 20),
    'min_samples_leaf': randint(1, 20)
}

# 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: 0.900
Best parameters: {'max_features': 7, 'min_samples_leaf': 1, 'min_samples_split': 2, 'n_estimators': 36}
Test set accuracy: 0.800

The steps are as follows:

1. Generate a synthetic binary classification dataset using make_classification.
2. Split the dataset into train and test sets using train_test_split.
3. Define the ExtraTreesClassifier model.
4. Define the hyperparameter distribution with different values for n_estimators, max_features, min_samples_split, and min_samples_leaf.
5. Perform random search using RandomizedSearchCV, specifying the ExtraTreesClassifier 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 ExtraTreesClassifier model.