Function check_classifiers_train

sklearn/utils/estimator_checks.py:2981–3116

(
    name, classifier_orig, readonly_memmap=False, X_dtype="float64"
)

@ignore_warnings  # Warnings are raised by decision function
def check_classifiers_train(
    name, classifier_orig, readonly_memmap=False, X_dtype="float64"
):
    X_m, y_m = make_blobs(n_samples=300, random_state=0)
    X_m = X_m.astype(X_dtype)
    X_m, y_m = shuffle(X_m, y_m, random_state=7)
    X_m = StandardScaler().fit_transform(X_m)
    # generate binary problem from multi-class one
    y_b = y_m[y_m != 2]
    X_b = X_m[y_m != 2]

    if name in ["BernoulliNB", "MultinomialNB", "ComplementNB", "CategoricalNB"]:
        X_m -= X_m.min()
        X_b -= X_b.min()

    if readonly_memmap:
        X_m, y_m, X_b, y_b = create_memmap_backed_data([X_m, y_m, X_b, y_b])

    problems = [(X_b, y_b)]
    tags = get_tags(classifier_orig)
    if tags.classifier_tags.multi_class:
        problems.append((X_m, y_m))

    for X, y in problems:
        classes = np.unique(y)
        n_classes = len(classes)
        n_samples, n_features = X.shape
        classifier = clone(classifier_orig)
        X = _enforce_estimator_tags_X(classifier, X)
        y = _enforce_estimator_tags_y(classifier, y)

        set_random_state(classifier)
        # raises error on malformed input for fit
        if not tags.no_validation:
            with raises(
                ValueError,
                err_msg=(
                    f"The classifier {name} does not raise an error when "
                    "incorrect/malformed input data for fit is passed. The number "
                    "of training examples is not the same as the number of "
                    "labels. Perhaps use check_X_y in fit."
                ),
            ):
                classifier.fit(X, y[:-1])

        # fit
        classifier.fit(X, y)
        # with lists
        classifier.fit(X.tolist(), y.tolist())
        assert hasattr(classifier, "classes_")
        y_pred = classifier.predict(X)

        assert y_pred.shape == (n_samples,)
        # training set performance
        if not tags.classifier_tags.poor_score:
            assert accuracy_score(y, y_pred) > 0.83

        # raises error on malformed input for predict