def test_metadata_correct_case2(self):
'''
Typically, the metadata is collected following a successful
validation. However, here we don't validate. Check that
it goes and collects the table in the process
'''
m = Matrix()
resource_path = os.path.join(TESTDIR, 'test_matrix.tsv')
metadata = m.extract_metadata(resource_path)
# Parse the test file to ensure we extracted the right content.
line = open(resource_path).readline()
contents = line.strip().split('\t')
samplenames = contents[1:]
obs_list = [Observation(x) for x in samplenames]
gene_list = []
for i, line in enumerate(open(resource_path)):
if i > 0:
g = line.split('\t')[0]
gene_list.append(g)
feature_list = [Feature(x) for x in gene_list]
obs_set = ObservationSetSerializer(ObservationSet(obs_list)).data
feature_set = FeatureSetSerializer(FeatureSet(feature_list)).data
self.assertEqual(obs_set, metadata[OBSERVATION_SET_KEY])
self.assertEqual(feature_set, metadata[FEATURE_SET_KEY])
self.assertIsNone(metadata[PARENT_OP_KEY])
def test_metadata_correct_case1(self):
'''
Typically, the metadata is collected following a successful
validation. Do that here
'''
m = Matrix()
resource_path = os.path.join(TESTDIR, 'test_matrix.tsv')
is_valid, err = m.validate_type(resource_path)
self.assertTrue(is_valid)
self.assertIsNone(err)
# OK, the validation worked. Get metadata
metadata = m.extract_metadata(resource_path)
# Parse the test file to ensure we extracted the right content.
line = open(resource_path).readline()
contents = line.strip().split('\t')
samplenames = contents[1:]
obs_list = [Observation(x) for x in samplenames]
gene_list = []
for i, line in enumerate(open(resource_path)):
if i > 0:
g = line.split('\t')[0]
gene_list.append(g)
feature_list = [Feature(x) for x in gene_list]
obs_set = ObservationSetSerializer(ObservationSet(obs_list)).data
feature_set = FeatureSetSerializer(FeatureSet(feature_list)).data
self.assertEqual(obs_set, metadata[OBSERVATION_SET_KEY])
self.assertEqual(feature_set, metadata[FEATURE_SET_KEY])
self.assertIsNone(metadata[PARENT_OP_KEY])
def test_table_without_rownames(self):
'''
Tables without row names fails
'''
m = Matrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_integer_matrix.no_rownames.tsv'))
self.assertFalse(is_valid)
self.assertEqual(err, NUMBERED_ROW_NAMES_ERROR)
def test_table_without_header(self):
'''
Tables without a header row fail
'''
m = Matrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_integer_matrix.no_header.tsv'))
self.assertFalse(is_valid)
self.assertEqual(err, NUMBERED_COLUMN_NAMES_ERROR)
def test_reads_table_without_gene_label(self):
'''
Tables with a blank first column name are OK
'''
m = Matrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_integer_matrix.no_gene_label.tsv'))
self.assertTrue(is_valid)
self.assertIsNone(err)
def test_reads_integer_table(self):
'''
Tables of integers also pass validation
'''
m = Matrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_integer_matrix.tsv'))
self.assertTrue(is_valid)
self.assertIsNone(err)
def test_reads_float_table(self):
'''
Capable of parsing a table of mixed numeric types
'''
m = Matrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_matrix.tsv'))
self.assertTrue(is_valid)
self.assertIsNone(err)
def test_reads_float_table_with_na(self):
'''
Capable of parsing a table containing missing
data
'''
m = Matrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_matrix.with_na.tsv'))
self.assertTrue(is_valid)
self.assertIsNone(err)
def test_incorrect_table(self):
'''
Tests that a table with a string entry fails
'''
m = Matrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_incorrect_matrix.tsv'))
self.assertFalse(is_valid)
bad_col_str = 'SW2_Control (column 2)'
expected_err_str = NON_NUMERIC_ERROR.format(cols=bad_col_str)
self.assertEqual(err, expected_err_str)
def test_with_real_files(self):
'''
Runs the test with real files rather than providing mocked
metadata. Not a true unit test, but whatever.
'''
# get a workspace in our db:
workspaces = Workspace.objects.filter(owner=self.regular_user_1)
if len(workspaces) == 0:
raise ImproperlyConfigured('Need at least one workspace.')
workspace = None
for w in workspaces:
workspace_resources = w.resources.filter(is_active = True)
if len(workspace_resources) >= 2:
workspace = w
if workspace is None:
raise ImproperlyConfigured('Need at least two resources that'
' are in a workspace. Modify the test database'
)
# we will attach the metadata to two resources:
all_resources = workspace.resources.all()
all_resources = [x for x in all_resources if x.is_active]
TESTDIR = os.path.dirname(__file__)
TESTDIR = os.path.join(TESTDIR, 'resource_validation_test_files')
resource_path = os.path.join(TESTDIR, 'deseq_results_example_concat.tsv')
self.assertTrue(os.path.exists(resource_path))
t = FeatureTable()
metadata0 = t.extract_metadata(resource_path, 'tsv')
r0 = all_resources[0]
add_metadata_to_resource(r0, metadata0)
resource_path = os.path.join(TESTDIR, 'test_matrix.tsv')
self.assertTrue(os.path.exists(resource_path))
m = Matrix()
metadata1 = m.extract_metadata(resource_path, 'tsv')
r1 = all_resources[1]
add_metadata_to_resource(r1, metadata1)
url = reverse(
'workspace-observations-metadata',
kwargs={'workspace_pk':workspace.pk}
)
response = self.authenticated_regular_client.get(url)
response_json = response.json()
def test_duplicate_rownames_fails(self):
m = Matrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_matrix.duplicate_rownames.tsv'))
self.assertFalse(is_valid)
self.assertEqual(err, NONUNIQUE_ROW_NAMES_ERROR)