In[1]:

import pandas as pd

import numpy as np

import os

os.chdir(‘/course/DataAnalyze/data’)

detail= pd.read_csv ('meal_order_detail1.csv')

detailPivot = pd.pivot_table(detail[['order_id','counts','amounts']],index = 'order_id')

print('以order_id作为分组键创建的订单透视表为：\n',detailPivot.head())

Out[1]:

以 order_id 作为分组键创建的订单透视表为：

amounts    counts

order_id

137       32.333333  1.500000

165       52.944444  1.166667

166       48.200000  1.400000

171       36.285714  1.428571

177       34.250000  1.000000

In[2]:

detailPivot1 = pd.pivot_table(detail[['order_id','counts','amounts']],

index = 'order_id',aggfunc = np.sum)

print('以order_id作为分组键创建的订单销量与售价总和透视表为：\n',detailPivot1.head())

Out[2]:

以 order_id 作为分组键创建的订单销量与售价总和透视表为：

amounts  counts

order_id

137           194       9

165           953      21

166           241       7

171           254      10

177           137       4

In[3]:

detailPivot2 = pd.pivot_table(detail[['order_id','dishes_name','counts','amounts']],

index = ['order_id','dishes_name'],aggfunc = np.sum)

print('以order_id和dishes_name作为分组键创建的订单销量与售价总和透视表为：\n',

detailPivot2.head())

Out[3]:

以 order_id 和 dishes_name 作为分组键创建的订单销量与售价总和透视表为：

amounts  counts

order_id dishes_name

137      农夫山泉NFC果汁100%橙汁        6       1

凉拌菠菜                  27       1

番茄炖牛腩                 35       1

白饭/小碗                  1       4

西瓜胡萝卜沙拉               26       1

In[3]:

detailPivot2 = pd.pivot_table(detail[['order_id','dishes_name','counts','amounts']],

index = 'order_id',columns = 'dishes_name',aggfunc = np.sum)

print('以order_id和dishes_name作为行列分组键创建的透视表前5行4列为：\n',

detailPivot2.iloc[:5,:4])

Out[3]:

以 order_id 和 dishes_name 作为行列分组键创建的透视表前 5 行 4 列为：

amounts

dishes_name  42度海之蓝  北冰洋汽水  38度剑南春  50度古井贡酒

order_id

137             NaN     NaN     NaN     NaN

165             NaN     NaN    80.0     NaN

166             NaN     NaN     NaN     NaN

171             NaN     NaN     NaN     NaN

177             NaN     NaN     NaN     NaN

In[4]:

detailPivot4 = pd.pivot_table(detail[['order_id','dishes_name','counts','amounts']],

index = 'order_id', values = 'counts', aggfunc = np.sum)

print('以order_id作为行分组键counts作为值创建的透视表前5行为：\n',

detailPivot4.head())

Out[4]:

以order_id作为行分组键counts作为值创建的透视表前5行为：

counts

order_id

1002         7.0

1003        10.0

1004        17.0

1008         5.0

1011        10.0

In[5]:

detailPivot5 = pd.pivot_table(detail[['order_id','dishes_name','counts','amounts']],

index = 'order_id',columns = 'dishes_name',

aggfunc = np.sum,fill_value = 0)

print('空值填0后以order_id和dishes_name为行列分组键创建透视表前5行4列为：\n',

detailPivot5.iloc[:5,:4])

Out[5]:

空值填0后以order_id和dishes_name为行列分组键创建透视表前5行4列为：

amounts

dishes_name  42度海之蓝北冰洋汽水  38度剑南春  50度古井贡酒

order_id

1002              0       0       0       0

1003              0       0       0       0

1004              0       0       0       0

1008              0       0       0       0

1011             99       0       0       0

In[6]:

detailPivot6 = pd.pivot_table(detail[['order_id','dishes_name','counts','amounts']],

index = 'order_id',columns = 'dishes_name',

aggfunc = np.sum,fill_value = 0,margins = True)

print('添加margins后以order_id和dishes_name为分组键的透视表前5行后4列为：\n',

detailPivot6.iloc[:5,-4:])

Out[6]:

添加margins后以order_id和dishes_name为分组键的透视表前5行后4列为：

counts

dishes_name黄油曲奇饼干黄花菜炒木耳黑米恋上葡萄   All

order_id

1002           0.0    0.0    0.0   7.0

1003           0.0    0.0    0.0  10.0

1004           0.0    1.0    0.0  17.0

1008           0.0    0.0    0.0   5.0

1011           0.0    0.0    0.0  10.0