def fit(self, X, y=None):
""" Does nothing, returns an unchanged estimator.
This method is here to implement the usual scikit-learn API and hence
work in pipelines.
Parameters
----------
X : ndarray of shape (n_samples, n_features, 3)
Input data. Array of persistence diagrams, each a collection of
triples [b, d, q] representing persistent topological features
through their birth (b), death (d) and homology dimension (q).
y : None
There is no need for a target in a transformer, yet the pipeline
API requires this parameter.
Returns
-------
self : object
"""
check_diagrams(X)
self.__is_fitted = True
return self
def transform(self, X, y=None):
""" Transforms a PDs into PTS representations.
Parameters
----------
X : ndarray of shape (n_samples, n_features, 3)
Input data. Array of persistence diagrams, each a collection of
triples [b, d, q] representing persistent topological features
through their birth (b), death (d) and homology dimension (q).
We assume that the PDs are normalized. The normalization scheme
in the official implementation is PD_norm = PD/max(PD).
y : None
There is no need for a target in a transformer, yet the pipeline
API requires this parameter.
Returns
-------
pts_repr : ndarray of shape
(n_samples, n_features, `subspace_dimension`)
PTS features.
"""
Xs = check_diagrams(X, copy=True)
pts_list = []
n_pds = Xs.shape[0]
for pd in Xs:
perturbed_pds = self.make_perturbation(pd)
pdfs = self.make_pdfs(perturbed_pds)
while self.subspace_dimension >= len(pdfs) and self.tries > 0:
perturbed_pds = self.make_perturbation(pd)
pdfs = self.make_pdfs(perturbed_pds)
self.tries -= 1
else:
if self.subspace_dimension >= len(pdfs):
raise ValueError("Cannot extract PTS. Please try again")
manifold_point = self.map_to_manifold(pdfs)
manifold_point = np.expand_dims(manifold_point, axis=0)
pts_list.append(manifold_point)
pts_repr = np.concatenate(pts_list, axis=0)
return pts_repr
def test_inputs_arrayStruc_V():
X = np.array([[[[1, 1, 0], [2, 2, 1]]]])
with pytest.raises(ValueError):
check_diagrams(X)