def term_types_in_paper(paper): """For each paper, count how often different term types appear. Possible term types: biological_process molecular_function cellular_component """ # term types (ontologies) in a given paper tt_count = {} go_con = mysqlConnect() go_cursor = go_con.cursor() for prec in paper: go_id = prec['go_id'] try: term_type = gu.go_acc_to_term_type(go_id, go_cursor) except IndexError: print go_id, "may be deprecated" continue # tt_count[term_type] = count of that term tt_count[term_type] = tt_count.get(term_type, 0) + 1 go_con.close() return tt_count # count of term types
def term_types_in_paper(paper): """For each paper, count how often different term types appear. Possible term types: biological_process molecular_function cellular_component """ # term types (ontologies) in a given paper tt_count = {} go_con = mysqlConnect() go_cursor = go_con.cursor() for prec in paper: go_id = prec['go_id'] try: term_type = gu.go_acc_to_term_type(go_id, go_cursor) except IndexError: print go_id,"may be deprecated" continue # tt_count[term_type] = count of that term tt_count[term_type] = tt_count.get(term_type,0) + 1 go_con.close() return tt_count # count of term types
outfile = sys.stdout for o, a in opts: if o in ('-i','--infile'): infile = a elif o in ('-o','--outfile'): outfile = open(a,"w") elif o in ('-f','--field'): go_acc_field = int(a) print "infile", infile if infile: for inline in file(infile): sp_id = inline.strip().split()[3] go_acc = inline.strip().split()[go_acc_field-1] go_level = gu.go_level(go_acc,goc) try: go_term_type = gu.go_acc_to_term_type(go_acc, goc) except IndexError: outfile.write("%s\t%s\t%.1f\t%s\n" % (go_acc, "NOTERMTYPE", go_level, sp_id)) continue outfile.write("%s\t%s\t%.1f\t%s\n" % (go_acc, go_term_type, go_level, sp_id)) else: go_acc = args[0] go_level = gu.go_level(go_acc,goc) go_term_type = gu.go_acc_to_term_type(go_acc, goc) outfile.write("%s\t%s\t%.1f\n" % (go_acc, go_term_type, go_level)) gocon.close() if outfile != sys.stdout: outfile.close()