MCPcopy Create free account
hub / github.com/PythonOT/POT / inverse_transform

Method inverse_transform

ot/da.py:1009–1040  ·  view source on GitHub ↗

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

(self, Xs=None, ys=None, Xt=None, yt=None, batch_size=128)

Source from the content-addressed store, hash-verified

1007 return transp_Xs
1008
1009 def inverse_transform(self, Xs=None, ys=None, Xt=None, yt=None, batch_size=128):
1010 r"""Transports target samples :math:`\mathbf{X_t}` onto source samples :math:`\mathbf{X_s}`
1011
1012 Parameters
1013 ----------
1014 Xs : array-like, shape (n_source_samples, n_features)
1015 The training input samples.
1016 ys : array-like, shape (n_source_samples,)
1017 The class labels
1018 Xt : array-like, shape (n_target_samples, n_features)
1019 The training input samples.
1020 yt : array-like, shape (n_target_samples,)
1021 The class labels. If some target samples are unlabelled, fill the
1022 :math:`\mathbf{y_t}`'s elements with -1.
1023
1024 Warning: Note that, due to this convention -1 cannot be used as a
1025 class label
1026 batch_size : int, optional (default=128)
1027 The batch size for out of sample inverse transform
1028
1029 Returns
1030 -------
1031 transp_Xt : array-like, shape (n_source_samples, n_features)
1032 The transported target samples.
1033 """
1034 nx = self.nx
1035
1036 # check the necessary inputs parameters are here
1037 if check_params(Xt=Xt):
1038 transp_Xt = nx.dot(Xt, self.A1_) + self.B1_
1039
1040 return transp_Xt
1041
1042
1043class LinearGWTransport(LinearTransport):

Callers 1

Calls 2

check_paramsFunction · 0.85
dotMethod · 0.45

Tested by 1