import pandas as pd
df = pd.read_excel('店铺数据.xlsx')
df['评价数']=df['评价数'].str.replace('条评价','').astype('int')
df['均价']=df['均价'].str.replace('人均：','').str.replace('元','').astype('int')
df['所在区']=df['所在区'].str.strip()
df=df.rename({'均价':"均价(元/人)"},axis='columns')
print(df)
print('处理重复zhi',len(df))
df.drop_duplicates(subset=['店名'],inplace=True,ignore_index=True)
print('删除重复值',len(df))
print(df)
df.dropna(inplace=True,ignore_index=True)
print("处理完缺失值",len(df))
print(df)