def test_matrix_to_dataframe_no_names_dataframe_sparse(self):
Y = scprep.io.utils._matrix_to_data_frame(self.X_dense, sparse=True)
assert scprep.utils.is_sparse_dataframe(Y)
assert not scprep.utils.is_SparseDataFrame(Y)
assert np.all(scprep.utils.toarray(Y) == self.X_numpy)
utils.assert_matrix_class_equivalent(Y, self.X_sparse)
Y = scprep.io.utils._matrix_to_data_frame(self.X_sparse, sparse=True)
assert scprep.utils.is_sparse_dataframe(Y)
assert not scprep.utils.is_SparseDataFrame(Y)
assert np.all(scprep.utils.toarray(Y) == self.X_numpy)
utils.assert_matrix_class_equivalent(Y, self.X_sparse)
def test_combine_batches():
X = data.load_10X()
Y = pd.concat([X, scprep.utils.select_rows(X, np.arange(X.shape[0] // 2))])
Y2, sample_labels = scprep.utils.combine_batches(
[X, scprep.utils.select_rows(X, np.arange(X.shape[0] // 2))],
batch_labels=[0, 1])
assert utils.assert_matrix_class_equivalent(Y, Y2)
utils.assert_all_equal(Y, Y2)
assert np.all(Y.index == Y2.index)
assert np.all(sample_labels == np.concatenate(
[np.repeat(0, X.shape[0]),
np.repeat(1, X.shape[0] // 2)]))
Y2, sample_labels = scprep.utils.combine_batches(
[X, scprep.utils.select_rows(X, np.arange(X.shape[0] // 2))],
batch_labels=[0, 1],
append_to_cell_names=True)
assert np.all(Y.index == np.array([i[:-2] for i in Y2.index]))
assert np.all(
np.core.defchararray.add("_", sample_labels.astype(str)) == np.array(
[i[-2:] for i in Y2.index], dtype=str))
transform = lambda X: scprep.utils.combine_batches(
[X, scprep.utils.select_rows(X, np.arange(X.shape[0] // 2))],
batch_labels=[0, 1])[0]
matrix.test_matrix_types(X,
utils.assert_transform_equals,
matrix._indexable_matrix_types,
Y=Y,
transform=transform,
check=utils.assert_all_equal)
def test_matrix_to_dataframe_names_dense(self):
Y = scprep.io.utils._matrix_to_data_frame(
self.X_dense,
cell_names=self.cell_names,
gene_names=self.gene_names,
sparse=False,
)
assert isinstance(Y, pd.DataFrame)
assert not scprep.utils.is_sparse_dataframe(Y)
assert not scprep.utils.is_SparseDataFrame(Y)
assert np.all(scprep.utils.toarray(Y) == self.X_numpy)
utils.assert_matrix_class_equivalent(Y, self.X_dense)
Y = scprep.io.utils._matrix_to_data_frame(
self.X_sparse,
cell_names=self.cell_names,
gene_names=self.gene_names,
sparse=False,
)
assert isinstance(Y, pd.DataFrame)
assert not scprep.utils.is_sparse_dataframe(Y)
assert not scprep.utils.is_SparseDataFrame(Y)
assert np.all(scprep.utils.toarray(Y) == self.X_numpy)
utils.assert_matrix_class_equivalent(Y, self.X_dense)
Y = scprep.io.utils._matrix_to_data_frame(
self.X_numpy,
cell_names=self.cell_names,
gene_names=self.gene_names,
sparse=False,
)
assert isinstance(Y, pd.DataFrame)
assert not scprep.utils.is_sparse_dataframe(Y)
assert not scprep.utils.is_SparseDataFrame(Y)
assert np.all(scprep.utils.toarray(Y) == self.X_numpy)
utils.assert_matrix_class_equivalent(Y, self.X_dense)
def test_fun(X):
X = scprep.utils.SparseDataFrame(X, index=index, columns=columns)
utils.assert_matrix_class_equivalent(X, Y)
def test_combine_batches():
X = data.load_10X()
Y = pd.concat(
[X, scprep.select.select_rows(X, idx=np.arange(X.shape[0] // 2))],
axis=0,
sort=True,
)
Y2, sample_labels = scprep.utils.combine_batches(
[X, scprep.select.select_rows(X, idx=np.arange(X.shape[0] // 2))],
batch_labels=[0, 1],
append_to_cell_names=False,
)
assert utils.assert_matrix_class_equivalent(Y, Y2)
utils.assert_all_equal(Y, Y2)
assert np.all(Y.index == Y2.index)
assert np.all(
sample_labels
== np.concatenate([np.repeat(0, X.shape[0]), np.repeat(1, X.shape[0] // 2)])
)
assert np.all(sample_labels.index == Y2.index)
assert sample_labels.name == "sample_labels"
Y2, sample_labels = scprep.utils.combine_batches(
[X, scprep.select.select_rows(X, idx=np.arange(X.shape[0] // 2))],
batch_labels=[0, 1],
append_to_cell_names=True,
)
assert np.all(Y.index == np.array([i[:-2] for i in Y2.index]))
assert np.all(
np.core.defchararray.add("_", sample_labels.astype(str))
== np.array([i[-2:] for i in Y2.index], dtype=str)
)
assert np.all(sample_labels.index == Y2.index)
assert sample_labels.name == "sample_labels"
def transform(X):
return scprep.utils.combine_batches(
[X, scprep.select.select_rows(X, idx=np.arange(X.shape[0] // 2))],
batch_labels=[0, 1],
)[0]
matrix.test_matrix_types(
X,
utils.assert_transform_equals,
matrix._pandas_matrix_types,
Y=Y,
transform=transform,
check=utils.assert_all_equal,
)
# don't sort for non pandas
Y = pd.concat(
[X, scprep.select.select_rows(X, idx=np.arange(X.shape[0] // 2))],
axis=0,
sort=False,
)
matrix.test_matrix_types(
X,
utils.assert_transform_equals,
matrix._scipy_indexable_matrix_types + matrix._numpy_matrix_types,
Y=Y,
transform=transform,
check=utils.assert_all_equal,
)
def test_fun(X):
Y, sample_labels = scprep.utils.combine_batches(
[X, scprep.select.select_rows(X, idx=np.arange(X.shape[0] // 2))],
batch_labels=[0, 1],
)
assert np.all(sample_labels.index == Y.index)
assert sample_labels.name == "sample_labels"
matrix.test_pandas_matrix_types(X, test_fun)
