多文件第一列相同，第二列合并成一行

drdachen

回复 9# substr函数

但是报错：

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
   

drdachen

回复 9# substr函数

但是报错：

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
   

vagrant_1220

file_list=($*)

echo -e "NAME\t${file_list[*]}"
for str in `awk '{print $1}' ${file_list[@]}|sort -u`
do
echo -e "\n${str}\t\c"
   for((i=0;i<${#file_list[@]};i++))
      do

      content=0
if [ $(grep -c "${str}" ${file_list[${i}]}) -gt 0 ];then

content=$(awk -v s=${str} '{if($1==s)print $2}' ${file_list[${i}]})

fi
echo -e "${content} \c"

     done

done
echo ""
[root@db test]# ./tn.sh a.txt b.txt
NAME    a.txt b.txt

ACC     0 1.0
ATG     1.3 2.0
ATT     1.1 2.3
CTG     1.2 2.1
[root@db test]# ./tn.sh a.txt b.txt c.txt
NAME    a.txt b.txt c.txt

ABC     0 0 3.0
ACC     0 1.0 0
ATG     1.3 2.0 2.1
ATT     1.1 2.3 2.3
CTG     1.2 2.1 2.1

结果

bb659030105

awk '{file_num+=FNR==1?1:0;len=length(a[$1]);if(len<file_num-1){for (i=1;i<=file_num-1;i++) a[$1]=a[$1]" 0.0"}a[$1]=a[$1]" "$2}END{for (i in a){for (k=1;k<=file_num-split(a[i],b," ");k++) a[i]=a[i]" 0.0";print i, a[i]}}' file1 file2 file3 .....

rulebook

1. awk 'FNR==1{f=f?f" "FILENAME:FILENAME} NR==FNR{a[$1]=$2;next} b[ARGIND]==0{for(i in a){a[i]=a[i]" @"};b[ARGIND]=1;s="";for(i=1;i<ARGIND;i++){s=s" "0}} {a[$1]=a[$1]?gensub(/@/,$2,"g",a[$1]):s" "$2} END{print "filename "f;for(i in a){gsub(/@/,0,a[i]);print i" "a[i]}}' s1 s2 s3

复制代码

substr函数

回复 10# drdachen

python2 p1.py a.txt b.txt c.txt

喔, 没有问题 [   ]

1. name        a        b        c
   
2. aa         11        111        1111
   
3. cc         33        333        3333
   
4. dd         44        0        0
   
5. bb         22        222        2222
   

复制代码