Method split

sklearn/model_selection/_split.py:116–145

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. y : array-l

(self, X, y=None, groups=None)

    __metadata_request__split = {"groups": metadata_routing.UNUSED}

    def split(self, X, y=None, 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.

        y : array-like of shape (n_samples,)
            The target variable for supervised learning problems.

        groups : array-like of shape (n_samples,), default=None
            Group labels for the samples used while splitting the dataset into
            train/test set.

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

        test : ndarray
            The testing set indices for that split.
        """
        X, y, groups = indexable(X, y, groups)
        indices = np.arange(_num_samples(X))
        for test_index in self._iter_test_masks(X, y, groups):
            train_index = indices[np.logical_not(test_index)]
            test_index = indices[test_index]
            yield train_index, test_index

    # Since subclasses must implement either _iter_test_masks or
    # _iter_test_indices, neither can be abstract.