本章内容包括：

用户个体消费分析

python 的 query = SQL 的 where，切比雪夫不等式：mean+5std = 95%的数据。

//input1
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
plt.style.use('ggplot')
columns = ['user_id','order_dt','order_products','order_amount']
df = pd.read_table('CDNOW_master.txt',names = columns,sep = '\s+')
//user_id:用户ID
//order_dt:购买日期
//orderproducts:购买产品数
//order_amount:购买金额
df['order_dt'] = pd.to_datetime(df.order_dt,format='%Y%m%d')
df['month'] = df.order_dt.values.astype('datetime64[M]')
df.info()





//output1
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 69659 entries, 0 to 69658
Data columns (total 5 columns):
user_id           69659 non-null int64
order_dt          69659 non-null datetime64[ns]
order_products    69659 non-null int64
order_amount      69659 non-null float64
month             69659 non-null datetime64[ns]
dtypes: datetime64[ns](2), float64(1), int64(2)
memory usage: 2.7 MB








//input2
df.head()




//output2
user_id order_dt    order_products  order_amount    month
0   1   1997-01-01  1   11.77   1997-01-01
1   2   1997-01-12  1   12.00   1997-01-01
2   2   1997-01-12  5   77.00   1997-01-01
3   3   1997-01-02  2   20.76   1997-01-01
4   3   1997-03-30  2   20.76   1997-03-01









//input3
grouped_user = df.groupby('user_id')
grouped_user.sum().describe()  



//output3
order_products  order_amount
count   23570.000000    23570.000000
mean    7.122656    106.080426
std 16.983531   240.925195
min 1.000000    0.000000
25% 1.000000    19.970000
50% 3.000000    43.395000
75% 7.000000    106.475000
max 1033.000000 13990.930000








//input4
grouped_user.sum().query('order_amount < 4000').plot.scatter(x= 'order_amount',y = 'order_products')




//output4

//input5
grouped_user.sum().query('order_products <60').order_products.hist(bins = 10)




//output5

//input6
user_cumsum = grouped_user.sum().sort_values('order_amount').apply(lambda x:x.cumsum()/x.sum())
user_cumsum.reset_index().order_amount.plot()



//output6