Method transform

ot/da.py:2136–2173

r"""Transports source samples :math:`\mathbf{X_s}` onto target ones :math:`\mathbf{X_t}` Parameters ---------- Xs : array-like, shape (n_source_samples, n_features) The training input samples. Returns ------- transp_Xs : array-like, shape

(self, Xs)

        return self

    def transform(self, Xs):
        r"""Transports source samples :math:`\mathbf{X_s}` onto target ones :math:`\mathbf{X_t}`

        Parameters
        ----------
        Xs : array-like, shape (n_source_samples, n_features)
            The training input samples.

        Returns
        -------
        transp_Xs : array-like, shape (n_source_samples, n_features)
            The transport source samples.
        """
        nx = self.nx

        # check the necessary inputs parameters are here
        if check_params(Xs=Xs):
            if nx.array_equal(self.xs_, Xs):
                # perform standard barycentric mapping
                transp = self.coupling_ / nx.sum(self.coupling_, 1)[:, None]

                # set nans to 0
                transp = nx.nan_to_num(transp, nan=0, posinf=0, neginf=0)

                # compute transported samples
                transp_Xs = nx.dot(transp, self.xt_)
            else:
                if self.kernel == "gaussian":
                    K = kernel(Xs, self.xs_, method=self.kernel, sigma=self.sigma)
                elif self.kernel == "linear":
                    K = Xs
                if self.bias:
                    K = nx.concatenate(
                        [K, nx.ones((Xs.shape[0], 1), type_as=K)], axis=1
                    )
                transp_Xs = nx.dot(K, self.mapping_)

            return transp_Xs


class UnbalancedSinkhornTransport(BaseTransport):