航空公司客户价值分析-KMeans聚类

航空公司客户价值分析-KMeans聚类

import numpy as np
import pandas as pd

data = pd.read_csv(r'***\chapter7\demo\data\air_data.csv', encoding='utf-8')
data.head()

	MEMBER_NO	FFP_DATE	FIRST_FLIGHT_DATE	GENDER	FFP_TIER	WORK_CITY	WORK_PROVINCE	WORK_COUNTRY	AGE	LOAD_TIME	...	ADD_Point_SUM	Eli_Add_Point_Sum	L1Y_ELi_Add_Points	Points_Sum	L1Y_Points_Sum	Ration_L1Y_Flight_Count	Ration_P1Y_Flight_Count	Ration_P1Y_BPS	Ration_L1Y_BPS	Point_NotFlight
0	54993	2006/11/02	2008/12/24	男	6	.	北京	CN	31.0	2014/03/31	...	39992	114452	111100	619760	370211	0.509524	0.490476	0.487221	0.512777	50
1	28065	2007/02/19	2007/08/03	男	6	NaN	北京	CN	42.0	2014/03/31	...	12000	53288	53288	415768	238410	0.514286	0.485714	0.489289	0.510708	33
2	55106	2007/02/01	2007/08/30	男	6	.	北京	CN	40.0	2014/03/31	...	15491	55202	51711	406361	233798	0.518519	0.481481	0.481467	0.518530	26
3	21189	2008/08/22	2008/08/23	男	5	Los Angeles	CA	US	64.0	2014/03/31	...	0	34890	34890	372204	186100	0.434783	0.565217	0.551722	0.448275	12
4	39546	2009/04/10	2009/04/15	男	6	贵阳	贵州	CN	48.0	2014/03/31	...	22704	64969	64969	338813	210365	0.532895	0.467105	0.469054	0.530943	39

5 rows × 44 columns

一、数据探索

explore = data.describe(percentiles = [], include = 'all').T
# percentils参数是指定计算多少的分位数，可不加该参数，此处是计算50%分位数，转置为了阅读方便
# describe（）函数自动计算的的字段有count(非空值数)，unique(唯一值数)，top(频数最高者)，freq(最高频数)，mean（平均数），std, min, 50%, max
explore.head()

	count	unique	top	freq	mean	std	min	50%	max
MEMBER_NO	62988	NaN	NaN	NaN	31494.5	18183.2	1	31494.5	62988
FFP_DATE	62988	3068	2011/01/13	184	NaN	NaN	NaN	NaN	NaN
FIRST_FLIGHT_DATE	62988	3406	2013/02/16	96	NaN	NaN	NaN	NaN	NaN
GENDER	62985	2	男	48134	NaN	NaN	NaN	NaN	NaN
FFP_TIER	62988	NaN	NaN	NaN	4.10216	0.373856	4	4	6

explore['null'] = len(data)-explore['count']  #生成一列空值数
explore.head()

	count	unique	top	freq	mean	std	min	50%	max	null
MEMBER_NO	62988	NaN	NaN	NaN	31494.5	18183.2	1	31494.5	62988	0
FFP_DATE	62988	3068	2011/01/13	184	NaN	NaN	NaN	NaN	NaN	0
FIRST_FLIGHT_DATE	62988	3406	2013/02/16	96	NaN	NaN	NaN	NaN	NaN	0
GENDER	62985	2	男	48134	NaN	NaN	NaN	NaN	NaN	3
FFP_TIER	62988	NaN	NaN	NaN	4.10216	0.373856	4	4	6	0

#导入属性信息表
shuxing = pd.read_excel(r'***\chapter7\demo\data\客户信息属性说明.xls')
shuxing.head()

	属性中文	属性英文	备注
0	会员卡号	MEMBER_NO	NaN
1	入会时间	FFP_DATE	办理会员卡的开始的时间
2	第一次飞行日期	FIRST_FLIGHT_DATE	NaN
3	性别	GENDER	NaN
4	会员卡级别	FFP_TIER	NaN

#合并表
explore1 = pd.merge(explore, shuxing, left_index=True, right_on='属性英文' ,how ='left' )
explore1