分组一般都是用x[$2]=x[$3]....的方式来实现的,其中x[$2]中的$2为要分的组,当然可以多个分组,x[$3]为要处理的值
[root@localhost wms]# cat groupandsum.txt
John|P|physics|2|02/12/2002
Rick|L|Mechanical|1|02/12/2002
Jack|T|electrical|3|03/12/2003
Phil|R|Electrucal|1|03/12/2003
Mike|T|mechamical|2|10/12/2003
Paul|R|chemical|2|10/12/2003
John|T|chemical|3|10/12/2002
Tony|N|chemical|2|10/11/2003
James|R|Electrucal|2|10/11/2003
分组求和:
一般求和:
awk -F '|' '{sum1 += $4} END {print sum1}' groupandsum.txt
分组求和:
一次分组:
[root@localhost wms]# awk -F "|" '{x[$5]+=$4} END{for( i in x ){print i,x[i]}}' groupandsum.txt
03/12/2003 4
02/12/2002 3
10/12/2002 3
10/12/2003 4
10/11/2003 4
二次分组:
[root@localhost wms]# awk -F "|" '{x[$5"-"$3]+=$4} END{for( i in x ){print i,x[i]}}' groupandsum.txt
10/12/2002-chemical 3
03/12/2003-Electrucal 1
03/12/2003-electrical 3
02/12/2002-Mechanical 1
10/12/2003-mechamical 2
02/12/2002-physics 2
10/11/2003-Electrucal 2
10/11/2003-chemical 2
10/12/2003-chemical 2
[root@localhost wms]#
格式化处理:
awk -F'|' '{a[$5]+=$4}END{for(i in a)printf("%s\t%d\n",i,a[i])}' groupandsum.txt
分组求平均值:
一般情况下求平均:
[root@localhost wms]# awk -F'|' '{sum+=$4} END {print "Average = ", sum/NR}' groupandsum.txt
Average = 2
分组求平均:
[root@localhost wms]# awk -F'|' '{a[$5]+=$4;ca[$5]++}END{for(i in a)printf("%s\t%d\taverage:%d\n",i,a[i],a[i]/ca[i])}' groupandsum.txt
03/12/2003 4 average:2
02/12/2002 3 average:1
10/12/2002 3 average:3
10/12/2003 4 average:2
10/11/2003 4 average:2
注意了,/ 求是整数,% 求余数
/ 也能求得完整的值,只是没有显示而已,用%.2f就可以显示了
[root@localhost wms]# awk -F'|' '{a[$5]+=$4;ca[$5]++}END{for(i in a)printf("%s\t%d\t%.2f\n",i,a[i],a[i]/ca[i])}' groupandsum.txt
03/12/2003 4 2.00
02/12/2002 3 1.50
10/12/2002 3 3.00
10/12/2003 4 2.00
10/11/2003 4 2.00
分组求最大最小
一般情况下求最大最小:
[root@localhost wms]# awk -F'|' 'BEGIN {max=0}{if($4>max){max=$4}} END{print max}' groupandsum.txt
3
分组情况求最大最小:
[root@localhost wms]# awk -F'|' '{if($4>x[$5]){x[$5]=$4}} END{for (i in x) print i,x[i] }' groupandsum.txt
03/12/2003 3
02/12/2002 2
10/12/2002 3
10/12/2003 2
10/11/2003 2
分组整理字符:
a 111
a 222
a 333
b 444
d 555
>awk '{x[$1]=x[$1]"\n"$2} END{for( i in x ){print i":", x[i]}}' juhe.txt
a:
111
222
333
b:
444
555
ORACLE开发优化群:134426686 欢迎加入
[root@localhost wms]# cat groupandsum.txt
John|P|physics|2|02/12/2002
Rick|L|Mechanical|1|02/12/2002
Jack|T|electrical|3|03/12/2003
Phil|R|Electrucal|1|03/12/2003
Mike|T|mechamical|2|10/12/2003
Paul|R|chemical|2|10/12/2003
John|T|chemical|3|10/12/2002
Tony|N|chemical|2|10/11/2003
James|R|Electrucal|2|10/11/2003
分组求和:
一般求和:
awk -F '|' '{sum1 += $4} END {print sum1}' groupandsum.txt
分组求和:
一次分组:
[root@localhost wms]# awk -F "|" '{x[$5]+=$4} END{for( i in x ){print i,x[i]}}' groupandsum.txt
03/12/2003 4
02/12/2002 3
10/12/2002 3
10/12/2003 4
10/11/2003 4
二次分组:
[root@localhost wms]# awk -F "|" '{x[$5"-"$3]+=$4} END{for( i in x ){print i,x[i]}}' groupandsum.txt
10/12/2002-chemical 3
03/12/2003-Electrucal 1
03/12/2003-electrical 3
02/12/2002-Mechanical 1
10/12/2003-mechamical 2
02/12/2002-physics 2
10/11/2003-Electrucal 2
10/11/2003-chemical 2
10/12/2003-chemical 2
[root@localhost wms]#
格式化处理:
awk -F'|' '{a[$5]+=$4}END{for(i in a)printf("%s\t%d\n",i,a[i])}' groupandsum.txt
分组求平均值:
一般情况下求平均:
[root@localhost wms]# awk -F'|' '{sum+=$4} END {print "Average = ", sum/NR}' groupandsum.txt
Average = 2
分组求平均:
[root@localhost wms]# awk -F'|' '{a[$5]+=$4;ca[$5]++}END{for(i in a)printf("%s\t%d\taverage:%d\n",i,a[i],a[i]/ca[i])}' groupandsum.txt
03/12/2003 4 average:2
02/12/2002 3 average:1
10/12/2002 3 average:3
10/12/2003 4 average:2
10/11/2003 4 average:2
注意了,/ 求是整数,% 求余数
/ 也能求得完整的值,只是没有显示而已,用%.2f就可以显示了
[root@localhost wms]# awk -F'|' '{a[$5]+=$4;ca[$5]++}END{for(i in a)printf("%s\t%d\t%.2f\n",i,a[i],a[i]/ca[i])}' groupandsum.txt
03/12/2003 4 2.00
02/12/2002 3 1.50
10/12/2002 3 3.00
10/12/2003 4 2.00
10/11/2003 4 2.00
分组求最大最小
一般情况下求最大最小:
[root@localhost wms]# awk -F'|' 'BEGIN {max=0}{if($4>max){max=$4}} END{print max}' groupandsum.txt
3
分组情况求最大最小:
[root@localhost wms]# awk -F'|' '{if($4>x[$5]){x[$5]=$4}} END{for (i in x) print i,x[i] }' groupandsum.txt
03/12/2003 3
02/12/2002 2
10/12/2002 3
10/12/2003 2
10/11/2003 2
分组整理字符:
a 111
a 222
a 333
b 444
d 555
>awk '{x[$1]=x[$1]"\n"$2} END{for( i in x ){print i":", x[i]}}' juhe.txt
a:
111
222
333
b:
444
555
ORACLE开发优化群:134426686 欢迎加入
来自 “ ITPUB博客 ” ,链接:http://blog.itpub.net/25960404/viewspace-1818866/,如需转载,请注明出处,否则将追究法律责任。
转载于:http://blog.itpub.net/25960404/viewspace-1818866/