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 test_fails_with_float_table(self):
'''
Capable of parsing a table of mixed numeric types
'''
m = IntegerMatrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_matrix.tsv'))
self.assertFalse(is_valid)
def test_excel_parses_correctly(self):
'''
Test that we can parse an excel spreadsheet provided the
data is contained in the first sheet
'''
m = IntegerMatrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_integer_matrix.xlsx'))
self.assertTrue(is_valid)
def test_table_without_rownames(self):
'''
Tables without row names fails
'''
m = IntegerMatrix()
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_reads_table_without_gene_label(self):
'''
Tables with a blank first column name are OK
'''
m = IntegerMatrix()
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_table_without_header(self):
'''
Tables without a header row fail
'''
m = IntegerMatrix()
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_excel_fails_if_not_in_first_sheet(self):
'''
If the data is contained on a different sheet than "the first"
the table is empty. If the first sheet contained data, then
there's really nothing we can do to correct that.
'''
m = IntegerMatrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_integer_matrix.second_sheet.xlsx'))
self.assertFalse(is_valid)
self.assertEqual(err, EMPTY_TABLE_ERROR)
def test_fails_parsing_int_table_with_na(self):
'''
Here, we take a NaN value which would be typically handled
gracefully as in the TestIntegerMatrix.test_reads_int_table_with_na
test function above. However, we also put a non-integer in the same
column to test that the special case handling is working properly.
'''
m = IntegerMatrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_integer_matrix.with_na_and_float.csv'))
self.assertFalse(is_valid)
def test_reads_int_table_with_na(self):
'''
Capable of parsing an integer table containing missing
data. Note that this requires some special handling
since NaN's force the column to be parsed as a float,
even if all other values in the column are integers
'''
m = IntegerMatrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_integer_matrix.with_na.csv'))
self.assertTrue(is_valid)
self.assertIsNone(err)
def test_fails_if_filetype_incorrect_case2(self):
'''
If a user specifies TSV but the file is, in fact,
a CSV, we fail out.
We are unable to decipher (without looking at the table)
that it was due to an incorrect file extension, but the
file still fails validation.
'''
m = IntegerMatrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR,
'test_csv_integer_matrix_labeled_as_tsv.tsv'))
self.assertFalse(is_valid)
def test_fails_parsing_int_table_with_na_and_float(self):
'''
Here, we take a NaN value which would be typically handled
gracefully as in the TestIntegerMatrix.test_reads_int_table_with_na
test function above. However, we also put a non-integer in a
different column (5) to test that the special case handling is
working properly.
'''
m = IntegerMatrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR,
'test_integer_matrix.with_multiple_na_and_float.csv'))
self.assertFalse(is_valid)
bad_col_str = 'SW5_Treated (column 5)'
expected_err_str = NON_INTEGER_ERROR.format(cols=bad_col_str)
self.assertEqual(err, expected_err_str)
def test_metadata_correct_case1(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')
is_valid, err = m.validate_type(resource_path, 'tsv')
self.assertTrue(is_valid)
self.assertIsNone(err)
# OK, the validation worked. Get metadata
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_reads_integer_table(self):
'''
Tables of integers pass validation
'''
m = IntegerMatrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_integer_matrix.tsv'))
self.assertTrue(is_valid)
self.assertIsNone(err)
m = IntegerMatrix()
is_valid, err = m.validate_type(
os.path.join(TESTDIR, 'test_integer_matrix.csv'))
self.assertTrue(is_valid)
self.assertIsNone(err)
def test_duplicate_rownames_fails(self):
m = IntegerMatrix()
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)
