def test_observation_set_csv_converter(self):
obs1 = Observation('foo')
obs2 = Observation('bar')
obs_set = ObservationSet([obs1, obs2])
d = obs_set.to_dict()
c = ObservationSetCsvConverter()
# order doesn't matter, so need to check both orders:
converted_input = c.convert('xyz', d, '', '')
self.assertTrue(({
'xyz': 'foo,bar'
} == converted_input)
| ({
'xyz': 'bar,foo'
} == converted_input))
def test_metadata_correct_case2(self):
'''
Typically, the metadata is collected following a successful
validation. Do that here
'''
m = IntegerMatrix()
resource_path = os.path.join(TESTDIR, 'test_integer_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 setUp(self):
# create a couple Observations to use and a corresponding serializer
self.el1 = Observation('sampleA', {'phenotype': StringAttribute('WT')})
self.el1_serializer = ObservationSerializer(self.el1)
self.el2 = Observation('sampleB', {'phenotype': StringAttribute('KO')})
self.el2_serializer = ObservationSerializer(self.el2)
# a duplicate of el1 above, for testing addition of duplicate elements:
self.duplicate_element = Observation('sampleA', {})
self.dup_element_serializer = ObservationSerializer(
self.duplicate_element)
# the correct serialized representation of an ElementSet instance
self.expected_element_set_data = {
'multiple': True,
'elements': [self.el1_serializer.data, self.el2_serializer.data]
}
# a correctly formed instance of an ObservationSet
self.element_set = ObservationSet([self.el1, self.el2])
# the class that will execute the tests
self.tester_class = ElementSetSerializerTester(
ObservationSetSerializer)
def test_metadata_correct(self):
resource_path = os.path.join(TESTDIR, 'three_column_annotation.tsv')
t = AnnotationTable()
column_dict = {}
obs_list = []
for i, line in enumerate(open(resource_path)):
if i == 0:
contents = line.strip().split('\t')
for j, c in enumerate(contents[1:]):
column_dict[j] = c
else:
contents = line.strip().split('\t')
samplename = contents[0]
attr_dict = {}
for j, v in enumerate(contents[1:]):
attr = UnrestrictedStringAttribute(v)
attr_dict[column_dict[j]] = attr
obs = Observation(samplename, attr_dict)
obs_list.append(obs)
expected_obs_set = ObservationSetSerializer(
ObservationSet(obs_list)).data
metadata = t.extract_metadata(resource_path, 'tsv')
self.assertEqual(metadata[OBSERVATION_SET_KEY], expected_obs_set)
self.assertIsNone(metadata[FEATURE_SET_KEY])
self.assertIsNone(metadata[PARENT_OP_KEY])
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, 'tsv')
# 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])
# Commented out when removed the feature metadata, as it was causing database
# issues due to the size of the json object.
#self.assertEqual(feature_set, metadata[FEATURE_SET_KEY])
self.assertIsNone(metadata[FEATURE_SET_KEY])
self.assertIsNone(metadata[PARENT_OP_KEY])
def test_observation_set_list_converter(self):
'''
Tests that we get properly formatted JSON-compatible
arrays (of strings in this case). Used when we need to
supply a WDL job with a list of relevant samples as an
array of strings, for instance.
'''
obs1 = Observation('foo')
obs2 = Observation('bar')
obs_set = ObservationSet([obs1, obs2])
d = obs_set.to_dict()
c = ObservationSetListConverter()
# order doesn't matter, so need to check both orders:
converted_input = c.convert('xyz', d, '', '')
self.assertTrue(({
'xyz': ['foo', 'bar']
} == converted_input)
| ({
'xyz': ['bar', 'foo']
} == converted_input))
def _build_set(self, data):
'''
A helper method which attempts to build an ObservationSet
given the `data` arg. Assumes the `data` does have the
proper keys
'''
obs_list = []
for obs_dict in data['elements']:
obs_serializer = ObservationSerializer(data=obs_dict)
obs = obs_serializer.get_instance()
obs_list.append(obs)
return ObservationSet(obs_list, data['multiple'])
def extract_metadata(self, resource_path, parent_op_pk=None):
super().extract_metadata(resource_path, parent_op_pk)
# the FeatureSet comes from the rows:
f_set = FeatureSet([Feature(x) for x in self.table.index])
self.metadata[DataResource.FEATURE_SET] = FeatureSetSerializer(
f_set).data
# the ObservationSet comes from the cols:
o_set = ObservationSet([Observation(x) for x in self.table.columns])
self.metadata[DataResource.OBSERVATION_SET] = ObservationSetSerializer(
o_set).data
return self.metadata
def test_merge_of_different_types_fails(self):
'''
We cannot merge two different types (e.g. and Obs Set and Feat. Set)
Test that it raises an exception.
'''
element_list1 = [self.el1, self.el2]
some_feature = Feature('geneA', {'oncogene': StringAttribute('Y')})
element_list2 = [
some_feature,
]
obs_set = ObservationSet(element_list1)
feature_set = FeatureSet(element_list2)
with self.assertRaises(Exception):
new_set = merge_element_set([obs_set, feature_set])
def extract_metadata(self, resource_path, parent_op_pk=None):
'''
When we extract the metadata from an AnnotationTable, we
expect the Observation instances to be the rows.
Additional columns specify attributes of each Observation,
which we incorporate
'''
super().extract_metadata(resource_path, parent_op_pk)
observation_list = super().prep_metadata(Observation)
o_set = ObservationSet(observation_list)
self.metadata[DataResource.OBSERVATION_SET] = ObservationSetSerializer(
o_set).data
return self.metadata
def create(self, validated_data):
'''
Returns an ObservationSet instance from the validated
data.
'''
obs_list = []
for obs_dict in validated_data['elements']:
# the validated data has the Observation info as an OrderedDict
# below, we use the ObservationSerializer to turn that into
# proper Observation instance.
obs_serializer = ObservationSerializer(data=obs_dict)
obs = obs_serializer.get_instance()
obs_list.append(obs)
return ObservationSet(
obs_list,
validated_data['multiple']
)
def extract_metadata(self,
resource_path,
file_extension,
parent_op_pk=None):
super().extract_metadata(resource_path, file_extension, parent_op_pk)
# Note: removed the addition of FeatureSets to the metadata as it was causing
# issues with large json objects being inserted into the database.
# the FeatureSet comes from the rows:
# f_set = FeatureSet([Feature(x) for x in self.table.index])
# self.metadata[DataResource.FEATURE_SET] = FeatureSetSerializer(f_set).data
# the ObservationSet comes from the cols:
o_set = ObservationSet([Observation(x) for x in self.table.columns])
self.metadata[DataResource.OBSERVATION_SET] = ObservationSetSerializer(
o_set).data
return self.metadata