def test_10X_zip_not_a_file():
utils.assert_raises_message(
FileNotFoundError,
"No such file: 'not_a_file.zip'",
scprep.io.load_10X_zip,
"not_a_file.zip",
)
def test_10X_zip_url_404():
utils.assert_raises_message(
urllib.error.HTTPError,
"HTTP Error 404: Not Found",
scprep.io.load_10X_zip,
"https://github.com/KrishnaswamyLab/scprep/invalid_url",
)
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_mean_difference():
X = data.load_10X()
X = scprep.filter.filter_empty_genes(X)
Y = scprep.stats.mean_difference(X.iloc[:20], X.iloc[20:100])
assert np.allclose(np.max(Y), 16.8125)
assert np.allclose(np.min(Y), -0.5625)
def test_fun(X, **kwargs):
return scprep.stats.mean_difference(
scprep.select.select_rows(X, idx=np.arange(20)),
scprep.select.select_rows(X, idx=np.arange(20, 100)),
**kwargs,
)
matrix.test_all_matrix_types(
X,
utils.assert_transform_equals,
Y=Y,
transform=test_fun,
check=utils.assert_all_close,
)
utils.assert_raises_message(
ValueError,
"Expected X and Y to have the same number of columns. "
"Got shapes {}, {}".format(X.shape, X.iloc[:, :10].shape),
scprep.stats.mean_difference,
X,
X.iloc[:, :10],
)
def test_check_numeric_bad_dtype():
utils.assert_raises_message(
ValueError,
"could not convert string to float: ",
scprep.sanitize.check_numeric,
np.array(["hello", "world"]),
)
def test_10X_zip_url_not_a_zip():
utils.assert_raises_message(
zipfile.BadZipFile,
"File is not a zip file",
scprep.io.load_10X_zip,
"https://github.com/KrishnaswamyLab/scprep/raw/master/data/test_data/test_10X",
)
def test_get_values_invalid():
utils.assert_raises_message(
TypeError,
"Expected h5py.Dataset or tables.CArray. Got <class 'str'>",
scprep.io.hdf5.get_values,
"invalid",
)
def test_subsample_n_too_large(self):
utils.assert_raises_message(
ValueError,
"Expected n (101) <= n_samples (100)",
scprep.select.subsample,
self.X,
n=self.X.shape[0] + 1,
)
def test_select_cols_invalid_index(self):
utils.assert_raises_message(
KeyError,
"'not_a_gene'",
scprep.select.select_cols,
self.X,
idx="not_a_gene",
)
def test_select_rows_invalid_index(self):
utils.assert_raises_message(
KeyError,
"'not_a_cell'",
scprep.select.select_rows,
self.X,
idx="not_a_cell",
)
def test_sqrt_negative_value():
X = np.arange(10) * -1
utils.assert_raises_message(
ValueError,
"Cannot square root transform negative values",
scprep.transform.sqrt,
data=X,
)
def test_list_nodes_invalid():
utils.assert_raises_message(
TypeError,
"Expected h5py.File, tables.File, h5py.Group or "
"tables.Group. Got <class 'str'>",
scprep.io.hdf5.list_nodes,
"invalid",
)
def test_dyngen_backbone_not_in_list(self):
utils.assert_raises_message(
ValueError,
"Input not in default backbone list. "
"Choose backbone from get_backbones()",
scprep.run.DyngenSimulate,
backbone="not_a_backbone",
verbose=False,
)
def test_slingshot_distance(self):
utils.assert_raises_message(
NotImplementedError,
"distance argument not currently implemented",
scprep.run.Slingshot,
self.X_pca,
self.clusters,
distance=lambda X, Y: np.sum(X - Y),
)
def test_select_cols_2d_list_index(self):
utils.assert_raises_message(
ValueError,
"Expected idx to be 1D. "
"Got shape (2, {})".format(self.X.shape[1]),
scprep.select.select_cols,
self.X,
idx=[self.X.columns, self.X.columns],
)
def test_select_rows_2d_dataframe_index(self):
utils.assert_raises_message(
ValueError,
"Expected idx to be 1D. "
"Got shape (2, {})".format(self.X.shape[0]),
scprep.select.select_rows,
self.X,
idx=pd.DataFrame([self.X.index, self.X.index]),
)
def test_select_rows_unequal_rows(self):
utils.assert_raises_message(
ValueError,
