def test_is_pairwise():
# simple checks for _is_pairwise
pca = KernelPCA(kernel='precomputed')
with pytest.warns(None) as record:
assert _is_pairwise(pca)
assert not record
# pairwise attribute that is not consistent with the pairwise tag
class IncorrectTagPCA(KernelPCA):
_pairwise = False
pca = IncorrectTagPCA(kernel='precomputed')
msg = "_pairwise was deprecated in 0.24 and will be removed in 1.1"
with pytest.warns(FutureWarning, match=msg):
assert not _is_pairwise(pca)
# the _pairwise attribute is present and set to True while pairwise tag is
# not present
class TruePairwise(BaseEstimator):
_pairwise = True
true_pairwise = TruePairwise()
with pytest.warns(FutureWarning, match=msg):
assert _is_pairwise(true_pairwise)
# pairwise attribute is not defined thus tag is used
est = BaseEstimator()
with pytest.warns(None) as record:
assert not _is_pairwise(est)
assert not record
def test_is_pairwise():
# simple checks for _is_pairwise
pca = KernelPCA(kernel='precomputed')
with pytest.warns(None) as record:
assert _is_pairwise(pca)
assert not record
# pairwise attribute that is not consistent with the pairwise tag
class IncorrectTagPCA(KernelPCA):
_pairwise = False
pca = IncorrectTagPCA(kernel='precomputed')
msg = ("_pairwise was deprecated in 0.24 and will be removed in 0.26. "
"Set the estimator tags of your estimator instead")
with pytest.warns(FutureWarning, match=msg):
assert not _is_pairwise(pca)
# the _pairwise attribute is present and set to False while the pairwise
# tag is not present
class FalsePairwise(BaseEstimator):
_pairwise = False
def _get_tags(self):
tags = super()._get_tags()
del tags['pairwise']
return tags
false_pairwise = FalsePairwise()
with pytest.warns(None) as record:
assert not _is_pairwise(false_pairwise)
assert not record
# the _pairwise attribute is present and set to True while pairwise tag is
# not present
class TruePairwise(FalsePairwise):
_pairwise = True
true_pairwise = TruePairwise()
with pytest.warns(FutureWarning, match=msg):
assert _is_pairwise(true_pairwise)
# pairwise attribute is not defined thus tag is used
est = BaseEstimator()
with pytest.warns(None) as record:
assert not _is_pairwise(est)
assert not record
def _safe_split(estimator, X, y, indices, train_indices=None):
"""Create subset of dataset and properly handle kernels.
Slice X, y according to indices for cross-validation, but take care of
precomputed kernel-matrices or pairwise affinities / distances.
If ``estimator._pairwise is True``, X needs to be square and
we slice rows and columns. If ``train_indices`` is not None,
we slice rows using ``indices`` (assumed the test set) and columns
using ``train_indices``, indicating the training set.
.. deprecated:: 0.24
The _pairwise attribute is deprecated in 0.24. From 1.1
(renaming of 0.26) and onward, this function will check for the
pairwise estimator tag.
Labels y will always be indexed only along the first axis.
Parameters
----------
estimator : object
Estimator to determine whether we should slice only rows or rows and
columns.
X : array-like, sparse matrix or iterable
Data to be indexed. If ``estimator._pairwise is True``,
this needs to be a square array-like or sparse matrix.
y : array-like, sparse matrix or iterable
Targets to be indexed.
indices : array of int
Rows to select from X and y.
If ``estimator._pairwise is True`` and ``train_indices is None``
then ``indices`` will also be used to slice columns.
train_indices : array of int or None, default=None
If ``estimator._pairwise is True`` and ``train_indices is not None``,
then ``train_indices`` will be use to slice the columns of X.
Returns
-------
X_subset : array-like, sparse matrix or list
Indexed data.
y_subset : array-like, sparse matrix or list
Indexed targets.
"""
if _is_pairwise(estimator):
if not hasattr(X, "shape"):
raise ValueError("Precomputed kernels or affinity matrices have "
"to be passed as arrays or sparse matrices.")
# X is a precomputed square kernel matrix
if X.shape[0] != X.shape[1]:
raise ValueError("X should be a square kernel matrix")
if train_indices is None:
X_subset = X[np.ix_(indices, indices)]
else:
X_subset = X[np.ix_(indices, train_indices)]
else:
X_subset = _safe_indexing(X, indices)
if y is not None:
y_subset = _safe_indexing(y, indices)
else:
y_subset = None
return X_subset, y_subset