import pandas as pd
import numpy as np
inputfile = '5Preprocessing/1.xlsx' #销量数据路径
s = pd.read_excel(inputfile) #读入数据
print('数据输出为：\n',s)
#去除重复
data1 = s['x'].drop_duplicates()
print('数据输出为：\n',data1)
#缺失值中位数填补
data2=s['y'].fillna(s['y'].median())
print(data2)