awk - 拉出对列并获取出现次数

Question

我有一个表模式 - 以逗号分隔的列名。为了清楚起见，我将它们放在每行一列中，如下所示

$ cat cols_name.txt
id
resp
x_amt
rate1
rate2
rate3
pay1
pay2
rate_r1
rate_r2
x_rate1
x_rate2
x_rate3
x_rate_r1
x_rate_r2
x_pay1
x_pay2
rev1
x_rev1

我需要找出与列对 ( pay1 -> x_pay1 ) 匹配的对，并将它们列在一起作为中间输出，如下所示

x_rate1 rate1
x_rate2 rate2
x_rate3 rate3
x_pay1 pay1
x_pay2 pay2
x_rate_r1 rate_r1
x_rate_r2 rate_r2
x_rev1 rev1

然后最后将频率打印为

 pay 2
 rate 3
 rate_r 2
 rev 1

在我尝试获取中间输出时，下面的 awk 命令不起作用。

awk ' NR==FNR { if( $1~/^x_/ ) a[$1]=1 ; next }  $1~/"x_" a[$1]/ { print $0 } ' cols_name.txt cols_name.txt

它没有打印任何东西。可以帮忙解决一下吗

Answer 1

这里是单程 awk 来完成它：

 awk '/^x_/ {xk[$0]; next} {s=$0; sub(/[0-9]+$/, "", s); xv[$0]=s} END {for (i in xv) if ("x_" i in xk) {print "x_" i, i; ++fq[xv[i]]}; print "== Summary =="; for (i in fq) print i, fq[i]}' file

x_rev1 rev1
x_rate1 rate1
x_rate2 rate2
x_rate3 rate3
x_rate_r1 rate_r1
x_pay1 pay1
x_rate_r2 rate_r2
x_pay2 pay2
== Summary ==
rate_r 2
rate 3
rev 1
pay 2

更易读的形式：

awk '
/^x_/ {
   xk[$0]
   next
}
{
   s = $0
   sub(/[0-9]+$/, "", s)
   xv[$0] = s
}
END {
   for (i in xv)
      if ("x_" i in xk) {
         print "x_" i, i
         ++fq[xv[i]]
      }
   print "== Summary =="
   for (i in fq)
      print i, fq[i]
}' file

Answer 2

在每个 Unix 机器上的任何 shell 中使用任何 awk，并假设输入文件中的每个条目只出现一次，如您发布的示例所示：

$ cat tst.awk
{
    sub(/^x_/,"")
    pair = "x_" $0 OFS $0
    if ( ++count[pair] == 2 ) {
        print pair
        sub(/[0-9]+$/,"")
        freq[$0]++
    }
}
END {
    print "---"
    for (key in freq) {
        print key, freq[key]
    }
}

$ awk -f tst.awk cols_name.txt
x_rate1 rate1
x_rate2 rate2
x_rate3 rate3
x_rate_r1 rate_r1
x_rate_r2 rate_r2
x_pay1 pay1
x_pay2 pay2
x_rev1 rev1
---
rate_r 2
rev 1
rate 3
pay 2

Answer 3

假设文件实际上是：

id,resp,x_amt,rate1,rate2,rate3,pay1,pay2,rate_r1,rate_r2,x_rate1,x_rate2,x_rate3,x_rate_r1,x_rate_r2,x_pay1,x_pay2,rev1,x_rev1

按照原帖中的建议（不是很清楚），使用 GNU awk：

awk '{ split($0,map,",");for (i in map) { map1[map[i]]="1" } for (i in map) { if ( map[i] ~ /^x_/ ) { hd=gensub("x_","","g",map[i]);hd1=gensub("[[:digit:]]","","g",hd);if (map1[hd]=="1") { map2[hd1]++;print map[i]" "hd } } } printf "\n";for (i in map2) { print i" "map2[i] } }' cols_name.txt

解释：

awk '{ 
        split($0,map,",");                                     # Split the line into an array called map, using comma as the separator
        for (i in map) { 
           map1[map[i]]="1"                                    # Loop through map and create another array map1 with the values of map as indexes
        } 
        for (i in map) { 
           if ( map[i] ~ /^x_/ ) {                            
               hd=gensub("x_","","g",map[i]);                  # Loop through map and it the value is prefixed with "x_", remove it, reading the result into hd
               hd1=gensub("[[:digit:]]","","g",hd);            # Take any digits out of hd and read into hd1
               if (map1[hd]=="1") {
                 map2[hd1]++;                                  # Create a third array map2 with the index hd1 and the value an incrementing counter 
                 print map[i]" "hd                             # If a match exists in the map1 array, print the match
               } 
            } 
         } 
         printf "\n";
         for (i in map2) { 
            print i" "map2[i]                                  # Loop through the count array and print the values
         }   
       }' cols_name.txt

输出：

x_pay2 pay2
x_rev1 rev1
x_rate1 rate1
x_rate2 rate2
x_rate3 rate3
x_rate_r1 rate_r1
x_rate_r2 rate_r2
x_pay1 pay1

rate_r 2
rate 3
rev 1
pay 2

Answer 4

对于您展示的示例，您能否尝试在 GNU awk 中使用展示的示例进行跟踪、编写和测试。

awk -v s1="x_" '
FNR==NR{
  if($0~"^"s1){
    arr[$0]=$0
  }
  next
}
((s1 $0) in arr){
  print arr[s1 $0],$0
  gsub(/^x_|[0-9]+$/,"",$0)
  sum[$0]++
}
END{
  for(i in sum){
    print i,sum[i]
  }
}
'  Input_file  Input_file

说明：为上述添加详细说明。

awk -v s1="x_" '             ##Starting awk program from here.
FNR==NR{                     ##Checking condition which will be TRUE when first time Input_file is being read.
  if($0~"^"s1){              ##Checking condition if line starts with s1 value then do following.
    arr[$0]=$0               ##Creating arr with current line index and value with current line.
  }
  next                       ##next will skip all further statements from here.
}
((s1 $0) in arr){            ##Checking condition if s1 $0 is present in arr then do following.
  print arr[s1 $0],$0        ##Printing value of array with current line.
  gsub(/^x_|[0-9]+$/,"",$0)  ##Globally substituting starting x_ AND ending digits with NULL in current line.
  sum[$0]++                  ##Creating sum with inceasing value of 1 each time cursor comes here.
}
END{                         ##Starting END block of this question from here.
  for(i in sum){             ##Traversing through sum elements here.
    print i,sum[i]           ##Printing key and value of sum in here.
  }
}
'  Input_file  Input_file    ##Mentioning Input_file names here.