python数据清洗cvs里面带中文字符

　　数据清洗，使用python数据清洗cvs里面带中文字符，意图是用字典对应中文字符，即key值是中文字符，value值是index，自增即可；利用字典数据结构没有重复key值的特性，把中文字符映射到了数值index。

　　python代码如下：（data数据时csv格式）

import csv

dict2 = {}      #Cdict4 = {}      #Edict25 = {}     #zdict26 = {}     #AAdict27 = {}     #ABdict37 = {}     #ALdict38 = {}     #AMdict40 = {}     #AOdict41 = {}     #APdict42 = {}     #AQdict45 = {}     #ATdict49 = {}     #AXindex = 0flag = False

#        print(row[2],dict[row[2]])

with open("E:/yuce/test.csv", ‘w+‘, newline=‘‘) as csv_file_write:        writer = csv.writer(csv_file_write)        with open(‘E:/yuce/b.csv‘, ‘r‘, newline=‘‘) as csv_file_read:            reader = csv.reader(csv_file_read)            for row in reader:                if(flag):                    dict2[row[2]] = index                    dict4[row[4]] = index                    dict25[row[25]] = index                    dict26[row[26]] = index                    dict27[row[27]] = index                    dict37[row[37]] = index                    dict38[row[38]] = index                    dict40[row[40]] = index                    dict41[row[41]] = index                    dict42[row[42]] = index                    dict45[row[45]] = index                    dict49[row[49]] = index                    row[2] = dict2[row[2]]                    row[4] = dict4[row[4]]                    row[25] = dict25[row[25]]                    row[26] = dict26[row[26]]                    row[27] = dict27[row[27]]                    row[37] = dict37[row[37]]                    row[38] = dict38[row[38]]                    row[40] = dict40[row[40]]                    row[41] = dict41[row[41]]                    row[42] = dict42[row[42]]                    row[45] = dict45[row[45]]                    row[49] = dict49[row[49]]                    index = index + 1                writer.writerow(row)                flag = True        csv_file_read.close()csv_file_write.close()

print(‘done!‘)

　　上例是真实的数据处理，有两百列属性，三万条数据的原始数据。其中包括中文字符，及缺失值，需要一步步清洗。