def _parse_sample_sets(filename, sep):
if not os.path.exists(filename):
logging.error("Sample set file '%s' not found" % (filename))
sys.exit(1)
ext = os.path.splitext(filename)[-1]
if ext == '.smx':
for ss in SampleSet.parse_smx(filename, sep):
yield ss
elif ext == '.smt':
for ss in SampleSet.parse_smt(filename, sep):
yield ss
elif ext == '.json':
for ss in SampleSet.parse_json(filename):
yield ss
else:
logging.error('suffix not recognized (.smx, .smt, or .json)')
def test_sample_set_smx_parser(self):
# generate samples
samples = ['S%d' % (i) for i in range(10000)]
# generate sample sets
N = 100
minsize = 1
maxsize = N
sample_sets = []
for i in xrange(N):
sample_sets.append(generate_random_sample_set(minsize,maxsize,samples))
# write to a temp file
names = ['Name'] + [ss.name for ss in sample_sets]
descs = ['Desc'] + [ss.desc for ss in sample_sets]
with open('tmp', 'w') as fileh:
print >>fileh, '\t'.join(names)
print >>fileh, '\t'.join(descs)
for i in xrange(len(samples)):
fields = [samples[i]]
for j in xrange(len(sample_sets)):
if samples[i] in sample_sets[j].value_dict:
fields.append(sample_sets[j].value_dict[samples[i]])
else:
fields.append('')
print >>fileh, '\t'.join(map(str,fields))
fileh.close()
# read into sample sets
read_sample_sets = SampleSet.parse_smx('tmp')
self.assertTrue(len(read_sample_sets) == N)
self.assertTrue(len(read_sample_sets) == len(sample_sets))
for i in xrange(N):
ss = sample_sets[i]
rss = read_sample_sets[i]
self.assertEqual(rss.name, ss.name)
self.assertEqual(rss.desc, ss.desc)
self.assertTrue(set(rss.value_dict.items()) ==
set(ss.value_dict.items()))
a = ss.get_array(samples)
b = rss.get_array(samples)
self.assertTrue(np.array_equal(a, b))
os.remove('tmp')