def merge(args):
filename = args.sample_set_file
sep = args.sep
name = args.name
desc = args.desc
sample_set_names = args.sample_set_names
# check arguments
if name is None:
name = 'merge'
if desc is None:
desc = name
if not sample_set_names:
logging.error('No sample set names specified')
return 1
sample_sets = dict((ss.name,ss) for ss in _parse_sample_sets(filename, sep))
new_value_dict = collections.defaultdict(lambda: 0)
for ss_name in sample_set_names:
if ss_name not in sample_sets:
logging.error('Sample set name "%s" not found.. Exiting.' % (ss_name))
return 1
ss = sample_sets[ss_name]
for k,v in ss.value_dict.iteritems():
if k in new_value_dict:
continue
new_value_dict[k] = v
ss = SampleSet(name, desc, new_value_dict.items())
print ss.to_json()
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 db_ss_printJSON(ssea_dir, matrix_dir, ss_id):
sample_sets_json_file = os.path.join(ssea_dir, 'sample_set.json')
bm = BigCountMatrix.open(matrix_dir)
samples = bm.colnames
ss = SampleSet.parse_json(sample_sets_json_file)[0]
membership = ss.get_array(samples)
d = ss.to_dict(membership)
d['_id'] = int(ss_id)
print json.dumps(d)
def newcohort(args):
sample_set_file = args.sample_set_file
cohort_file = args.cohort_file
sep = args.sep
cohort_samples = set(line.strip() for line in open(cohort_file))
for ss in _parse_sample_sets(sample_set_file, sep):
new_value_dict = {}
hits = 0
for k,v in ss.value_dict.iteritems():
if k in cohort_samples:
if v == 1:
hits += 1
new_value_dict[k] = v
if hits > 0:
ss = SampleSet(ss.name, ss.desc, new_value_dict.items())
print ss.to_json()
else:
logging.warning('Sample set %s has no hits' % (ss.name))
def db_ss_printJSON(ssea_dir, matrix_dir, ss_id):
sample_sets_json_file = os.path.join(ssea_dir,
'sample_set.json')
bm = BigCountMatrix.open(matrix_dir)
samples = bm.colnames
ss = SampleSet.parse_json(sample_sets_json_file)[0]
membership = ss.get_array(samples)
d = ss.to_dict(membership)
d['_id'] = int(ss_id)
print json.dumps(d)
def info(args):
input_dirs = args.input_dirs
if input_dirs is None:
logging.error('Please specify SSEA directories using "-d" or "--dir"')
return 1
for path in find_paths(input_dirs):
sample_set_json_file = os.path.join(path, Config.SAMPLE_SET_JSON_FILE)
sample_set = SampleSet.parse_json(sample_set_json_file)[0]
compname = computerize_name(sample_set.name)
print '\t'.join([compname, path])
def info(args):
input_dirs = args.input_dirs
if input_dirs is None:
logging.error('Please specify SSEA directories using "-d" or "--dir"')
return 1
for path in find_paths(input_dirs):
sample_set_json_file = os.path.join(path, Config.SAMPLE_SET_JSON_FILE)
sample_set = SampleSet.parse_json(sample_set_json_file)[0]
compname = computerize_name(sample_set.name)
print '\t'.join([compname, path])
def generate_random_sample_set(minsize, maxsize, samples):
size = random.randint(minsize, maxsize)
randsamples = random.sample(samples, size)
randvalues = np.random.random_integers(0,1,size=size)
values = []
for i in xrange(len(samples)):
if samples[i] in randsamples:
index = randsamples.index(samples[i])
values.append((samples[i],randvalues[index]))
return SampleSet(name="SS",
desc="Sample Set",
values=values)
def subset(args):
filename = args.sample_set_file
sep = args.sep
name = args.name
desc = args.desc
hit_set_names = args.hit_sets
miss_set_names = args.miss_sets
# check arguments
if name is None:
name = 'subset'
if desc is None:
desc = name
if not hit_set_names or not miss_set_names:
logging.error('Sample sets to be considered "hits" or "misses" '
'should be specified using --hit and --miss')
return 1
sample_sets = dict((ss.name,ss) for ss in _parse_sample_sets(filename, sep))
new_value_dict = {}
for ss_name in hit_set_names:
if ss_name not in sample_sets:
logging.error('Sample set name "%s" not found.. Exiting.' % (ss_name))
return 1
ss = sample_sets[ss_name]
for k,v in ss.value_dict.iteritems():
if v == 1:
new_value_dict[k] = 1
for ss_name in miss_set_names:
if ss_name not in sample_sets:
logging.error('Sample set name "%s" not found.. Exiting.' % (ss_name))
return 1
ss = sample_sets[ss_name]
for k,v in ss.value_dict.iteritems():
if v == 1:
new_value_dict[k] = 0
ss = SampleSet(name, desc, new_value_dict.items())
print ss.to_json()
def merge(args):
# get args
input_paths_file = args.input_paths_file
input_dirs = args.input_dirs
output_dir = args.output_dir
# check args
input_paths = set()
if input_paths_file is not None:
if not os.path.exists(input_paths_file):
logging.error('Input paths file "%s" not found' %
(input_paths_file))
else:
with open(input_paths_file) as fileh:
for line in fileh:
path = line.strip()
if check_path(path):
input_paths.add(path)
if input_dirs is not None:
input_paths.update(find_paths(input_dirs))
if len(input_paths) == 0:
logging.error('No valid SSEA results directories found.. Exiting.')
