def test_get_column_data(self):
"""
Test: Assert array equals when getting column data
"""
try:
log.info(TestFilteredSummaryReader.test_count_records.__doc__)
fsr = FilteredSummaryReader(
os.path.join(BaseTestCase.get_data_dir(), 'loading',
'filtered_summary_small.csv'))
fsr.load()
ri_exp = [
'm120128_025832_42129_c100277632550000001523007907041250_s2_p0/0',
'm120128_025832_42129_c100277632550000001523007907041250_s2_p0/1'
]
ri_act = []
data = fsr.data_as_numpy_array()
for row in data:
ri_act.append(row['ReadId'])
self.assertSequenceEqual(ri_exp, ri_act)
except:
log.error(traceback.format_exc())
raise
def _get_all_filtered_read_ids(self):
reader = FilteredSummaryReader(os.path.join(
self.DATA_DIR, 'filtered_summary.csv'), CSV_COLUMN_MAP)
reader.load()
data = reader.data_as_numpy_array()
ids = set([])
for row in data:
ids.add(row['ReadId'])
return ids
def _get_all_filtered_read_ids(self):
reader = FilteredSummaryReader(
os.path.join(self.DATA_DIR, 'filtered_summary.csv'),
CSV_COLUMN_MAP)
reader.load()
data = reader.data_as_numpy_array()
ids = set([])
for row in data:
ids.add(row['ReadId'])
return ids
def test_count_records(self):
"""
Test: Count num csv records
"""
try:
log.info(TestFilteredSummaryReader.test_count_records.__doc__)
fsr = FilteredSummaryReader(os.path.join(BaseTestCase.get_data_dir(), 'loading', 'filtered_summary_small.csv'))
fsr.load()
self.assertEqual(2, fsr.num_records)
except:
log.error(traceback.format_exc())
raise
def _get_filtered_reads(filtered_subreads_csv):
"""
Return a numpy array of csv data filtered by
PassedFilter > 0
:param filtered_subreads_csv: path to filtered_summary.csv f
"""
reader = FilteredSummaryReader(filtered_subreads_csv, CSV_COLUMN_MAP)
reader.load()
data = reader.data_as_numpy_array()
data = data[data["PassedFilter"] > 0]
log.info('Total # reads in {f}: {i}'.format(
f=filtered_subreads_csv, i=reader.num_records))
log.info('# reads that passed filter: {i}'.format(i=len(data)))
return data
def _get_filtered_reads(filtered_subreads_csv):
"""
Return a numpy array of csv data filtered by
PassedFilter > 0
:param filtered_subreads_csv: path to filtered_summary.csv f
"""
reader = FilteredSummaryReader(filtered_subreads_csv, CSV_COLUMN_MAP)
reader.load()
data = reader.data_as_numpy_array()
data = data[data["PassedFilter"] > 0]
log.info('Total # reads in {f}: {i}'.format(f=filtered_subreads_csv,
i=reader.num_records))
log.info('# reads that passed filter: {i}'.format(i=len(data)))
return data
def test_num_reads(self):
"""
Test: get num reads from csv
"""
try:
log.info(TestFilteredSummaryReader.test_num_reads.__doc__)
fsr = FilteredSummaryReader(
os.path.join(BaseTestCase.get_data_dir(), 'loading',
'filtered_summary_small.csv'))
fsr.load()
self.assertEqual(1, fsr.num_reads)
except:
log.error(traceback.format_exc())
raise
def test_io_error(self):
"""
Test: Throws IOError in constructor
"""
log.info(TestFilteredSummaryReader.test_io_error.__doc__)
try:
FilteredSummaryReader('/i/dont/exits')
self.fail('Should have thrown IOError')
except IOError:
pass
except:
log.error(traceback.format_exc())
raise
def test_get_column_data(self):
"""
Test: Assert array equals when getting column data
"""
try:
log.info(TestFilteredSummaryReader.test_count_records.__doc__)
fsr = FilteredSummaryReader(os.path.join(BaseTestCase.get_data_dir(), 'loading', 'filtered_summary_small.csv'))
fsr.load()
ri_exp = ['m120128_025832_42129_c100277632550000001523007907041250_s2_p0/0',
'm120128_025832_42129_c100277632550000001523007907041250_s2_p0/1']
ri_act = []
data = fsr.data_as_numpy_array()
for row in data:
ri_act.append(row['ReadId'])
self.assertSequenceEqual(ri_exp, ri_act)
except:
log.error(traceback.format_exc())
raise
