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 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 _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 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 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)
