def convert_to_cxg(
input_file,
output_directory,
backed,
title,
about,
sparse_threshold,
obs_names,
var_names,
disable_custom_colors,
disable_corpora_schema,
overwrite,
):
"""
Convert a dataset file into CXG.
"""
h5ad_data_file = H5ADDataFile(
input_file,
backed,
title,
about,
obs_names,
var_names,
use_corpora_schema=not disable_corpora_schema)
# Get the directory that will hold all the CXG files
cxg_output_container = get_output_directory(input_file, output_directory,
overwrite)
h5ad_data_file.to_cxg(
cxg_output_container,
sparse_threshold,
convert_anndata_colors_to_cxg_colors=not disable_custom_colors)
def test__create_h5ad_data_file__non_h5ad_raises_exception(self):
non_h5ad_filename = "my_fancy_dataset.csv"
with self.assertRaises(Exception) as exception_context:
H5ADDataFile(non_h5ad_filename)
self.assertIn("File must be an H5AD", str(exception_context.exception))
def test__create_h5ad_data_file__inputted_dataset_title_and_about_overrides_extracted(
self):
h5ad_file = H5ADDataFile(self.sample_h5ad_filename,
dataset_about="override_about",
dataset_title="override_title")
self.assertEqual(h5ad_file.dataset_title, "override_title")
self.assertEqual(h5ad_file.dataset_about, "override_about")
def sparse_diffexp(self, apply_col_shift):
with tempfile.TemporaryDirectory() as dirname:
# create a sparse matrix
h5adfile_path = os.path.join(dirname, "sparse.h5ad")
create_test_h5ad(h5adfile_path, 2000, 2000, 10, apply_col_shift)
h5ad_file_to_convert = H5ADDataFile(h5adfile_path, use_corpora_schema=False)
sparsename = os.path.join(dirname, "sparse.cxg")
h5ad_file_to_convert.to_cxg(sparsename, 11, True)
adaptor_anndata = self.load_dataset(h5adfile_path, extra_dataset_config=dict(embeddings__names=[]))
adaptor_sparse = self.load_dataset(sparsename)
assert adaptor_sparse.open_array("X").schema.sparse
assert adaptor_sparse.has_array("X_col_shift") == apply_col_shift
densename = os.path.join(dirname, "dense.cxg")
h5ad_file_to_convert.to_cxg(densename, True, 0)
adaptor_dense = self.load_dataset(densename)
assert not adaptor_dense.open_array("X").schema.sparse
assert not adaptor_dense.has_array("X_col_shift")
maskA = self.get_mask(adaptor_anndata, 1, 10)
maskB = self.get_mask(adaptor_anndata, 2, 10)
diffexp_results_anndata = diffexp_generic.diffexp_ttest(adaptor_anndata, maskA, maskB, 10)
diffexp_results_sparse = diffexp_cxg.diffexp_ttest(adaptor_sparse, maskA, maskB, 10)
diffexp_results_dense = diffexp_cxg.diffexp_ttest(adaptor_dense, maskA, maskB, 10)
self.compare_diffexp_results(diffexp_results_anndata, diffexp_results_sparse)
self.compare_diffexp_results(diffexp_results_anndata, diffexp_results_dense)
topcols = np.array([x[0] for x in diffexp_results_anndata])
cols_anndata = self.get_X_col(adaptor_anndata, topcols)
cols_sparse = self.get_X_col(adaptor_sparse, topcols)
cols_dense = self.get_X_col(adaptor_dense, topcols)
assert cols_anndata.shape[0] == adaptor_sparse.get_shape()[0]
assert cols_anndata.shape[1] == len(diffexp_results_anndata)
def convert(mat, cols):
return decode_matrix_fbs(encode_matrix_fbs(mat, col_idx=cols)).to_numpy()
cols_anndata = convert(cols_anndata, topcols)
cols_sparse = convert(cols_sparse, topcols)
cols_dense = convert(cols_dense, topcols)
x = adaptor_sparse.get_X_array()
assert x.shape == adaptor_sparse.get_shape()
for row in range(cols_anndata.shape[0]):
for col in range(cols_anndata.shape[1]):
vanndata = cols_anndata[row][col]
vsparse = cols_sparse[row][col]
vdense = cols_dense[row][col]
self.assertTrue(np.isclose(vanndata, vsparse, 1e-6, 1e-6))
self.assertTrue(np.isclose(vanndata, vdense, 1e-6, 1e-6))
def test__create_h5ad_data_file__no_copy_if_obs_and_var_index_names_specified(
self):
h5ad_file = H5ADDataFile(
self.sample_h5ad_filename,
use_corpora_schema=False,
