Python中通过defaultdict获得文件各列的代码实例

#!/usr/bin/python
"""USAGE: python *.py align_SNP_site out_file"""
import sys
#import time
from collections import Counter
#t0=time.clock()
info=open(sys.argv[1])
fast=sys.argv[2]
d_c = {}
d1={}
d2={}
for line in info:
    cols=line.strip().split("\t")
    if cols[0] == "SNP pattern":
        continue
    else:
        d1.setdefault(cols[4],[]).append(cols[1])
        d2.setdefault(cols[7],[]).append(cols[1])
    #d1.setdefault(cols[0],[]).append(cols[5])
    #d2[cols[0]] = "\t".join(cols[0:3])
info.close()
print len(d1)
print len(d2)
my_list=[]
ref_fa = open("some_example.fasta", 'r')
for i in ref_fa.readlines():
    if i.startswith(">"):
        my_list.append(i.rstrip())
ref_fa.close()
print len(my_list)
#sys.exit()
result = open(fast,'w')
for k,v in d1.iteritems():
    cnt1 = Counter(v)
    #print cnt1
    result.write("%s\t" % k)
    for i in sorted(cnt1.items(), key = lambda x: x[1], reverse=True):
        result.write("%s\t%d\t"%(i[0],i[1]))
    result.write("\n")
for k,v in d2.iteritems():
    cnt2 = Counter(v)
    #print cnt2
    result.write("%s\t" % k)
    for i in sorted(cnt2.items(), key = lambda x: x[1], reverse=False):
        result.write("%s\t%d\t"%( i[0],i[1]))
    result.write("\n")
#t1=time.clock()
#print (t1-t0)