Method fit

sklearn/multiclass.py:331–395

Fit underlying estimators. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Data. y : {array-like, sparse matrix} of shape (n_samples,) or (n_samples, n_classes) Multi-class targets. An indicator matrix t

(self, X, y, **fit_params)

        prefer_skip_nested_validation=False
    )
    def fit(self, X, y, **fit_params):
        """Fit underlying estimators.

        Parameters
        ----------
        X : {array-like, sparse matrix} of shape (n_samples, n_features)
            Data.

        y : {array-like, sparse matrix} of shape (n_samples,) or (n_samples, n_classes)
            Multi-class targets. An indicator matrix turns on multilabel
            classification.

        **fit_params : dict
            Parameters passed to the ``estimator.fit`` method of each
            sub-estimator.

            .. versionadded:: 1.4
                Only available if `enable_metadata_routing=True`. See
                :ref:`Metadata Routing User Guide <metadata_routing>` for more
                details.

        Returns
        -------
        self : object
            Instance of fitted estimator.
        """
        _raise_for_params(fit_params, self, "fit")

        routed_params = process_routing(
            self,
            "fit",
            **fit_params,
        )
        # A sparse LabelBinarizer, with sparse_output=True, has been shown to
        # outperform or match a dense label binarizer in all cases and has also
        # resulted in less or equal memory consumption in the fit_ovr function
        # overall.
        self.label_binarizer_ = LabelBinarizer(sparse_output=True)
        Y = self.label_binarizer_.fit_transform(y)
        Y = Y.tocsc()
        self.classes_ = self.label_binarizer_.classes_
        columns = (col.toarray().ravel() for col in Y.T)
        # In cases where individual estimators are very fast to train setting
        # n_jobs > 1 in can results in slower performance due to the overhead
        # of spawning threads.  See joblib issue #112.
        self.estimators_ = Parallel(n_jobs=self.n_jobs, verbose=self.verbose)(
            delayed(_fit_binary)(
                self.estimator,
                X,
                column,
                fit_params=routed_params.estimator.fit,
                classes=[
                    "not %s" % self.label_binarizer_.classes_[i],
                    self.label_binarizer_.classes_[i],
                ],
            )
            for i, column in enumerate(columns)
        )