本文实例讲述了Python使用defaultdict读取文件各列的方法。分享给大家供大家参考，具体如下：
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
|
#!/usr/bin/python"""USAGE: python *.py align_SNP_site out_file"""import sys#import timefrom 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) |
希望本文所述对大家Python程序设计有所帮助。
