import pandas as pd 

#创建dataframe第一种方式，使用相等长度列表的字典创建
# df = pd.DataFrame({'x1':[1,2,3], 'x2':[4,5,6]})

# df2 = pd.read_excel('yyy.xlsx')
df3 = pd.read_excel('chuli001.xlsx')

# print(df2.index, df2.columns, df2.values)
#df2.at[0, '空气质量等级'] = '优'

#fiter_ = df2['空气质量指数' ] == 80

#print(df2[fiter_])

# print(df2['空气质量等级'][2])

# print(df2.at[2, '空气质量等级'])

# print(df2.head(3), df2.tail(3))

# print(df2[  ['日期','天气' ,'空气质量指数'] ])

print("----------------------")

print(df3)

#删除第0行，默认是axis=0，   删除第'性别'列，axis=1表示列操作
print(df3.drop(0) , df3.drop('性别', axis = 1))


print(df3['序号'].count())

print( round(df3['语文'].sum() / df3['语文'].count(), 2) ,  round( df3['语文'].mean() , 2) , df3['语文'].max(), df3['语文'].min() )


print(df3['语文'].describe() )

print("+++++++++++++++++++++++++++")


print( round (df3.groupby('性别')['语文'].mean(), 2) )

print( round (df3.groupby('性别')['语文'].describe(), 2) )

print("===========================")

#sort_index 

#先按序号降序排，再按语文，数学升序排序
# for i in df3.sort_values( ['序号'] ,  ascending = True ).sort_values( ['语文','数学'] ,  ascending = False ).groupby('性别') :
#   print(i)

print(df3)

print(df3.sort_values('语文', inplace = True) )


print(df3)

groupby里的as_index属性，意思是否作为新分组的属性

import pandas as pd
test = {"group_id":[1,1,2,3,3,3,4,4],"age":[22,15,27,35,28,17,45,29],
        "status":[1,2,3,4,5,6,7,8]}
df = pd.DataFrame(test)
print(df)

print(df.groupby(['group_id'] ).mean() , type(df.groupby(['group_id'] ).mean() ))


print(df.groupby(['group_id'] ,as_index = False ).mean())

—— 本文来自火龙信奥（义乌睿码科技）：义乌青少年信息学奥赛与编程教育平台，专注 CSP-J/S、NOIP、GESP 竞赛培训，线上线下融合教学，助力编程升学。网址：hlcoding.com