去掉最大值和最小值然后求平均值

yestreenstars

回复 9# jason680


    嗯，看出来了，确实如此，那我得好好研究一下你的代码了，虽然有点难以看懂~

peawseshc

强人啊，学习

yinyuemi

回复 1# yestreenstars


    去掉一个最高分，去掉一个最低分，最后得分。。。

cao627

回复 9# jason680

Description: (mask them to see description)
  x ($1) for key name
  p[x] for full name
  c[x] for count
  p[x,1] for total $4
  p[x,2] for total $5
  p[x,3] for Max $4, and the same line $5 be p[x,4]
  p[x,5] for Min $4, and the same line $5 be p[x,6]


$ time awk '{x=$1;p[x]=$1" "$2" "$3;if(!c[x]++)for(n=0;n++<2p[x,n]=p[x,n+2]=p[x,n+4]=$(n+3);else{p[x,1]+=$4;p[x,2]+=$5;if(p[x,3]<$4){p[x,3]=$4;p[x,4]=$5}if(p[x,5]>$4){p[x,5]=$4;p[x,6]=$5}}}END{for(x in c){if(c[x]>=3){p[x,1]-=(p[x,3]+p[x,5]);p[x,2]-=(p[x,4]+p[x,6]);c[x]-=2}print p[x],p[x,1]/c[x],p[x,2]/c[x]}}' FILE1

beautiful！



   

blackold

回复 1# yestreenstars


    try:

1. awk '!c[$1]++{h[$1]=$1" "$2" "$3;max[$1]=min[$1]=$4;m[$1]=n[$1]=$5;}{if($4>max[$1]){max[$1]=$4;m[$1]=$5;}else if($4<min[$1]){min[$1]=$4;n[$1]=$5;}a[$1]+=$4;b[$1]+=$5;}END{for(i in c){if(c[i]>=3){a[i]-=max[i]+min[i];b[i]-=m[i]+n[i];c[i]-=2;}print h[i],a[i]/c[i],b[i]/c[i];}}' urfile

复制代码

blackold

测试:

1. $ wc -l urfile
   
2. 297620 urfile

复制代码

1. $ time awk '!c[$1]++{h[$1]=$1" "$2" "$3;max[$1]=min[$1]=$4;m[$1]=n[$1]=$5;}{if($4>max[$1]){max[$1]=$4;m[$1]=$5;}else if($4<min[$1]){min[$1]=$4;n[$1]=$5;}a[$1]+=$4;b[$1]+=$5;}END{for(i in c){if(c[i]>=3){a[i]-=max[i]+min[i];b[i]-=m[i]+n[i];c[i]-=2;}print h[i],a[i]/c[i],b[i]/c[i];}}' urfile
   
2. Ken Black Driver 84.67 47.33
   
3. Anne Red Student 60.86 105.27
   
4. Peter Blue Teacher 77.9499 50.9545
   
5. Sue Yellow Worker 114.58 66.3602
   
6. awk  urfile  4.58s user 0.06s system 99% cpu 4.641 total
   

复制代码

1. $ time awk '{x=$1;p[x]=$1" "$2" "$3;if(!c[x]++)for(n=0;n++<2;)p[x,n]=p[x,n+2]=p[x,n+4]=$(n+3);else{p[x,1]+=$4;p[x,2]+=$5;if(p[x,3]<$4){p[x,3]=$4;p[x,4]=$5}if(p[x,5]>$4){p[x,5]=$4;p[x,6]=$5}}}END{for(x in c){if(c[x]<=2){x4=p[x,1]/c[x];x5=p[x,2]/c[x]}else{x4=(p[x,1]-p[x,3]-p[x,5])/(c[x]-2);x5=(p[x,2]-p[x,4]-p[x,6])/(c[x]-2)}print p[x],x4,x5}}' urfile
   
2. Ken Black Driver 84.67 47.33
   
3. Anne Red Student 60.86 105.27
   
4. Peter Blue Teacher 77.9499 50.9545
   
5. Sue Yellow Worker 114.58 66.3602
   
6. awk  urfile  7.50s user 0.06s system 98% cpu 7.641 total

复制代码

1. $ time awk '{a[$1]=a[$1]!=""?a[$1]" "$4:$4;b[$1,$4]=$5;NF-=2;c[$1]=$0}END{for(i in a){k=split(a[i],d," ");asort(d,e);if(k==1)print c[i],e[1],b[i,e[1]];if(k==2){m=(e[1]+e[2])/2;n=(b[i,e[1]]+b[i,e[2]])/2;print c[i],m,n}if(k>=3){for(j=2;j<k;j++){m+=e[j];n+=b[i,e[j]]}print c[i],m/(k-2),n/(k-2)}m=n=0}}' urfile
   
2. 
   
3. .... 还在运行中

复制代码

pix77

看到这么一坨，头都大了，没看下去的动力了

yestreenstars

回复 17# blackold


    囧rz..黑哥你就别笑话我了~

jason680

回复 17# blackold


Thank you for your idea and test time report.
That's great naming rule for array by max/m and min/n.