linux 中awk命令实现根据一列数值的大小筛选指定列多个类别的最大或者最小项

 

001、

(base) [b20223040323@admin1 test2]$ cat 003.txt  ## 测试数据如下，第一列有多个项，且部分项有重复，实现根据第三列筛选出最大的项
ID=gene-TRNAC-GCA       rna-TRNAC-GCA   72
ID=gene-ATP5O   rna-XM_005674665.3      793
ID=gene-ITSN1   rna-XR_001917533.1      4437
ID=gene-ITSN1   rna-XM_018043229.1      9110
ID=gene-ITSN1   rna-XM_018041619.1      9323
ID=gene-ITSN1   rna-XM_018042670.1      9247
ID=gene-ITSN1   rna-XM_018042157.1      9141
ID=gene-ITSN1   rna-XM_018043907.1      5462
ID=gene-CRYZL1  rna-XM_005674667.3      1609
ID=gene-CRYZL1  rna-XM_013962888.2      1588
ID=gene-CRYZL1  rna-XM_005674668.3      1600
ID=gene-CRYZL1  rna-XM_013962952.2      1749
ID=gene-CRYZL1  rna-XM_005674666.3      1745
ID=gene-DONSON  rna-XM_018045976.1      2568
ID=gene-SON     rna-XR_001295570.2      8568
ID=gene-SON     rna-XM_005674676.3      8488
ID=gene-SON     rna-XM_005674677.3      8409
ID=gene-SON     rna-XM_005674679.3      7645
ID=gene-SON     rna-XM_005674680.3      8005
ID=gene-GART    rna-XM_005674671.3      4934

 

002、输出最大项的实现方法如下：

(base) [b20223040323@admin1 test2]$ awk '{if(ay1[$1] == "") {ay1[$1] = $3; ay2[$1] = $0};if(ay1[$1] < $3){ay1[$1] = $3; ay2[$1] = $0} } END{for(i in ay1) {print ay2[i]}}' 003.txt
ID=gene-GART    rna-XM_005674671.3      4934            ## 借助awk 数组来实现； 基本思想利用awk循环对第三列数值进行判断；出现最大值，则将当前行存储在ay2数组中
ID=gene-TRNAC-GCA       rna-TRNAC-GCA   72
ID=gene-SON     rna-XR_001295570.2      8568
ID=gene-DONSON  rna-XM_018045976.1      2568
ID=gene-CRYZL1  rna-XM_013962952.2      1749
ID=gene-ATP5O   rna-XM_005674665.3      793
ID=gene-ITSN1   rna-XM_018041619.1      9323

 

003、输出最小项的实现方法如下：

(base) [b20223040323@admin1 test2]$ awk '{if(ay1[$1] == "") {ay1[$1] = $3; ay2[$1] = $0}; if(ay1[$1] > $3){ay1[$1] = $3; ay2[$1] = $0}} END {for(i in ay1) {print ay2[i]}}' 003.txt
ID=gene-GART    rna-XM_005674671.3      4934        ## 实现的方法与输出最大项方法一致
ID=gene-TRNAC-GCA       rna-TRNAC-GCA   72
ID=gene-SON     rna-XM_005674679.3      7645
ID=gene-DONSON  rna-XM_018045976.1      2568
ID=gene-CRYZL1  rna-XM_013962888.2      1588
ID=gene-ATP5O   rna-XM_005674665.3      793
ID=gene-ITSN1   rna-XR_001917533.1      4437

 

004、如何保持第一列的顺序

a、输出最大项，并保持第一列的顺序

(base) [b20223040323@admin1 test2]$ awk '{if(ay1[$1] == "") {tmp++; ay1[$1] = $3; ay2[tmp] = $0};if(ay1[$1] < $3){ay1[$1] = $3; ay2[tmp] = $0} } END{for(i = 1; i <= length(ay2); i++) {print ay2[i]}}' 003.txt
ID=gene-TRNAC-GCA       rna-TRNAC-GCA   72           ## 利用tmp计数； 最后按照for数值循环输出
ID=gene-ATP5O   rna-XM_005674665.3      793
ID=gene-ITSN1   rna-XM_018041619.1      9323
ID=gene-CRYZL1  rna-XM_013962952.2      1749
ID=gene-DONSON  rna-XM_018045976.1      2568
ID=gene-SON     rna-XR_001295570.2      8568
ID=gene-GART    rna-XM_005674671.3      4934

 

b、输出最小项，并保持第一列的顺序

(base) [b20223040323@admin1 test2]$ awk '{if(ay1[$1] == "") {tmp++; ay1[$1] = $3; ay2[tmp] = $0}; if(ay1[$1] > $3){ay1[$1] = $3; ay2[tmp] = $0}} END {for(i = 1; i <= length(ay2); i++) {print ay2[i]}}' 003.txt
ID=gene-TRNAC-GCA       rna-TRNAC-GCA   72   ## 输出最小项，并保持第一列的顺序
ID=gene-ATP5O   rna-XM_005674665.3      793
ID=gene-ITSN1   rna-XR_001917533.1      4437
ID=gene-CRYZL1  rna-XM_013962888.2      1588
ID=gene-DONSON  rna-XM_018045976.1      2568
ID=gene-SON     rna-XM_005674679.3      7645
ID=gene-GART    rna-XM_005674671.3      4934

 。