return 1
if not os.path.exists(output_dir):
logging.debug('Creating output directory "%s"' % (output_dir))
os.makedirs(output_dir)
# read paths already in output directory
existing_paths = set()
for path in glob.iglob(os.path.join(output_dir, "*")):
if os.path.exists(path) and os.path.isdir(path):
existing_paths.add(path)
# merge input paths
for src in input_paths:
sample_set_json_file = os.path.join(src, Config.SAMPLE_SET_JSON_FILE)
sample_set = SampleSet.parse_json(sample_set_json_file)[0]
dirname = computerize_name(sample_set.name)
dst = os.path.join(output_dir, dirname)
if os.path.exists(dst):
logging.error(
'Conflict when merging sample set name "%s" from path "%s"' %
(sample_set.name, src))
else:
logging.debug('Moving sample set "%s" from "%s" to "%s"' %
(sample_set.name, src, dst))
shutil.move(src, dst)
def test_sample_set_smt_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
fileh = open('tmp', 'w')
fields = ['Name', 'Description']
fields.extend(samples)
print >>fileh, '\t'.join(fields)
for i in xrange(len(sample_sets)):
ss = sample_sets[i]
fields = [ss.name, ss.desc]
for j in xrange(len(samples)):
if samples[j] in ss.value_dict:
fields.append(ss.value_dict[samples[j]])
else:
fields.append('')
print >>fileh, '\t'.join(map(str,fields))
fileh.close()
# read into sample sets
read_sample_sets = SampleSet.parse_smt('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')
def merge(args):
# get args
input_paths_file = args.input_paths_file
input_dirs = args.input_dirs
output_dir = args.output_dir
# check args
input_paths = set()
if input_paths_file is not None:
if not os.path.exists(input_paths_file):
logging.error('Input paths file "%s" not found' % (input_paths_file))
else:
with open(input_paths_file) as fileh:
for line in fileh:
path = line.strip()
if check_path(path):
input_paths.add(path)
if input_dirs is not None:
input_paths.update(find_paths(input_dirs))
if len(input_paths) == 0:
logging.error('No valid SSEA results directories found.. Exiting.')
return 1
if not os.path.exists(output_dir):
logging.debug('Creating output directory "%s"' % (output_dir))
os.makedirs(output_dir)
# read paths already in output directory
existing_paths = set()
for path in glob.iglob(os.path.join(output_dir, "*")):
if os.path.exists(path) and os.path.isdir(path):
existing_paths.add(path)
# merge input paths
for src in input_paths:
sample_set_json_file = os.path.join(src, Config.SAMPLE_SET_JSON_FILE)
sample_set = SampleSet.parse_json(sample_set_json_file)[0]
dirname = computerize_name(sample_set.name)
dst = os.path.join(output_dir, dirname)
if os.path.exists(dst):
logging.error('Conflict when merging sample set name "%s" from path "%s"' % (sample_set.name, src))
else:
logging.debug('Moving sample set "%s" from "%s" to "%s"' % (sample_set.name, src, dst))
shutil.move(src, dst)
