Method split

sklearn/model_selection/_split.py:849–889

Generate indices to split data into training and test set. Parameters ---------- X : array-like of shape (n_samples, n_features) Training data, where `n_samples` is the number of samples and `n_features` is the number of features. Note th

(self, X, y, groups=None)

            yield test_folds == i

    def split(self, X, y, groups=None):
        """Generate indices to split data into training and test set.

        Parameters
        ----------
        X : array-like of shape (n_samples, n_features)
            Training data, where `n_samples` is the number of samples
            and `n_features` is the number of features.

            Note that providing ``y`` is sufficient to generate the splits and
            hence ``np.zeros(n_samples)`` may be used as a placeholder for
            ``X`` instead of actual training data.

        y : array-like of shape (n_samples,)
            The target variable for supervised learning problems.
            Stratification is done based on the y labels.

        groups : array-like of shape (n_samples,), default=None
            Always ignored, exists for API compatibility.

        Yields
        ------
        train : ndarray
            The training set indices for that split.

        test : ndarray
            The testing set indices for that split.

        Notes
        -----
        Randomized CV splitters may return different results for each call of
        split. You can make the results identical by setting `random_state`
        to an integer.
        """
        if groups is not None:
            warnings.warn(
                f"The groups parameter is ignored by {self.__class__.__name__}",
                UserWarning,
            )
        y = check_array(y, input_name="y", ensure_2d=False, dtype=None)
        return super().split(X, y, groups)


class StratifiedGroupKFold(GroupsConsumerMixin, _BaseKFold):