python实现数据预处理之填充缺失值的示例

5.1 3.5 1.4 0.2
4.9 3 1.4 0.2
4.7 3.2 1.3 0.2
4.6 3.1 1.5 0.2
5 3.6 1.4 0.2
5.4 3.9 1.7 0.4
4.6 3.4 1.4 0.3
5 3.4 1.5 0.2
4.4 2.9 1.4 0.2
4.9 -3.1 1.5 0.1
5.4 3.7 1.5 0.2
4.8 3.4 1.6 0.2
4.8 3 -1.4 0.1
4.3 3 1.1 0.1
5.8 4 1.2 0.2
5.7 4.4 1.5 0.4
5.4 3.9 1.3 0.4
5.1 3.5 1.4 0.3
5.7 3.8 1.7 0.3
5.1 3.8 -1.5 0.3
5.4 3.4 1.7 0.2
5.1 3.7 1.5 0.4
4.6 3.6 1 0.2
5.1 3.3 1.7 0.5
4.8 3.4 1.9 0.2

import numpy as np
data = []
my_list = []
con=0
noise_data = open('noise-data-1.txt') 
clean_data = open("clean_data3.txt", 'w')
for line in noise_data.readlines():
 if len(line) == 0:
 break
 if line.count('\n') == len(line):
 continue 
 dataline =line.strip().split('\t')
 my_list.append(dataline)
 con+=1
for i in range(0,con):
 for j in range(0,len(my_list[i])):
 if my_list[i][j].count('.')==0:
  miss_row=[]
  for a in range(0,len(my_list[i])):
  if float(my_list[i][a])<0:
   miss_row.append(-float(my_list[i][a])) 
  miss_row.append(float(my_list[i][a])) 
  my_average=round(np.average(miss_row),1)
  my_list[i][j]=my_average
 else:
  if float(my_list[i][j])<0:
   my_list[i][j]=-float(my_list[i][j]) 
  my_list[i][j]=float(my_list[i][j]) 
print my_list
def file_write(filename,data_list):
 file1=open(filename,'w')
 for i in data_list:
 for j in i:
  if type(j)!=str:
  j=str(j)
  file1.write(j)
  file1.write(' ')
 file1.write('\n')
 file1.close()
 return file1
filename='clean_data.txt'
file_write(filename,my_list)