Scikit-Learn RandomizedSearchCV AdaBoostRegressor

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 AdaBoostRegressor model, commonly used for regression 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.

AdaBoostRegressor is a boosting algorithm that combines multiple weak learners to create a strong learner. It iteratively adjusts the weights of weak learners based on their performance, aiming to reduce the overall prediction error.

Key hyperparameters for AdaBoostRegressor include the number of boosting stages (n_estimators), which controls the number of weak learners combined; the learning rate (learning_rate), which shrinks the contribution of each regressor to prevent overfitting; and the loss function (loss), which defines the error metric used for optimization.

from sklearn.datasets import make_regression
from sklearn.model_selection import train_test_split, RandomizedSearchCV
from sklearn.ensemble import AdaBoostRegressor
from sklearn.metrics import mean_squared_error
from scipy.stats import uniform

# Generate synthetic regression dataset
X, y = make_regression(n_samples=100, n_features=10, 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 the model
model = AdaBoostRegressor(random_state=42)

# Define hyperparameter distribution
param_dist = {
    'n_estimators': range(10, 50),
    'learning_rate': uniform(loc=0.01, scale=0.99),
    'loss': ['linear', 'square', 'exponential']
}

# Perform random search
random_search = RandomizedSearchCV(estimator=model,
                                   param_distributions=param_dist,
                                   n_iter=50,
                                   cv=5,
                                   scoring='neg_mean_squared_error',
                                   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_
mse = mean_squared_error(y_test, best_model.predict(X_test))
print(f"Test set mean squared error: {mse:.3f}")

Running the example gives an output like:

Best score: -10209.558
Best parameters: {'learning_rate': 0.6692631330513217, 'loss': 'square', 'n_estimators': 36}
Test set mean squared error: 20556.649

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 the AdaBoostRegressor model.
4. Define the hyperparameter distribution with different values for n_estimators, learning_rate, and loss.
5. Perform random search using RandomizedSearchCV, specifying the AdaBoostRegressor model, hyperparameter distribution, 100 iterations, 5-fold cross-validation, and negative mean squared error 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 mean squared error.

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 AdaBoostRegressor model.