航空公司客户价值分析

 1  -*- coding: utf-8 -*-
 2 """
 3 Spyder Editor
 4 
 5 This is a temporary script file.
 6 """
 7 
 8 
 9 import pandas as pd
10 datafile = 'C:/Users/admin/Desktop/air_data.csv'
11 resultfile = 'C:/Users/admin/Desktop/explore.csv'
12 data = pd.read_csv(datafile,encoding = 'utf-8')
13 
14 explore = data.describe(percentiles = [],include = 'all').T
15 
16 explore['null'] = len(data)-explore['count']
17 
18 explore = explore[['null','max','min']]
19 explore.columns = [u'空数值',u'最大值',u'最小值']
20 explore.to_csv(resultfile)
21 
22 
23 import matplotlib.pyplot as plt
24 from datetime import datetime
25 ffp = data['FFP_DATE'].apply(lambda x:datetime.strptime(x,'%Y/%m/%d'))
26 ffp_year = ffp.map(lambda x:x.year)
27 fig = plt.figure(figsize = (8,5))
28 plt.rcParams['font.sans-serif'] = 'SimHei'
29 plt.rcParams['axes.unicode_minus'] = False
30 plt.hist(ffp_year,bins = 'auto',color = '#0504aa')
31 plt.xlabel('年份')
32 plt.ylabel('入会人数')
33 plt.title('各年份会员入会人数（学号202031014040）')
34 plt.show()
35 plt.close
36 
37 male = pd.value_counts(data['GENDER'])['男']
38 female = pd.value_counts(data['GENDER'])['女']
39 fig = plt.figure(figsize = (7,4))
40 plt.pie([male,female],labels = ['男','女'],colors = ['lightskyblue','lightcoral'],autopct = '%1.1f%%')
41 plt.title('会员性别比例（学号2020310143040）')
42 plt.show()
43 plt.close
44 
45 lv_four = pd.value_counts(data['FFP_TIER'])[4]
46 lv_five = pd.value_counts(data['FFP_TIER'])[5]
47 lv_six = pd.value_counts(data['FFP_TIER'])[6]
48 fig = plt.figure(figsize =(8,5))
49 plt.bar(x = range(3),height = [lv_four,lv_five,lv_six],width = 0.4,alpha = 0.8,color = 'skyblue')
50 plt.xticks([index for index in range(3)],['4','5','6'])
51 plt.xlabel('会员等级')
52 plt.ylabel('会员人数')
53 plt.title('会员各级别人数（学号2020310143040）')
54 plt.show()
55 plt.close
56 
57 age = data['AGE'].dropna()
58 age = age.astype('int64')
59 fig = plt.figure(figsize = (8,5))
60 plt.boxplot(age,patch_artist = True,labels = ['会员年龄'],boxprops = {'facecolor':'lightblue'})
61 plt.title('会员年龄分布箱型图（学号2020310143040）')
62 plt.grid(axis = 'y')
63 plt.show()
64 plt.close

 1 # 乘机信息类别
 2 lte = data['LAST_TO_END']
 3 fc = data['FLIGHT_COUNT']
 4 sks = data['SEG_KM_SUM']
 5 
 6 # 绘制最后乘机至结束时长箱线图
 7 fig = plt.figure(figsize = (5 ,8))
 8 plt.boxplot(lte, 
 9             patch_artist=True,
10             labels = ['时长'],  # 设置x轴标题
11             boxprops = {'facecolor':'gold'})  # 设置填充颜色
12 plt.title('会员最后乘机至结束时长分布箱线图（学号2020310143040）')
13 # 显示y坐标轴的底线
14 plt.grid(axis='y')
15 plt.show()
16 plt.close
17 # 绘制客户飞行次数箱线图
18 fig = plt.figure(figsize = (5 ,8))
19 plt.boxplot(fc, 
20             patch_artist=True,
21             labels = ['飞行次数'],  # 设置x轴标题
22             boxprops = {'facecolor':'gold'})  # 设置填充颜色
23 plt.title('会员飞行次数分布箱线图（学号2020310143040）')
24 # 显示y坐标轴的底线
25 plt.grid(axis='y')
26 plt.show()
27 plt.close
28 # 绘制客户总飞行公里数箱线图
29 fig = plt.figure(figsize = (5 ,10))
30 plt.boxplot(sks, 
31             patch_artist=True,
32             labels = ['总飞行公里数'],  # 设置x轴标题
33             boxprops = {'facecolor':'gold'})  # 设置填充颜色
34 plt.title('客户总飞行公里数箱线图（学号2020310143040）')
35 # 显示y坐标轴的底线
36 plt.grid(axis='y')
37 plt.show()
38 plt.close
39 # 积分信息类别
40 # 提取会员积分兑换次数
41 ec = data['EXCHANGE_COUNT']
42 # 绘制会员兑换积分次数直方图
43 fig = plt.figure(figsize = (8 ,5))  # 设置画布大小
44 plt.hist(ec, bins=5, color='#0504aa')
45 plt.xlabel('兑换次数')
46 plt.ylabel('会员人数')
47 plt.title('会员兑换积分次数分布直方图（学号2020310143040）')
48 plt.show()
49 plt.close
50 # 提取会员总累计积分
51 ps = data['Points_Sum']
52 # 绘制会员总累计积分箱线图
53 fig = plt.figure(figsize = (5 ,8))
54 plt.boxplot(ps, 
55             patch_artist=True,
56             labels = ['总累计积分'],  # 设置x轴标题
57             boxprops = {'facecolor':'gold'})  # 设置填充颜色
58 plt.title('客户总累计积分箱线图（学号2020310143040）')
59 # 显示y坐标轴的底线
60 plt.grid(axis='y')
61 plt.show()
62 plt.close

 1 # 提取属性并合并为新数据集
 2 data_corr = data[['FFP_TIER','FLIGHT_COUNT','LAST_TO_END',
 3                   'SEG_KM_SUM','EXCHANGE_COUNT','Points_Sum']]
 4 age1 = data['AGE'].fillna(0)
 5 data_corr['AGE'] = age1.astype('int64')
 6 data_corr['ffp_year'] = ffp_year
 7 
 8 # 计算相关性矩阵
 9 dt_corr = data_corr.corr(method = 'pearson')
10 print('相关性矩阵为（学号2020310143040）：\n',dt_corr)
11 
12 # 绘制热力图
13 import seaborn as sns
14 plt.subplots(figsize=(10, 10)) # 设置画面大小 
15 sns.heatmap(dt_corr, annot=True, vmax=1, square=True, cmap='Blues') 
16 plt.title('热力图（学号2020310143040）')
17 plt.show()
18 plt.close