Scikit-Learn GridSearchCV KNeighborsRegressor

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 KNeighborsRegressor, a popular algorithm 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.

KNeighborsRegressor is a regression model that predicts the target for a data point by averaging the targets of its nearest neighbors in the feature space. It is straightforward but can be very effective for certain types of regression problems.

The key hyperparameters for KNeighborsRegressor include the number of neighbors (n_neighbors), which determines how many neighbors are used in the prediction; the weights function (weights), which decides whether all neighbors are weighted equally or closer neighbors have more influence; and the algorithm used to compute the nearest neighbors (algorithm), which can affect the efficiency of the model.

from sklearn.datasets import make_regression
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.neighbors import KNeighborsRegressor

# Generate synthetic regression dataset
X, y = make_regression(n_samples=1000, 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 parameter grid
param_grid = {
    'n_neighbors': [3, 5, 7, 9],
    'weights': ['uniform', 'distance'],
    'algorithm': ['auto', 'ball_tree', 'kd_tree', 'brute']
}

# Perform grid search
grid_search = GridSearchCV(estimator=KNeighborsRegressor(),
                           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: -4205.617
Best parameters: {'algorithm': 'auto', 'n_neighbors': 5, 'weights': 'distance'}
Test set score: 0.781

The steps are as follows:

1. Generate a synthetic regression dataset using make_regression.
2. Split the dataset into train and test sets using train_test_split.
3. Define the parameter grid with different values for n_neighbors, weights, and algorithm hyperparameters.
4. Perform grid search using GridSearchCV, specifying the KNeighborsRegressor model, parameter grid, 5-fold cross-validation, and negative mean squared error 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 score.

By using GridSearchCV, we can efficiently explore different hyperparameter settings and identify the optimal configuration for our KNeighborsRegressor model, ensuring better performance on regression tasks.