"Expected `data` and `extra_data` to have the same number of "
"rows. Got [100, 50]",
scprep.select.select_rows,
self.X,
self.X.to_numpy()[:50, :],
)
def test_invalid_method(self):
utils.assert_raises_message(
ValueError,
"Expected `method` in ['svd', 'orth_rproj', 'rproj']. "
"Got 'invalid'",
scprep.reduce.pca,
self.X_sparse,
method="invalid",
)
def test_10X_HDF5_invalid_gene_labels():
h5_file = os.path.join(data.data_dir, "test_10X.h5")
utils.assert_raises_message(
ValueError,
"gene_labels='invalid' not recognized. " "Choose from ['symbol', 'id', 'both']",
scprep.io.load_10X_HDF5,
filename=h5_file,
gene_labels="invalid",
)
def test_10X_HDF5_invalid_genome():
h5_file = os.path.join(data.data_dir, "test_10X.h5")
utils.assert_raises_message(
ValueError,
"Genome invalid not found in {}. " "Available genomes: GRCh38".format(h5_file),
scprep.io.load_10X_HDF5,
filename=h5_file,
genome="invalid",
)
def test_10X_HDF5_invalid_backend():
h5_file = os.path.join(data.data_dir, "test_10X.h5")
utils.assert_raises_message(
ValueError,
"Expected backend in ['tables', 'h5py']. Got invalid",
scprep.io.load_10X_HDF5,
filename=h5_file,
backend="invalid",
)
def test_select_rows_get_cell_set_ndarray_data(self):
utils.assert_raises_message(
ValueError,
"Can only select based on row names with DataFrame input. "
"Please set `idx` to select specific rows.",
scprep.select.select_rows,
self.X.to_numpy(),
starts_with="A",
)
def test_install_bioc():
utils.assert_raises_message(
rpy2.rinterface_lib.embedded.RRuntimeError,
"Error: Bioconductor version '3.1' requires R version '3.2'; see",
scprep.run.install_bioconductor,
version="3.1",
site_repository="https://bioconductor.org/packages/3.1/bioc",
verbose=False,
)
def test_get_cell_set_ndarray(self):
utils.assert_raises_message(
TypeError,
"data must be a list of cell names or a pandas "
"DataFrame. Got ndarray",
scprep.select.get_cell_set,
data=self.X.to_numpy(),
regex="G\\-1$",
)
def test_libsize_norm_rescale_invalid(self):
utils.assert_raises_message(
ValueError,
"Expected rescale in ['median', 'mean'], a number or `None`. "
"Got invalid",
scprep.normalize.library_size_normalize,
self.X,
rescale="invalid",
)
def test_select_rows_conflicting_data(self):
utils.assert_raises_message(
ValueError,
"Expected `data` and `extra_data` pandas inputs to have the same "
"index. Fix with "
"`scprep.select.select_rows(*extra_data, idx=data.index)`",
scprep.select.select_rows,
self.X,
self.X.iloc[::-1],
)
def test_fcs_naming_error():
path = fcsparser.test_sample_path
utils.assert_raises_message(
ValueError,
"Expected channel_naming in ['$PnS', '$PnN']. " "Got 'invalid'",
scprep.io.load_fcs,
path,
override=True,
channel_naming="invalid",
)
def test_matrix_elementwise_multiply_invalid_axis():
X = data.generate_positive_sparse_matrix(shape=(50, 100))
utils.assert_raises_message(
ValueError,
"Expected axis in [0, 1, None]. Got 5",
scprep.utils.matrix_vector_elementwise_multiply,
X,
X[0],
axis=5,
)
def test_matrix_elementwise_multiply_guess_wrong_size():
X = data.generate_positive_sparse_matrix(shape=(50, 100))
utils.assert_raises_message(
ValueError,
"Expected `multiplier` to be a vector of length `data.shape[0]` (50) "
"or `data.shape[1]` (100). Got (10,)",
scprep.utils.matrix_vector_elementwise_multiply,
X,
X[0, :10],
)
def test_failed_import_both():
with mock.patch.dict(sys.modules, {"tables": None, "h5py": None}):
utils.assert_raises_message(
ImportError,
"Found neither tables nor h5py. "
"Please install one of them with e.g. "
"`pip install --user tables` or "
"`pip install --user h5py`",
hdf5_available,
)