第七章 航空公司客户价值分析

一、数据探索分析

import pandas as pd
import numpy as np
import datetime
import matplotlib.pyplot as plt

#查询空值、最大值、最小值
path='C:\\Users\\11728\\Desktop\\文件\\python\\《Python数据分析与挖掘实战》-数据\\chapter7\\demo\\data\\air_data.csv'
air_data=pd.read_csv(path,encoding='utf-8')
explore=air_data.describe(percentiles=[],include='all').T
explore['null']=len(air_data)-explore['count']
explore=explore[['null','max','min']]
explore.columns=[[u'空值数',u'最大值',u'最小值']]
print(explore)

#结果
                         空值数       最大值   最小值
MEMBER_NO                   0     62988     1
FFP_DATE                    0       NaN   NaN
FIRST_FLIGHT_DATE           0       NaN   NaN
GENDER                      3       NaN   NaN
FFP_TIER                    0         6     4
WORK_CITY                2269       NaN   NaN
WORK_PROVINCE            3248       NaN   NaN
WORK_COUNTRY               26       NaN   NaN
AGE                       420       110     6
LOAD_TIME                   0       NaN   NaN
FLIGHT_COUNT                0       213     2
BP_SUM                      0    505308     0
EP_SUM_YR_1                 0         0     0
EP_SUM_YR_2                 0     74460     0
SUM_YR_1                  551    239560     0
SUM_YR_2                  138    234188     0
SEG_KM_SUM                  0    580717   368
WEIGHTED_SEG_KM             0    558440     0
LAST_FLIGHT_DATE            0       NaN   NaN
AVG_FLIGHT_COUNT            0    26.625  0.25
AVG_BP_SUM                  0   63163.5     0
BEGIN_TO_FIRST              0       729     0
LAST_TO_END                 0       731     1
AVG_INTERVAL                0       728     0
MAX_INTERVAL                0       728     0
ADD_POINTS_SUM_YR_1         0    600000     0
ADD_POINTS_SUM_YR_2         0    728282     0
EXCHANGE_COUNT              0        46     0
avg_discount                0       1.5     0
P1Y_Flight_Count            0       118     0
L1Y_Flight_Count            0       111     0
P1Y_BP_SUM                  0    246197     0
L1Y_BP_SUM                  0    259111     0
EP_SUM                      0     74460     0
ADD_Point_SUM               0    984938     0
Eli_Add_Point_Sum           0    984938     0
L1Y_ELi_Add_Points          0    728282     0
Points_Sum                  0    985572     0
L1Y_Points_Sum              0    728282     0
Ration_L1Y_Flight_Count     0         1     0
Ration_P1Y_Flight_Count     0         1     0
Ration_P1Y_BPS              0  0.999989     0
Ration_L1Y_BPS              0  0.999993     0
Point_NotFlight             0       140     0

二、数据预处理

1.数据清洗

path='C:\\Users\\11728\\Desktop\\文件\\python\\《Python数据分析与挖掘实战》-数据\\chapter7\\demo\\data\\air_data.csv'
data=pd.read_csv(path,encoding='utf-8')
data=data[data['SUM_YR_1'].notnull()&data['SUM_YR_2'].notnull()] #第一、二年票价非空
condition1=data['SUM_YR_1']!=0 
condition2=data['SUM_YR_2']!=0  #第一、二年票价不等于0
condition3=(data['SEG_KM_SUM']==0)&(data['avg_discount']==0) #平均折扣与总飞行公里为0
data=data[condition1|condition2|condition3]
print(data)

2.数据规约

data=data[['LOAD_TIME','FFP_DATE','LAST_TO_END','FLIGHT_COUNT','SEG_KM_SUM','avg_discount']]

3.数据变换

#datetime.datetime.strptime(row['LOAD_TIME'], "%Y/%m/%d") 字符串转化为日期
data['L']=data.apply(lambda row:(datetime.datetime.strptime(row['LOAD_TIME'], "%Y/%m/%d")-datetime.datetime.strptime(row['FFP_DATE'], "%Y/%m/%d")).days,axis=1) #入会员书时间
data=data.drop(['LOAD_TIME','FFP_DATE'],axis=1) #删除
data.columns=['R','F','M','C','L']
data_zs=(data-data.mean(axis=0))/(data.std(axis=0)) #数据标准化
data_zs.columns=['Z'+i for i in data.columns]
print(data_zs)


#结果
         ZR         ZF         ZM        ZC        ZL
0 -0.944948  14.034016  26.761154  1.295540  1.435707
1 -0.911894   9.073213  13.126864  2.868176  1.307152
2 -0.889859   8.718869  12.653481  2.880950  1.328381
3 -0.416098   0.781585  12.540622  1.994714  0.658476
4 -0.922912   9.923636  13.898736  1.344335  0.386032

三、模型构建

from sklearn.cluster import KMeans
k=5  
kmodel=KMeans(n_clusters=k,n_jobs=2)
kmodel.fit(data_zs)
cen=kmodel.cluster_centers_ #聚类中心
kinds=kmodel.labels_ #聚类标签


#聚类结果：
[[-0.41487223 -0.16115608 -0.16097537 -0.25507251 -0.70022909 -0.41487223]
 [-0.79938326  2.4832016   2.42472391  0.30863003  0.48332845 -0.79938326]
 [-0.00299761 -0.22662501 -0.23103958  2.19174737  0.05220837 -0.00299761]
 [-0.37722119 -0.08691852 -0.09484404 -0.1559046   1.16066672 -0.37722119]
 [ 1.68623455 -0.57402693 -0.53683869 -0.17318782 -0.31366659  1.68623455]]

四、雷达图

labels=data_zs.columns
n=len(labels) #n=5
cen=np.c_[cen,cen[:,0]] #首尾列相同，数据闭合
angles=np.linspace(0,2*np.pi,n,endpoint=False)
angles=np.append(angles,angles[0]) #角度闭合
index=['c1','c2','c3','c4','c5']
print(cen)
fig = plt.figure()
su = fig.add_subplot(111, polar=True)# polar参数！！
for i in range(len(index)):
    su.plot(angles,cen[i], linewidth=2,label=index[i])# 画线
su.set_thetagrids(angles * 180/np.pi, labels, fontproperties="SimHei") 添加标签
plt.legend(loc='lower right') #添加图列
plt.show()