第三周python作业

航空公司客户价值分析

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sn
data=pd.read_csv('../data/air_data.csv')
data
#数据的描述性统计
explore=data.describe(percentiles=[],include='all').T
explore

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))
plt.rcParams['font.sans-serif'] = 'SimHei'  # 设置中文显示
plt.rcParams['axes.unicode_minus'] = False
plt.hist(ffp_year, bins='auto', color='#111111')
plt.xlabel('年份')
plt.ylabel('入会人数')
plt.title('各年份会员入会人数 2020310143049l吕莹')
plt.show()
plt.close

 

 

 

male=pd.value_counts(data['GENDER'])['男']
female=pd.value_counts(data['GENDER'])['女']
fig = plt.figure(figsize = (7 ,4))  # 设置画布大小
plt.pie([ male, female], labels=['男','女'], colors=['lightskyblue', 'lightcoral'],
       autopct='%1.1f%%')
plt.title('会员性别比例 2020310143049l吕莹')
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：\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-2019320143321魏沛然-')
plt.show()
plt.close