def _get_sliceXarray(self, row: slice,
col: Sequence[int]) -> ss.csc_matrix:
idxs = np.asarray(col)
if idxs.dtype == bool:
idxs = np.where(idxs)
return ss.csc_matrix(get_compressed_vectors(self, idxs),
shape=(self.shape[0], len(idxs)))[row, :]
def sparse_matrix_from_args(type, arg1, *args, **kwargs):
if type == "coo":
return _sp.coo_matrix(arg1, *args, **kwargs)
elif type == "csr":
return _sp.csr_matrix(arg1, *args, **kwargs)
elif type == "csc":
return _sp.csc_matrix(arg1, *args, **kwargs)
elif type == "dia":
return _sp.dia_matrix(arg1, *args, **kwargs)
def _get_missing_features_info(self, X):
"""Compute the imputer mask and the indices of the features
containing missing values.
Parameters
----------
X : {ndarray or sparse matrix}, shape (n_samples, n_features)
The input data with missing values. Note that ``X`` has been
checked in ``fit`` and ``transform`` before to call this function.
Returns
-------
imputer_mask : {ndarray or sparse matrix}, shape \
(n_samples, n_features)
The imputer mask of the original data.
features_with_missing : ndarray, shape (n_features_with_missing)
The features containing missing values.
"""
if sparse.issparse(X):
mask = _get_mask(X.data, self.missing_values)
# The imputer mask will be constructed with the same sparse format
# as X.
sparse_constructor = (sparse.csr_matrix
if X.format == 'csr' else sparse.csc_matrix)
imputer_mask = sparse_constructor(
(mask, X.indices.copy(), X.indptr.copy()),
shape=X.shape,
dtype=np.float32)
# temporarly switch to using float32 as
# cupy cannot operate with bool as of now
if self.features == 'missing-only':
n_missing = imputer_mask.sum(axis=0)
if self.sparse is False:
imputer_mask = imputer_mask.toarray()
elif imputer_mask.format == 'csr':
imputer_mask = imputer_mask.tocsc()
else:
imputer_mask = _get_mask(X, self.missing_values)
if self.features == 'missing-only':
n_missing = imputer_mask.sum(axis=0)
if self.sparse is True:
imputer_mask = sparse.csc_matrix(imputer_mask)
if self.features == 'all':
features_indices = np.arange(X.shape[1])
else:
features_indices = np.flatnonzero(n_missing)
return imputer_mask, features_indices
def _get_sliceXint(self, row: slice, col: int) -> ss.csc_matrix:
return ss.csc_matrix(get_compressed_vector(self, col),
shape=(self.shape[0], 1))[row, :]