python讀取文件csv，先按第4列排序，再按第5列的數值排序

插入代碼：

from operator import itemgetter

input_file = open("PDBhaemoglobinReport.csv")
output_file = open("PDBhaemoglobinSorted.csv","w")

table = []
header = input_file.readline() #讀取並彈出第一行
for line in input_file:
    col = line.split(',') #每行分隔為列表，好處理列格式
    col[3] = float(col[3][1:-1])
    col[4] = int(col[4][1:-2]) #各行沒有先strip 末位是\n
    table.append(col) #嵌套列表table[[8,8][*,*],...]

table_sorted = sorted(table, key=itemgetter(3, 4))#先后按列索引3,4排序

output_file.write(header + '\t')
for row in table_sorted:                    #遍歷讀取排序后的嵌套列表
    row = [str(x) for x in row]             #轉換為字符串格式，好寫入文本
    output_file.write("\t".join(row) + '\n')

input_file.close()
output_file.close()

 

附：

PDBhaemoglobinReportcsv內容

PDB ID,Chain ID,Exp. Method,Resolution,Chain Length
"1A4F","A","X-RAY DIFFRACTION","2.00","141"
"1C7C","A","X-RAY DIFFRACTION","1.80","283"
"1CG5","A","X-RAY DIFFRACTION","1.60","141"
"1FAW","A","X-RAY DIFFRACTION","3.09","141"
"1HDA","A","X-RAY DIFFRACTION","2.20","141"
"1IRD","A","X-RAY DIFFRACTION","1.25","141"
"1KFR","A","X-RAY DIFFRACTION","1.85","147"
"1QPW","A","X-RAY DIFFRACTION","1.80","141"
"1SPG","A","X-RAY DIFFRACTION","1.95","144"
"1UX8","A","X-RAY DIFFRACTION","2.15","132"

 

PDBhaemoglobinSorted.csv ：

PDB ID,Chain ID,Exp. Method,Resolution,Chain Length
"2W72" "A" "X-RAY DIFFRACTION" 1.07 141
"1IRD" "A" "X-RAY DIFFRACTION" 1.25 141
"2H8F" "A" "X-RAY DIFFRACTION" 1.3 143
"2WY4" "A" "X-RAY DIFFRACTION" 1.35 140
"2D5X" "A" "X-RAY DIFFRACTION" 1.45 141
"4ESA" "A" "X-RAY DIFFRACTION" 1.45 143
"3VRG" "A" "X-RAY DIFFRACTION" 1.5 141
"1CG5" "A" "X-RAY DIFFRACTION" 1.6 141
"4HBI" "A" "X-RAY DIFFRACTION" 1.6 146
"1QPW" "A" "X-RAY DIFFRACTION" 1.8 141