python数据挖掘-航空公司客户价值分析

数据探索

import pandas as pd
datafile='D:/laizheli111/air_data.csv'
resultfile='D:/laizheli111/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'空值数',u'最大值',u'最小值']
explore.to_csv(resultfile)

探索客户的基本信息分布情况

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)
#绘制各年份会员入会人数直方图
fig = plt.figure(figsize=(8,5))   #设置画布大小
plt.rcParams['font.sans-serif'] = ['SimHei']  #用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  #用来正常显示负号
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(3005)')
plt.show()
plt.close

#会指挥员不同性别人数
male = pd.value_counts(data['GENDER'])['男']
female = pd.value_counts(data['GENDER'])['女']
#会指挥员性别比例饼图
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(3005)')
plt.show()
plt.close

#提取不同级别会员人数
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]
#会指挥员各级别人数条形图
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(3005)')
plt.show()
plt.close()

#提取会员年龄
age = data['AGE'].dropna()
age = age.astype('int64')
#绘制会员年龄分布箱型图
fig = plt.figure(figsize=(5,10))
plt.boxplot(age,
            patch_artist=True,
            labels = ['会员年龄'],                       #设置x轴光标
            boxprops = {'facecolor':'lightblue'})       #设置填充颜色
plt.title('会员年龄分布箱型图(3005)')
#设置y坐标轴的底线
plt.grid(axis='y')
plt.show()
plt.close

探索客户乘机信息分布情况

lte = data['LAST_TO_END']
fc = data['FLIGHT_COUNT']
sks = data['SEG_KM_SUM']

plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

fig = plt.figure(figsize=(5, 8))
plt.boxplot(lte, patch_artist=True, labels=['时长'], boxprops={'facecolor' : 'lightblue'})
plt.title('会员最后乘机至结束时长分布箱型图(3005)')
plt.grid(axis='y')
plt.show()
plt.close()

fig = plt.figure(figsize=(5, 8))
plt.boxplot(fc, patch_artist=True, labels=['飞行次数'], boxprops={'facecolor' : 'lightblue'})
plt.title('会员飞行次数分布箱型图(3005)')
plt.grid(axis='y')
plt.show()
plt.close()

fig = plt.figure(figsize=(5, 8))
plt.boxplot(sks, patch_artist=True, labels=['总飞行公里数'], boxprops={'facecolor' : 'lightblue'})
plt.title('客户总飞行公里数箱型图(3005)')

plt.grid(axis='y')
plt.show()
plt.close()

探索客户的积分信息分布情况

ec=data['EXCHANGE_COUNT']
fig=plt.figure(figsize=(8,5))
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(3005)')
plt.show()
plt.close

ps=data['Points_Sum']
fig=plt.figure(figsize=(5,8))
plt.boxplot(ps,
            patch_artist=True,
            labels=['总累计积分'],
            boxprops={'facecolor':'lightblue'})
plt.title('客户总累计积分箱型图(3005)')
plt.grid(axis='y')
plt.show()
plt.close

相关系数矩阵与热力图

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

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

import seaborn as sns
plt.subplots(figsize=(10,10))
sns.heatmap(dt_corr,annot=True,vmax=1,square=True,cmap='Blues')
plt.title('热力图(3005)')
plt.show()
plt.close