会员

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

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 2020310143049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 2020310143049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-2020310143049吕莹')
plt.show()
plt.close

# 去除票价为空的记录
airline_notnull = data.loc[data['SUM_YR_1'].notnull() & 
                                   data['SUM_YR_2'].notnull(),:]
print('删除缺失记录后数据的形状为：',airline_notnull.shape)

# 只保留票价非零的，或者平均折扣率不为0且总飞行公里数大于0的记录。
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  # 去除年龄大于100的记录
airline = airline_notnull[(index1 | index2) & index3 & ~index4]
print('数据清洗后数据的形状为：',airline.shape)

import pandas as pd
import numpy as np