航空公司客户价值分析

 -*- coding: utf-8 -*-
"""
Spyder Editor

This is a temporary script file.
"""


import pandas as pd
datafile = 'C:/Users/admin/Desktop/air_data.csv'
resultfile = 'C:/Users/admin/Desktop/explore.csv'
data = pd.read_csv(datafile,encoding = 'utf-8')

explore = data.describe(percentiles = [],include = 'all').T

explore['null'] = len(data)-explore['count']

explore = explore[['null','max','min']]
explore.columns = [u'空数值',u'最大值',u'最小值']
explore.to_csv(resultfile)


import matplotlib.pyplot as plt
from datetime import datetime
ffp = data['FFP_DATE'].apply(lambda x:datetime.strptime(x,'%Y/%m/%d'))
ffp_year = ffp.map(lambda x:x.year)
fig = plt.figure(figsize = (8,5))
plt.rcParams['font.sans-serif'] = 'SimHei'
plt.rcParams['axes.unicode_minus'] = False
plt.hist(ffp_year,bins = 'auto',color = '#0504aa')
plt.xlabel('年份')
plt.ylabel('入会人数')
plt.title('各年份会员入会人数（学号202031014040）')
plt.show()
plt.close

male = pd.value_counts(data['GENDER'])['男']
female = pd.value_counts(data['GENDER'])['女']
fig = plt.figure(figsize = (7,4))
plt.pie([male,female],labels = ['男','女'],colors = ['lightskyblue','lightcoral'],autopct = '%1.1f%%')
plt.title('会员性别比例（学号2020310143040）')
plt.show()
plt.close

lv_four = pd.value_counts(data['FFP_TIER'])[4]
lv_five = pd.value_counts(data['FFP_TIER'])[5]
lv_six = pd.value_counts(data['FFP_TIER'])[6]
fig = plt.figure(figsize =(8,5))
plt.bar(x = range(3),height = [lv_four,lv_five,lv_six],width = 0.4,alpha = 0.8,color = 'skyblue')
plt.xticks([index for index in range(3)],['4','5','6'])
plt.xlabel('会员等级')
plt.ylabel('会员人数')
plt.title('会员各级别人数（学号2020310143040）')
plt.show()
plt.close

age = data['AGE'].dropna()
age = age.astype('int64')
fig = plt.figure(figsize = (8,5))
plt.boxplot(age,patch_artist = True,labels = ['会员年龄'],boxprops = {'facecolor':'lightblue'})
plt.title('会员年龄分布箱型图（学号2020310143040）')
plt.grid(axis = 'y')
plt.show()
plt.close

# 乘机信息类别
lte = data['LAST_TO_END']
fc = data['FLIGHT_COUNT']
sks = data['SEG_KM_SUM']

# 绘制最后乘机至结束时长箱线图
fig = plt.figure(figsize = (5 ,8))
plt.boxplot(lte, 
            patch_artist=True,
            labels = ['时长'],  # 设置x轴标题
            boxprops = {'facecolor':'gold'})  # 设置填充颜色
plt.title('会员最后乘机至结束时长分布箱线图（学号2020310143040）')
# 显示y坐标轴的底线
plt.grid(axis='y')
plt.show()
plt.close
# 绘制客户飞行次数箱线图
fig = plt.figure(figsize = (5 ,8))
plt.boxplot(fc, 
            patch_artist=True,
            labels = ['飞行次数'],  # 设置x轴标题
            boxprops = {'facecolor':'gold'})  # 设置填充颜色
plt.title('会员飞行次数分布箱线图（学号2020310143040）')
# 显示y坐标轴的底线
plt.grid(axis='y')
plt.show()
plt.close
# 绘制客户总飞行公里数箱线图
fig = plt.figure(figsize = (5 ,10))
plt.boxplot(sks, 
            patch_artist=True,
            labels = ['总飞行公里数'],  # 设置x轴标题
            boxprops = {'facecolor':'gold'})  # 设置填充颜色
plt.title('客户总飞行公里数箱线图（学号2020310143040）')
# 显示y坐标轴的底线
plt.grid(axis='y')
plt.show()
plt.close
# 积分信息类别
# 提取会员积分兑换次数
ec = data['EXCHANGE_COUNT']
# 绘制会员兑换积分次数直方图
fig = plt.figure(figsize = (8 ,5))  # 设置画布大小
plt.hist(ec, bins=5, color='#0504aa')
plt.xlabel('兑换次数')
plt.ylabel('会员人数')
plt.title('会员兑换积分次数分布直方图（学号2020310143040）')
plt.show()
plt.close
# 提取会员总累计积分
ps = data['Points_Sum']
# 绘制会员总累计积分箱线图
fig = plt.figure(figsize = (5 ,8))
plt.boxplot(ps, 
            patch_artist=True,
            labels = ['总累计积分'],  # 设置x轴标题
            boxprops = {'facecolor':'gold'})  # 设置填充颜色
plt.title('客户总累计积分箱线图（学号2020310143040）')
# 显示y坐标轴的底线
plt.grid(axis='y')
plt.show()
plt.close

