多文件第一列相同，第二列合并成一行

mswsg

a.txt

1. ATT 1.1
   
2. CTG 1.2
   
3. ATG 1.3
   

复制代码

b.txt

1. ATT 2.3
   
2. CTG 2.1
   
3. ATG 2.0
   
4. ACC 1.0
   

复制代码

c.txt

1. ATT 2.3
   
2. CTG 2.1
   
3. ATG 2.1
   
4. ABC 3.0

复制代码

类似的文件有N个。注意ACC 1.0 在 a.txt ，c.txt 没出现则是0
结果文件是

1. Name a.txt b.txt c.txt
   
2. ATT 1.1 2.3 2.3
   
3. CTG 1.2 2.1 2.1
   
4. ATG 1.3 2.0 2.1
   
5. ACC 0 1.0 0
   
6. ABC 0 0 3.0

复制代码

希望命令。。我指定两个文件，则比较两个，指定3个，则比较3个，指定四个则比较4个。python，awk 语言不限。。。。

substr函数

回复 1# mswsg

[   ]
python2 a.txt b.txt
python2 a.txt b.txt c.txt
python2 a.txt b.txt c.txt d.txt ...

1. #!/usr/bin/python2
   
2. # coding: utf-8
   
3. 
   
4. import sys
   
5. 
   
6. KEY = sys.argv[1:]
   
7. DIC = {}
   
8. 
   
9. for F in KEY:
   
10.     for L in open(F):
    
11.         k, v = L.split()
    
12.         DIC.setdefault(k, {})[F] = v
    
13. 
    
14. print 'name\t', '\t'.join(KEY)
    
15. 
    
16. for k, v in DIC.items():
    
17.     print k, '\t', '\t'.join(v[i] if i in v else '0' for i in KEY)
    
18. 
    

复制代码

waker

1. 
   
2. awk 'FNR==1{f[fi++]=FILENAME}
   
3. !cl[$1]++{c[ci++]=$1}
   
4. {d[FILENAME,$1]=$2}
   
5. END{
   
6. printf "Name\t"
   
7. for(j=0;j<fi;j++) printf f[j]"\t"
   
8. print ""
   
9. for(i=0;i<ci;i++){
   
10. printf c[i]"\t"
    
11. for(j=0;j<fi;j++) printf  d[f[j],c[i]]+0"\t"
    
12. print ""
    
13. }
    
14. }' filea fileb filec
    

复制代码

waker

http://bbs.chinaunix.net/thread-4162357-1-1.html

大神们给的这些例子一点帮助没有?

haooooaaa

1. awk -vn="name" 'function w(m,p){while(split(a[m],t)!=b+1)sub(p," 0&",a[m])}FNR<2{n=n" "FILENAME;++b}{a[$1]=a[$1]?a[$1]" "$2:$0;w($1," [^ ]*$")}END{print n;for(i in a){w(i,"$");print a[i]}}' a b c
   
2. name a b c
   
3. ABC 0 0 3.0
   
4. ACC 0 1.0 0
   
5. CTG 1.2 2.1 2.1
   
6. ATG 1.3 2.0 2.1
   
7. ATT 1.1 2.3 2.3

复制代码

sync_1521

1. [root@test]# awk '{if(FNR==1){t=t?t" "FILENAME:FILENAME};a[$1];b[$1" "FILENAME]=$2}END{print "Name "t;for(i in a){s="";for(j=1;j<=split(t,c," ");j++){s=b[i" "c[j]]?s" "b[i" "c[j]]:s" "0};print i" "s}}' a.txt b.txt c.txt
   
2. Name a.txt b.txt c.txt
   
3. CTG  1.2 2.1 2.1
   
4. ABC  0 0 3.0
   
5. ACC  0 1.0 0
   
6. ATG  1.3 2.0 2.1
   
7. ATT  1.1 2.3 2.3

复制代码

tc1989tc

1. #!/bin/perl -w
   
2. use strict;
   
3. 
   
4. package T;
   
5. 
   
6. sub new {
   
7.         my $class = shift;
   
8.         my $self = {};
   
9.         ${$self}{'allFiles'} = shift;
   
10.         #print "allfiles: ", ${$self{'allFiles'}}[0];
    
11.         return bless $self, $class;
    
12. }
    
13. 
    
