Method partial_fit

sklearn/preprocessing/_data.py:476–545

Online computation of min and max on X for later scaling. All of X is processed as a single batch. This is intended for cases when :meth:`fit` is not feasible due to very large number of `n_samples` or because X is read from a continuous stream. Parameters -

(self, X, y=None)

    @_fit_context(prefer_skip_nested_validation=True)
    def partial_fit(self, X, y=None):
        """Online computation of min and max on X for later scaling.

        All of X is processed as a single batch. This is intended for cases
        when :meth:`fit` is not feasible due to very large number of
        `n_samples` or because X is read from a continuous stream.

        Parameters
        ----------
        X : array-like of shape (n_samples, n_features)
            The data used to compute the mean and standard deviation
            used for later scaling along the features axis.

        y : None
            Ignored.

        Returns
        -------
        self : object
            Fitted scaler.
        """
        feature_range = self.feature_range
        if feature_range[0] >= feature_range[1]:
            raise ValueError(
                "Minimum of desired feature range must be smaller than maximum. Got %s."
                % str(feature_range)
            )

        if sparse.issparse(X):
            raise TypeError(
                "MinMaxScaler does not support sparse input. "
                "Consider using MaxAbsScaler instead."
            )

        xp, _ = get_namespace(X)

        first_pass = not hasattr(self, "n_samples_seen_")
        X = validate_data(
            self,
            X,
            reset=first_pass,
            dtype=_array_api.supported_float_dtypes(xp, device=device(X)),
            ensure_all_finite="allow-nan",
        )

        device_ = device(X)
        feature_range = (
            xp.asarray(feature_range[0], dtype=X.dtype, device=device_),
            xp.asarray(feature_range[1], dtype=X.dtype, device=device_),
        )

        data_min = _array_api._nanmin(X, axis=0, xp=xp)
        data_max = _array_api._nanmax(X, axis=0, xp=xp)

        if first_pass:
            self.n_samples_seen_ = X.shape[0]
        else:
            data_min = xp.minimum(self.data_min_, data_min)