 

 

 

 

 

 

# 提取属性并合并为新数据集
data_corr = data[['FFP_TIER','FLIGHT_COUNT','LAST_TO_END',
                  'SEG_KM_SUM','EXCHANGE_COUNT','Points_Sum']]
age1 = data['AGE'].fillna(0)
data_corr['AGE'] = age1.astype('int64')
data_corr['ffp_year'] = ffp_year

# 计算相关性矩阵
dt_corr = data_corr.corr(method = 'pearson')
print('相关性矩阵为（学号2020310143040）：\n',dt_corr)

# 绘制热力图
import seaborn as sns
plt.subplots(figsize=(10, 10)) # 设置画面大小 
sns.heatmap(dt_corr, annot=True, vmax=1, square=True, cmap='Blues') 
plt.title('热力图（学号2020310143040）')
plt.show()
plt.close

import numpy as np
import pandas as pd
datafile='D:/anaconda/data/air_data.csv'
cleanedfile='D:/anaconda/data/data_cleaned.csv'
airline_data=pd.read_csv(datafile,encoding='utf-8')
print('原始数据的形状为：',airline_data.shape)
airline_notnull=airline_data.loc[airline_data['SUM_YR_1'].notnull()&airline_data['SUM_YR_2'].notnull(),:]
print('删除缺失记录后数据的形状为：\n',airline_notnull.shape)

index1=airline_notnull['SUM_YR_1'] != 0
index2=airline_notnull['SUM_YR_2'] != 0
index3=(airline_notnull['SEG_KM_SUM'] > 0)&(airline_notnull['avg_discount'] != 0)
index4=airline_notnull['AGE'] >100
airline=airline_notnull[(index1|index2)&index3&~index4]
print('数据清清洗后数据形状为：',airline.shape)
airline.to_csv(cleanedfile)

import numpy as np
import pandas as pd
cleanedfile='D:/anaconda/data/data_cleaned.csv'
airline_data=pd.read_csv(cleanedfile,encoding='utf-8')
airline_selection=airline[['FFP_DATE','LOAD_TIME','LAST_TO_END','FLIGHT_COUNT','SEG_KM_SUM','avg_discount']]
print('筛选的属性前5行为：\n',airline_selection.head())

L=pd.to_datetime(airline_selection['LOAD_TIME'])-\
pd.to_datetime(airline_selection['FFP_DATE'])
L=L.astype('str').str.split().str[0]
L=L.astype('int')/30

airline_features=pd.concat([L,airline_selection.iloc[:,2:]],axis=1)
print('构建的LRFMC属性前5行为：\n',airline_features.head())

from sklearn.preprocessing import StandardScaler
data=StandardScaler().fit_transform(airline_features)
np.savez('D:/anaconda/data/airline_scale.npz',data)
print('标准化后LRFMC5个属性为：\n',data[:5,:])

