import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sn
data=pd.read_csv('../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 2019320143322李之琛')
plt.show()
plt.close

<function matplotlib.pyplot.close(fig=None)>

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2019320143322李之琛')
plt.show()
plt.close

<function matplotlib.pyplot.close(fig=None)>

 #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3322李之琛')
plt.show()
plt.close()

C:\Users\reion\AppData\Local\Temp\ipykernel_21832\391820817.py:5: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  data_corr['AGE'] = age1.astype('int64')
C:\Users\reion\AppData\Local\Temp\ipykernel_21832\391820817.py:6: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  data_corr['ffp_year'] = ffp_year


相关性矩阵为：
                 FFP_TIER  FLIGHT_COUNT  LAST_TO_END  SEG_KM_SUM  \
FFP_TIER        1.000000      0.582447    -0.206313    0.522350   
FLIGHT_COUNT    0.582447      1.000000    -0.404999    0.850411   
LAST_TO_END    -0.206313     -0.404999     1.000000   -0.369509   
SEG_KM_SUM      0.522350      0.850411    -0.369509    1.000000   
EXCHANGE_COUNT  0.342355      0.502501    -0.169717    0.507819   
Points_Sum      0.559249      0.747092    -0.292027    0.853014   
AGE             0.076245      0.075309    -0.027654    0.087285   
ffp_year       -0.116510     -0.188181     0.117913   -0.171508   

                EXCHANGE_COUNT  Points_Sum       AGE  ffp_year  
FFP_TIER              0.342355    0.559249  0.076245 -0.116510  
FLIGHT_COUNT          0.502501    0.747092  0.075309 -0.188181  
LAST_TO_END          -0.169717   -0.292027 -0.027654  0.117913  
SEG_KM_SUM            0.507819    0.853014  0.087285 -0.171508  
EXCHANGE_COUNT        1.000000    0.578581  0.032760 -0.216610  
Points_Sum            0.578581    1.000000  0.074887 -0.163431  
AGE                   0.032760    0.074887  1.000000 -0.242579  
ffp_year             -0.216610   -0.163431 -0.242579  1.000000