数据清洗练习

import pandas as pd
import numpy as np
##1.检测处理重复值:

right = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],
                      'key2': ['K0', 'K0', 'K0', 'K0'],
                         'C': [1, 1, 2, 3],
                         'D': [2, 2, 4, 6],
                         'E': [1, 1, 2, 3]})

data_drop = right['key1'].drop_duplicates(keep=False)

# keep:保留第几个重复值,默认为first,last,false:都不保留
print(len(data_drop))

# 表去重:===>>去行
shape_det = right.drop_duplicates(subset=['key1','key2'])
# print(shape_det)

# 特征重复:==>>去列(计算相似度)
# corr_det = right[['C','D','E']].corr(method='kendall')  ##spearman
# print(corr_det)

detail = pd.read_excel('meal_order_detail.xlsx',sheet_name=0)
# 1.相似度矩阵
corr_det = detail[['counts','amounts','