# -*- coding:utf-8-*-
import pandas as pd
aa ='./data/mingribooks.xls'
df = pd.DataFrame(pd.read_excel(aa))
df1=df[['宝贝标题']]
# 去除重复记录，使用tolist()方法转成list
list1=df1['宝贝标题'].drop_duplicates().values.tolist()
print(list1)
import pandas as pd
aa ='./data/mingribooks.xls'
df = pd.DataFrame(pd.read_excel(aa))
df1=df.groupby(["宝贝标题"])["宝贝总数量"].sum() # 分组统计
df1.to_excel('dict.xls') # 保存到Excel文件
mydict=df1.to_dict() # 转换为字典
print(mydict)
import pandas as pd
aa =r'../data/1月销售数据.xls'
df = pd.DataFrame(pd.read_excel(aa))
df1.duplicated()
df1.drop_duplicates()
df1.drop_duplicates(['买家会员名'])
df1.drop_duplicates(['买家会员名'],keep='last')
df1.drop_duplicates(['买家会员名','买家支付宝账号'],inplace=Fasle)
