def test_check_numeric_inplace():
X = data.load_10X()
matrix.test_matrix_types(
X,
utils.assert_transform_unchanged,
matrix._scipy_matrix_types
+ matrix._numpy_matrix_types
+ matrix._pandas_dense_matrix_types
+ [matrix.SparseDataFrame],
transform=scprep.sanitize.check_numeric,
copy=False,
)
if matrix._pandas_0:
matrix._ignore_pandas_sparse_warning()
utils.assert_raises_message(
TypeError,
"pd.SparseDataFrame does not support " "copy=False. Please use copy=True.",
scprep.sanitize.check_numeric,
data=matrix.SparseDataFrame_deprecated(X),
copy=False,
)
matrix._reset_warnings()
class TypeErrorClass(object):
def astype(self, dtype):
return
X = TypeErrorClass()
utils.assert_raises_message(
TypeError,
"astype() got an unexpected keyword argument 'copy'",
scprep.sanitize.check_numeric,
data=X,
copy=None,
)
def test_toarray_vector():
X = data.generate_positive_sparse_matrix(shape=(50,))
def test_fun(X):
assert isinstance(scprep.utils.toarray(X), np.ndarray)
matrix.test_matrix_types(X, test_fun, matrix._pandas_vector_types)
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_sparse_dataframe_fill_value(self):
def test_fun(X):
Y = scprep.select.select_rows(X, idx=np.arange(X.shape[0] // 2))
for col in Y.columns:
assert X[col].dtype == Y[col].dtype, (X[col].dtype,
Y[col].dtype)
Y = scprep.select.select_cols(X, idx=np.arange(X.shape[1] // 2))
for col in Y.columns:
assert X[col].dtype == Y[col].dtype, (X[col].dtype,
Y[col].dtype)
matrix.test_matrix_types(self.X.astype(float), test_fun,
matrix._pandas_sparse_matrix_types)
def test_is_sparse_series():
X = data.load_10X(sparse=True)
assert scprep.utils.is_sparse_series(X[X.columns[0]])
def test_fun(X):
if scprep.utils.is_SparseDataFrame(X):
x = X[X.columns[0]]
else:
x = scprep.select.select_cols(X, idx=0)
assert not scprep.utils.is_sparse_series(x)
types = (matrix._scipy_matrix_types + matrix._numpy_matrix_types +
matrix._pandas_dense_matrix_types)
if matrix._pandas_0:
types.append(matrix.SparseDataFrame_deprecated)
matrix.test_matrix_types(X.to_numpy(), test_fun, types)
def test_is_sparse_dataframe():
X = data.load_10X(sparse=False)
Y = X.astype(pd.SparseDtype(float, fill_value=0.0))
assert scprep.utils.is_sparse_dataframe(Y)
def test_fun(X):
assert not scprep.utils.is_sparse_dataframe(X)
types = (matrix._scipy_matrix_types + matrix._numpy_matrix_types +
matrix._pandas_dense_matrix_types)
if matrix._pandas_0:
types.append(matrix.SparseDataFrame_deprecated)
matrix.test_matrix_types(
X,
test_fun,
types,
)
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)