$ cat > pandas.awk
BEGIN {
PROCINFO[“sorted_in”]=”@ind_str_asc” # traversal order for for(i in a)
}
NR==1 { # the header cols is in the beginning of data file
# FORGET THIS: header cols from another file replace NR==1 with NR==FNR and see * below
split($0,a,” “) # mkheader a[1]=first_col …
for(i in a) { # replace with a[first_col]=”” …
a[a[i]]
printf “%6s%s”, a[i], OFS # output the header
delete a[i] # remove a[1], a[2], …
}
# next # FORGET THIS * next here if cols from another file UNTESTED
}
{
gsub(/: /,”=”) # replace key-value separator “: ” with “=”
split($0,b,FS) # split record from “,”
for(i in b) {
split(b[i],c,”=”) # split key=value to c[1]=key, c[2]=value
b[c[1]]=c[2] # b[key]=value
}
for(i in a)# go thru headers in a[] and printf from b[]
printf “%6s%s”, (i in b?b[i]:”NaN”), OFS; print “”
}
数据样本（
pandas.txt）：
Col_01 Col_20 Col_21 Col_22 Col_23 Col_25Col_01: 14 Col_20: 25 Col_21: 23432 Col_22: 639142Col_01: 8 Col_20: 25 Col_22: 25134 Col_23: 243344Col_01: 17 Col_21: 75 Col_23: 79876 Col_25: 634534 Col_22: 5 Col_24: 73453Col_01: 19 Col_20: 25 Col_21: 32425 Col_23: 989423Col_01: 12 Col_20: 25 Col_21: 23424 Col_22: 342421 Col_23: 7 Col_24: 13424 Col_25: 67Col_01: 3 Col_20: 95 Col_21: 32121 Col_25: 111231$ awk -f pandas.awk -pandas.txtCol_01 Col_20 Col_21 Col_22 Col_23 Col_25 14 25 23432 639142 NaN NaN 8 25 NaN 25134 243344 NaN 17 NaN 75 5 79876 634534 19 25 32425 NaN 989423 NaN 12 25 23424 342421 7 67 3 95 32121 NaN NaN 111231
所有需要的列应该在数据文件头中。在处理过程中收集标头可能不是一件大事，只是将数据保留在数组中并最终打印（可能在版本3中）。
如果您从
cols.txt与数据文件（
pandas.txt）不同的文件（）中读取标头，请执行脚本（
pandas.awk）：
$ awk -F pandas.awk cols.txt pandas.txt