obs_index_column_name="float_category",
vars_index_column_name="int_category",
)
self.assertNotIn("name_0", h5ad_file.obs.columns)
self.assertNotIn("name_0", h5ad_file.var.columns)
def test__create_h5ad_data_file__copies_index_of_obs_and_var_to_column(
self):
h5ad_file = H5ADDataFile(self.sample_h5ad_filename,
use_corpora_schema=False)
# The automatic name chosen for the index should be "name_0"
self.assertNotIn("name_0", self.sample_anndata.obs.columns)
self.assertIn("name_0", h5ad_file.obs.columns)
self.assertNotIn("name_0", self.sample_anndata.var.columns)
self.assertIn("name_0", h5ad_file.var.columns)
def test__create_h5ad_data_file__obs_and_var_index_names_specified_doesnt_exist_raises_exception(
self):
with self.assertRaises(Exception) as exception_context:
H5ADDataFile(
self.sample_h5ad_filename,
use_corpora_schema=False,
obs_index_column_name="unknown_category",
vars_index_column_name="i_dont_exist",
)
self.assertIn("does not exist", str(exception_context.exception))
def test__create_h5ad_data_file__assert_warning_outputted_if_dataset_title_or_about_given(
self):
with self.assertLogs(level="WARN") as logger:
H5ADDataFile(
self.sample_h5ad_filename,
dataset_title="My Awesome Dataset",
dataset_about="http://www.awesomedataset.com",
use_corpora_schema=False,
)
self.assertIn("will override any metadata that is extracted",
logger.output[0])
def test__create_h5ad_data_file__obs_and_var_index_names_specified_not_unique_raises_exception(
self):
with self.assertRaises(Exception) as exception_context:
H5ADDataFile(
self.sample_h5ad_filename,
use_corpora_schema=False,
obs_index_column_name="float_category",
vars_index_column_name="bool_category",
)
self.assertIn("Please prepare data to contain unique values",
str(exception_context.exception))
def test__to_cxg__with_sparse_column_encoding(self):
anndata = self._create_sample_anndata_dataset()
anndata.X = np.ones((3, 4))
sparse_with_column_shift_filename = self._write_anndata_to_file(
anndata)
h5ad_file = H5ADDataFile(sparse_with_column_shift_filename)
h5ad_file.to_cxg(self.sample_output_directory, 50)
self._validate_expected_generated_list_of_tiledb_files(
has_column_encoding=True)
# Clean up
remove(sparse_with_column_shift_filename)
def test__create_h5ad_data_file__reads_anndata_successfully(self):
h5ad_file = H5ADDataFile(self.sample_h5ad_filename,
use_corpora_schema=False)
self.assertTrue((h5ad_file.anndata.X == self.sample_anndata.X).all())
self.assertEqual(h5ad_file.anndata.obs.sort_index(inplace=True),
self.sample_anndata.obs.sort_index(inplace=True))
self.assertEqual(h5ad_file.anndata.var.sort_index(inplace=True),
self.sample_anndata.var.sort_index(inplace=True))
for key in h5ad_file.anndata.obsm.keys():
self.assertIn(key, self.sample_anndata.obsm.keys())
self.assertTrue(
(h5ad_file.anndata.obsm[key] == self.sample_anndata.obsm[key]
).all())
for key in self.sample_anndata.obsm.keys():
self.assertIn(key, h5ad_file.anndata.obsm.keys())
self.assertTrue(
(h5ad_file.anndata.obsm[key] == self.sample_anndata.obsm[key]
).all())
def test__to_cxg__simple_anndata_with_corpora_and_dense(self):
h5ad_file = H5ADDataFile(self.sample_h5ad_filename)
h5ad_file.to_cxg(self.sample_output_directory, 0)
self._validate_expected_generated_list_of_tiledb_files()
def test__to_cxg__simple_anndata_no_corpora_and_sparse(self):
h5ad_file = H5ADDataFile(self.sample_h5ad_filename,
use_corpora_schema=False)
h5ad_file.to_cxg(self.sample_output_directory, 100)
self._validate_expected_generated_list_of_tiledb_files()
def test__create_h5ad_data_file__extract_about_and_title_from_dataset(
self):
h5ad_file = H5ADDataFile(self.sample_h5ad_filename)
self.assertEqual(h5ad_file.dataset_title, "random_link_name")
self.assertEqual(h5ad_file.dataset_about, "www.link.com")