Python数据分析之聚合与透视表

import pymysqlimport pandas as pdimport matplotlib.pyplot as plt
# 建立连接conn = pymysql.connect('localhost','username','password','database')
# 读取SQL为dfsql = 'select * from table'df = pd.read_sql(sql,con=conn)

# 查看基本属性print(df.index)print(df.columns)print(df.info())
# 修改时间格式df['stat_month'] = pd.to_datetime(df['stat_month'],format='%Y%m')
# 设置索引df.set_index('stat_month',inplace = True)print(df.head())
# 只看一个月份的df_grp1601= df['20160101'].groupby(['brand','areaname'],as_index = False)['profit'].sum()print(df_grp1601)
df_grpbrand = df_grp1601.groupby('brand').sum()print(df_grpbrand[df_grpbrand>200000].plot(kind = 'bar'))

pd.pivot_table(df['20160101':'20161201'],values = 'profit',\               index = ['stat_month','brand'],\               columns ='areaname',aggfunc='sum' )