import pandas as pd
import numpy as np
from sklearn.cluster import KMeans

airline_scale=np.load('D:/anaconda/data/airline_scale.npz')['arr_0']
k=5

kmeans_model=KMeans(n_clusters=k,random_state=123)
fit_kmeans=kmeans_model.fit(airline_scale)
kmeans_cc=kmeans_model.cluster_centers_
print('各类聚类中心为：\n',kmeans_cc)
kmeans_labels=kmeans_model.labels_
print('各类样本的类别标签为：\n',kmeans_labels)
r1=pd.Series(kmeans_model.labels_).value_counts()
print('最终每个类别的数目为：\n',r1)
cluster_center=pd.DataFrame(kmeans_model.cluster_centers_,\
columns=['ZL','ZR','ZF','ZM','ZC'])
cluster_center.index=pd.DataFrame(kmeans_model.labels_).\
drop_duplicates().iloc[:,0]
print(cluster_center)

import matplotlib.pyplot as plt
labels=['ZL','ZR','ZF','ZM','ZC']
legen=['客户群'+str(i+1) for i in cluster_center.index]
lstype=['-','--',(0,(3,5,1,5,1,5)),':','-.']
kinds=list(cluster_center.iloc[:,0])
cluster_center=pd.concat([cluster_center,cluster_center[['ZL']]],axis=1)
centers=np.array(cluster_center.iloc[:,0:])

n=len(labels)
angle=np.linspace(0,2*np.pi,n,endpoint=False)
angle=np.concatenate((angle,[angle[0]]))

fig=plt.figure(figsize=(8,6))
ax=fig.add_subplot(111,polar=True)
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
for i in range(len(kinds)):
    ax.plot(angle,centers[i],linestyle=lstype[i],linewidth=2,label=kinds[i])
    ang=angle*180/np.pi
    ax.set_thetagrids(ang[:-1],labels)
plt.title('客户特征分析雷达图学号2020310143040')
plt.legend(legen)
plt.show()
plt.close

#判断一个客户是，已流失，准流失，未流失的客户：

import numpy as np
import pandas as pd
datafile='D:/anaconda/data/air_data.csv'
cleanedfile='D:/anaconda/data/data_cleaned2.csv'
airline_data=pd.read_csv(datafile,encoding='utf-8')
print('原始数据的形状为：',airline_data.shape)
airline_notnull=airline_data.loc[airline_data['SUM_YR_1'].notnull()&airline_data['SUM_YR_2'].notnull(),:]
print('删除缺失记录后数据的形状为：\n',airline_notnull.shape)

#选取特征
airline_data['单位里程票价'] = (airline_data['SUM_YR_1'] + airline_data['SUM_YR_2'])/airline_data['SEG_KM_SUM']
airline_data['单位里程积分'] = (airline_data['P1Y_BP_SUM'] + airline_data['L1Y_BP_SUM'])/airline_data['SEG_KM_SUM']
airline_data['飞行次数比例'] = airline_data['L1Y_Flight_Count'] / airline_data['P1Y_Flight_Count'] #第二年飞行次数与第一年飞行次数的比例
#筛选出老客户(飞行次数大于6次的为老客户)
airline_data = airline_data[airline_data['FLIGHT_COUNT'] > 6]
#选择特征
airline_data = airline_data[['FFP_TIER','飞行次数比例','AVG_INTERVAL',
'avg_discount','EXCHANGE_COUNT','Eli_Add_Point_Sum','单位里程票价','单位里程积分']]
#导出
airline_data.to_csv(cleanedfile,index=None)

input_file = 'D:/anaconda/data/data_cleaned2.csv'
output_file = 'D:/anaconda/data/data_cleaned3.csv'
data = pd.read_csv(input_file,encoding='utf-8')
data['客户类型'] = None
for i in range(len(data)):
#第一、二年飞行次数比例小于50%的客户定义为已流失
    if data['飞行次数比例'][i] < 0.5:
        data['客户类型'][i] = 0 #0代表已流失
#第一、二年飞行次数比例在[0.5,0.9)之间的客户定义为准流失
    if (data['飞行次数比例'][i] >= 0.5) & (data['飞行次数比例'][i] < 0.9) :
        data['客户类型'][i] = 1 #1代表准流失
#第一、二年飞行次数比例大于等于90%的客户定义为未流失
    if data['飞行次数比例'][i] >= 0.9:
        data['客户类型'][i] = 2 #2代表未流失
#导出
data.to_csv(output_file,index=None)
print('筛选的属性前5行为：\n',data.head())