Scikit-Learn GridSearchCV NearestCentroid

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 NearestCentroid, a simple and efficient algorithm for classification 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.

NearestCentroid classifies samples based on the nearest centroid of each class in the feature space. The classifier is efficient and works well for certain types of classification problems.

The key hyperparameter for NearestCentroid is shrink_threshold, which is used to shrink centroids towards zero for better classification in high-dimensional spaces. Adjusting this parameter can help improve the model’s performance by reducing the effect of noise in the dataset.

from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.neighbors import NearestCentroid

# Generate synthetic binary classification dataset
X, y = make_classification(n_samples=1000, n_features=10, n_informative=5, n_redundant=5, 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 parameter grid
param_grid = {
    'shrink_threshold': [None, 0.1, 0.5, 1.0]
}

# Perform grid search
grid_search = GridSearchCV(estimator=NearestCentroid(),
                           param_grid=param_grid,
                           cv=5,
                           scoring='accuracy')
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_
accuracy = best_model.score(X_test, y_test)
print(f"Test set accuracy: {accuracy:.3f}")

Running the example gives an output like:

Best score: 0.819
Best parameters: {'shrink_threshold': None}
Test set accuracy: 0.805

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 parameter grid with different values for shrink_threshold.
4. Perform grid search using GridSearchCV, specifying the NearestCentroid model, parameter grid, 5-fold cross-validation, and accuracy scoring metric.
5. Report the best cross-validation score and best set of hyperparameters found by grid search.
6. Evaluate the best model on the hold-out test set and report the accuracy.

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 NearestCentroid model.