Parameter estimation using grid search with cross-validationΒΆ

This examples shows how a classifier is optimized by cross-validation, which is done using the sklearn.model_selection.GridSearchCV object on a development set that comprises only half of the available labeled data.

The performance of the selected hyper-parameters and trained model is then measured on a dedicated evaluation set that was not used during the model selection step.

More details on tools available for model selection can be found in the sections on Cross-validation: evaluating estimator performance and Tuning the hyper-parameters of an estimator.

from __future__ import print_function

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import classification_report
from sklearn.svm import SVC


# Loading the Digits dataset
digits = datasets.load_digits()

# To apply an classifier on this data, we need to flatten the image, to
# turn the data in a (samples, feature) matrix:
n_samples = len(digits.images)
X = digits.images.reshape((n_samples, -1))
y =

# Split the dataset in two equal parts
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.5, random_state=0)

# Set the parameters by cross-validation
tuned_parameters = [{'kernel': ['rbf'], 'gamma': [1e-3, 1e-4],
                     'C': [1, 10, 100, 1000]},
                    {'kernel': ['linear'], 'C': [1, 10, 100, 1000]}]

scores = ['precision', 'recall']

for score in scores:
    print("# Tuning hyper-parameters for %s" % score)

    clf = GridSearchCV(SVC(C=1), tuned_parameters, cv=5,
                       scoring='%s_macro' % score), y_train)

    print("Best parameters set found on development set:")
    print("Grid scores on development set:")
    means = clf.cv_results_['mean_test_score']
    stds = clf.cv_results_['std_test_score']
    for mean, std, params in zip(means, stds, clf.cv_results_['params']):
        print("%0.3f (+/-%0.03f) for %r"
              % (mean, std * 2, params))

    print("Detailed classification report:")
    print("The model is trained on the full development set.")
    print("The scores are computed on the full evaluation set.")
    y_true, y_pred = y_test, clf.predict(X_test)
    print(classification_report(y_true, y_pred))

# Note the problem is too easy: the hyperparameter plateau is too flat and the
# output model is the same for precision and recall with ties in quality.

Total running time of the script: (0 minutes 0.000 seconds)

Download Python source code:
Download IPython notebook: grid_search_digits.ipynb