Mercurial > repos > computationaltranscriptomics > vgx_converter
changeset 8:1ae351222569 draft
Uploaded
author | computationaltranscriptomics |
---|---|
date | Tue, 10 May 2016 19:21:45 -0400 |
parents | 006d30548237 |
children | 26655854fac5 |
files | vgx_converter.py |
diffstat | 1 files changed, 76 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/vgx_converter.py Tue May 10 19:21:45 2016 -0400 @@ -0,0 +1,76 @@ +#!/usr/bin/python + +import sys # +import csv +import json +import shlex + + +def __main__(): + + arg_names = ['command', "network", "delimiter", "attributes", "output"] + args = dict(zip(arg_names, sys.argv)) + print args + + idc = 0 # counter for the ids + ids = {} # dictionary with id and name correlation + keys = [] + + nodes = [] + links = [] + + delim = {} + delim['tab'] = '\t' + delim['space'] = ' ' + + ################################################# + data = {} + with open(sys.argv[1], 'r') as f: + reader = csv.reader(f, delimiter=delim[sys.argv[2]]) + for row in reader: # iterate through each line + p1 = shlex.split(row[0])[0] + p2 = shlex.split(row[2])[0] + + if p1 not in ids: + ids[p1] = idc + idc = idc + 1 + nodes.append({'id': ids[p1], 'name': p1 }) + if p2 not in ids: + ids[p2] = idc + idc = idc + 1 + nodes.append({'id': ids[p2], 'name': p2 }) + + links.append({'source': ids[p1], 'target': ids[p2]}) + f.close() + + data = { 'graph': {'nodes': nodes, 'edges': links}} + + if args['attributes'] != 'None': # None for Galaxy + data['some'] = 'not in here' + + # process attributes list + with open(sys.argv[3]) as f: + reader = csv.reader(f, delimiter='\t') + ids_keys = ids.keys() + for row in reader: + propscnt = 0 + if row[0] in ids_keys: + pos = ids[row[0]] + #for props in range(len(row)-1): + # nodes[pos]['property'+str(propscnt)] = row[props+1] + # propscnt = propscnt +1 + metadata = {} + for props in range(len(row)-1): + metadata['property'+str(propscnt)] = row[props+1] + propscnt = propscnt +1 + print metadata + nodes[pos]['metadata'] = metadata + f.close() + + # write json data back to spec ified output file + with open(sys.argv[4], 'w') as out: + json.dump(data, out) + out.close() + +if __name__ == "__main__": + __main__() \ No newline at end of file