Method fit

sklearn/preprocessing/_data.py:2875–2921

Compute the quantiles used for transforming. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) The data used to scale along the features axis. If a sparse matrix is provided, it will be converted into a sparse

(self, X, y=None)

    @_fit_context(prefer_skip_nested_validation=True)
    def fit(self, X, y=None):
        """Compute the quantiles used for transforming.

        Parameters
        ----------
        X : {array-like, sparse matrix} of shape (n_samples, n_features)
            The data used to scale along the features axis. If a sparse
            matrix is provided, it will be converted into a sparse
            CSC matrix. Additionally, the sparse matrix needs to be
            nonnegative if `ignore_implicit_zeros` is False.

        y : None
            Ignored.

        Returns
        -------
        self : object
           Fitted transformer.
        """
        if self.subsample is not None and self.n_quantiles > self.subsample:
            raise ValueError(
                "The number of quantiles cannot be greater than"
                " the number of samples used. Got {} quantiles"
                " and {} samples.".format(self.n_quantiles, self.subsample)
            )

        X = self._check_inputs(X, in_fit=True, copy=False)
        n_samples = X.shape[0]

        if self.n_quantiles > n_samples:
            warnings.warn(
                "n_quantiles (%s) is greater than the total number "
                "of samples (%s). n_quantiles is set to "
                "n_samples." % (self.n_quantiles, n_samples)
            )
        self.n_quantiles_ = max(1, min(self.n_quantiles, n_samples))

        rng = check_random_state(self.random_state)

        # Create the quantiles of reference
        self.references_ = np.linspace(0, 1, self.n_quantiles_, endpoint=True)
        if sparse.issparse(X):
            self._sparse_fit(X, rng)
        else:
            self._dense_fit(X, rng)

        return self

    def _transform_col(self, X_col, quantiles, inverse):
        """Private function to transform a single feature."""