14. sub load {
    
15.         my $self = shift;
    
16.        
    
17.         # load txt to hash, hash key is file names
    
18.         for my $file (@{${$self}{'allFiles'}}) {
    
19.                 #print "file: ", $file, " \n";
    
20.                 open(my $fh,  $file) or die "open file fail\n";
    
21.                 my %fileHash;
    
22.                 while (<$fh>) {
    
23.                         chomp ;
    
24.                         (my $k, my $v) = split;
    
25.                         $fileHash{$k} = $v;
    
26.                         #print $k,$v;
    
27.                 }
    
28.                           close $fh;
    
29.                 ${$self}{$file} = \%fileHash;
    
30.         }
    
31. }
    
32. 
    
33. sub uniqkey {
    
34.         my $self = shift;
    
35.        
    
36.         my @allkeys;
    
37.         for my $file (@{${$self}{'allFiles'}}) {
    
38.                 my @lists = keys %{${$self}{$file}};
    
39.                 push @allkeys, @lists;
    
40.         }
    
41.         my %hashkeys;
    
42.         %hashkeys = map {$_ => 1} @allkeys;
    
43.        
    
44.         # store keys
    
45.         ${$self}{'filekeys'} = [keys %hashkeys];
    
46. }
    
47. 
    
48. sub processfiles {
    
49.         my $self = shift;
    
50.         ${$self}{'result'} = {};
    
51. 
    
52.         # foreach keys
    
53.         for my $key (@{${$self}{'filekeys'}}) {
    
54.                 my $strs= $key;
    
55. 
    
56.                 # Check if exist in all files
    
57.                 for my $file (@{${$self}{'allFiles'}}) {
    
58.                         if (defined(${${$self}{$file}}{$key})) {
    
59.                                 $strs = join("\t",$strs, ${${$self}{$file}}{$key});       
    
60.                         } else {
    
61.                                 $strs = join("\t",$strs, 0);       
    
62.                         }
    
63.                 }
    
64.                 #print $strs, "\n";
    
65.                
    
66.                 ${${$self}{'result'}}{$key} = $strs;
    
67.         }
    
68.         ${$self}{'TITLE'} = join("\t", 'NAME', @{${$self}{'allFiles'}});
    
69. }
    
70. 
    
71. sub printresult {
    
72.         my $self = shift;
    
73.         print ${$self}{'TITLE'}, "\n";
    
74.        
    
75.         for (keys %{${$self}{'result'}}) {
    
76.                 print ${${$self}{'result'}}{$_}, "\n";
    
77.         }
    
78. }
    
79. my $files=['a.txt', 'b.txt', 'c.txt'];
    
80. my $a = T->new($files);
    
81. $a->load();
    
82. $a->uniqkey();
    
83. $a->processfiles();
    
84. $a->printresult();

复制代码

./test.pl
NAME        a.txt        b.txt        c.txt
ABC        0        0        3.0
ACC        0        1.0        0
ATT        1.1        2.3        2.3
CTG        1.2        2.1        2.1
ATG        1.3        2.0        2.1

drdachen

回复 6# substr函数


请问如何在linux下执行这个python脚本？谢谢

substr函数

回复 8# drdachen


    python2 thisscript.py a.txt b.txt c.txt

drdachen

回复 9# substr函数

但是报错，是怎么回事呢？

代码如下：

da@da:~/try$ cat a.txt
aa 11
bb 22
cc 33
dd 44
da@da:~/try$ cat b.txt
aa 111
bb 222
cc 333
da@da:~/try$ cat c.txt
aa 1111
bb 2222
cc 3333

da@da:~/try$ cat 1.py
#!/usr/bin/python2
# coding: utf-8

import sys

KEY = sys.argv[1:]
DIC = {}

for F in KEY:
    for L in open(F):
        k, v = L.split()
        DIC.setdefault(k, {})[F] = v

print 'name\t', '\t'.join(KEY)

for k, v in DIC.items():
    print k, '\t', '\t'.join(v if i in v else '0' for i in KEY)
da@da:~/try$ python2 1.py a.txt b.txt c.txt
Traceback (most recent call last):
  File "1.py", line 11, in <module>
    k, v = L.split()
ValueError: need more than 0 values to unpack