Class _BaseChain

sklearn/multioutput.py:638–842

class _BaseChain(BaseEstimator, metaclass=ABCMeta):
    _parameter_constraints: dict = {
        "estimator": [HasMethods(["fit", "predict"])],
        "order": ["array-like", StrOptions({"random"}), None],
        "cv": ["cv_object", StrOptions({"prefit"})],
        "random_state": ["random_state"],
        "verbose": ["boolean"],
    }

    def __init__(
        self,
        estimator,
        *,
        order=None,
        cv=None,
        random_state=None,
        verbose=False,
    ):
        self.estimator = estimator
        self.order = order
        self.cv = cv
        self.random_state = random_state
        self.verbose = verbose

    def _log_message(self, *, estimator_idx, n_estimators, processing_msg):
        if not self.verbose:
            return None
        return f"({estimator_idx} of {n_estimators}) {processing_msg}"

    def _get_predictions(self, X, *, output_method):
        """Get predictions for each model in the chain."""
        check_is_fitted(self)
        X = validate_data(self, X, accept_sparse=True, reset=False)
        Y_output_chain = np.zeros((X.shape[0], len(self.estimators_)))
        Y_feature_chain = np.zeros((X.shape[0], len(self.estimators_)))

        # `RegressorChain` does not have a `chain_method_` parameter so we
        # default to "predict"
        chain_method = getattr(self, "chain_method_", "predict")
        hstack = sp.hstack if sp.issparse(X) else np.hstack
        for chain_idx, estimator in enumerate(self.estimators_):
            previous_predictions = Y_feature_chain[:, :chain_idx]
            # if `X` is a scipy sparse dok_array, we convert it to a sparse
            # coo_array format before hstacking, it's faster; see
            # https://github.com/scipy/scipy/issues/20060#issuecomment-1937007039:
            if sp.issparse(X) and not sp.isspmatrix(X) and X.format == "dok":
                X = sp.coo_array(X)
            X_aug = hstack((X, previous_predictions))

            feature_predictions, _ = _get_response_values(
                estimator,
                X_aug,
                response_method=chain_method,
            )
            Y_feature_chain[:, chain_idx] = feature_predictions

            output_predictions, _ = _get_response_values(
                estimator,