python数据预处理

缺失值处理

import pandas as pda
import numpy as npy
import matplotlib.pylab as pyl
# data=pda.read_excel("D:/taobao2.xls")
def index(data):
  data = pda.DataFrame(data[1:],columns=data[0])
  print(data)
  data["价格"][(data["价格"]==0)]=None
  print(data)
  x=0
  for i in data.columns:
   for j in range(len(data)):
     if(data[i].isnull())[j]:
        data[i][j]=data["价格"].mean()
        x+=1
        print(x)

if __name__ == "__main__":
  data = nosupervision_read_data()
  index(data)

数据离散化处理

#离散化
#连续型数据离散化
#等宽离散化
import pandas as pda
import numpy as npy
import matplotlib.pylab as pyl
# data=pda.read_excel("D:/taobao2.xls")
def index(data):
    data = pda.DataFrame(data[1:], columns=data[0])
    da=data.values
    price=da[:,2]
    price.sort()
    print(price)
    k=5
    c1=pda.cut(price,k,labels=["太便宜","便宜","适中","贵","太贵"])
    print(c1)
#指点区间离散化
    k=[0,50,100,price.max()]
    print(k)
    c2=pda.cut(price,k,labels=["非常便宜","适中","贵"])
    print(c2)
if __name__ == "__main__":
   data = nosupervision_read_data()
   index(data)

数据集成处理

# -*- coding:utf-8 -*-
# 异常值处理
import pandas as pda
import numpy as npy
def index(data):
# 输出结果必须为字典output
   output = {}
# data = pda.read_excel("D:/taobao2.xls")
   data = pda.DataFrame(data[1:], columns=data[0])
# print(data)
   da = data.values
# 数据集成
   da1 = da[0:10]
   da2 = da[10:20]
   da3 = npy.concatenate((da1, da2))
   pda.DataFrame(da3)
   output['data_数据集成'] = pda.DataFrame(da3).values.tolist()
   print(pda.DataFrame(da1))
   print(pda.DataFrame(da2))
   print(pda.DataFrame(da3))
   print(output)
   return output
if __name__ == "__main__":
   data = nosupervision_read_data()
   index(data)