航空公司客户价值分析

描述性统计分析

import pandas as pd
datafile='D:\Python\数据处理/air_data.csv'
resultfile='D:\Python\数据处理/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)

分布分析

from datetime import datetime
import matplotlib.pyplot as plt
ffp = data['FFP_DATE'].apply(lambda x:datetime.strptime(x,'%Y/%m/%d'))
ffp_year = ffp.map(lambda x:x.year)

fig = plt.figure(figsize = (8,5))
plt.rcParams['font.sans-serif'] = 'SimHei'
plt.rcParams['axes.unicode_minus'] = False
plt.hist(ffp_year,bins='auto',color = '#0504aa')
plt.xlabel('年份')
plt.ylabel('入会年份')
plt.title('各年份会员入会人数3152')
plt.show()
plt.close

male = pd.value_counts(data['GENDER'])['男']
female = pd.value_counts(data['GENDER'])['女']

fig = plt.figure(figsize = (7,4))
plt.pie([male,female],labels=['男','女'],colors=['lightskyblue','lightcoral'],autopct='%1.lf%%')
plt.title('会员性别比例3152')
plt.show()
plt.close

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]

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3152')

age = data['AGE'].dropna()
age = age.astype('int64')
fig = plt.figure(figsize = (5,10))
plt.boxplot(age,
            patch_artist = True,
            labels = ['会员年龄'],
            boxprops = {'facecolor':'lightblue'})
plt.title('会员年龄分布箱型图3152')
plt.grid(axis='y')
plt.show()
plt.close

lte = data['LAST_TO_END']
fc = data['FLIGHT_COUNT']
sks = data['SEG_KM_SUM']
#乘机时长
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3152')

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3152')
plt.grid(axis='y')
plt.show()
plt.close

fig = plt.figure(figsize=(5,10))
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3152')
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3152')
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3152')
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

# 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))
sns.heatmap(dt_corr,annot=True,vmax=1,square=True,cmap='Blues')
plt.show()
plt.close

清洗空值与异常值

import numpy as np
import pandas as pd
datafile='D:\Python\数据处理/air_data.csv'
cleanedfile='D:\Python\数据处理/data_cleaned.csv'
airline_data = pd.read_csv(datafile,encoding = 'utf-8')
print('原始数据的形状为：',airline_data.shape)

airline_notnull = airline_data.loc[airline_data['SUM_YR_1'].notnull()&airline_data['SUM_YR_2'].notnull(),:]
print('删除确实记录后数据的形状为：',airline_notnull.shape)

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
airline = airline_notnull[(index1 | index2)&index3&~index4]
print('数据清洗后数据的形状为：',airline.shape)

airline.to_csv(cleanedfile)

属性选择

import pandas as pd
import numpy as np

cleanedfile='D:\Python\数据处理/data_cleaned.csv'
airline = pd.read_csv(cleanedfile,encoding='utf-8')

airline_selection = airline[['FFP_DATE','LOAD_TIME','LAST_TO_END','FLIGHT_COUNT','SEG_KM_SUM','avg_discount']]
print('筛选的属性前5行为：\n',airline_selection.head())

属性构造与数据标准化

L = pd.to_datetime(airline_selection['LOAD_TIME'])-\
    pd.to_datetime(airline_selection['FFP_DATE'])
L = L.astype('str').str.split().str[0]
L = L.astype('int')/30

airline_features = pd.concat([L,airline_selection.iloc[:,2:]],axis=1)
print('构建的LRFMC属性前5行为：\n',airline_features.head())

from sklearn.preprocessing import StandardScaler
data = StandardScaler().fit_transform(airline_features)
np.savez('D:\Python\数据处理/airline_scale.npz',data)
print('标准化后LRFMC 5个属性为：\n',data[:5,:])

import pandas as pd
import numpy as np
from sklearn.cluster import KMeans  # 导入kmeans算法
# 读取标准化后的数据
airline_scale = np.load('D:\Python\数据处理/airline_scale.npz')['arr_0']
k = 5  # 确定聚类中心数

# 构建模型，随机种子设为123
kmeans_model = KMeans(n_clusters=k,random_state=123)
fit_kmeans = kmeans_model.fit(airline_scale)  # 模型训练

# 查看聚类结果
kmeans_cc = kmeans_model.cluster_centers_  # 聚类中心
print('各类聚类中心为：\n',kmeans_cc)
kmeans_labels = kmeans_model.labels_  # 样本的类别标签
print('各样本的类别标签为：\n',kmeans_labels)
r1 = pd.Series(kmeans_model.labels_).value_counts()  # 统计不同类别样本的数目
print('最终每个类别的数目为：\n',r1)

# 输出聚类分群的结果
cluster_center = pd.DataFrame(kmeans_model.cluster_centers_,\
             columns=['ZL','ZR','ZF','ZM','ZC'])   # 将聚类中心放在数据框中
cluster_center.index = pd.DataFrame(kmeans_model.labels_ ).\
                  drop_duplicates().iloc[:,0]  # 将样本类别作为数据框索引
print(cluster_center)

%matplotlib inline
import matplotlib.pyplot as plt
# 客户分群雷达图
labels = ['ZL','ZR','ZF','ZM','ZC']
legen = ['客户群' + str(i + 1) for i in cluster_center.index]  # 客户群命名，作为雷达图的图例
lstype = ['-','--',(0, (3, 5, 1, 5, 1, 5)),':','-.']
kinds = list(cluster_center.iloc[:, 0])
# 由于雷达图要保证数据闭合，因此再添加L列，并转换为 np.ndarray
cluster_center = pd.concat([cluster_center, cluster_center[['ZL']]], axis=1)
centers = np.array(cluster_center.iloc[:, 0:])

# 分割圆周长，并让其闭合
n = len(labels)
angle = np.linspace(0, 2 * np.pi, n, endpoint=False)
angle = np.concatenate((angle, [angle[0]]))

# 绘图
fig = plt.figure(figsize=(8,6))
ax = fig.add_subplot(111, polar=True)  # 以极坐标的形式绘制图形
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

# 画线
for i in range(len(kinds)):
    ax.plot(angle, centers[i], linestyle=lstype[i], linewidth=2, label=kinds[i])
# 添加属性标签
ax.set_thetagrids(angle * 180 / np.pi, labels)
plt.title('客户特征分析雷达图3152')
plt.legend(legen)
plt.show()
plt.close

import numpy as np
import pandas as pd
#from pyecharts.charts import *
#from pyecharts import options as opts
import matplotlib.pyplot as plt
 
plt.rcParams['font.sans-serif'] = ['Microsoft YaHei'] # 指定默认字体
plt.rcParams['axes.unicode_minus'] = False # 解决保存图像是负号'-'显示为方块的问题
 
#读取文件
df = pd.read_csv('D:/Python/数据处理/WA_Fn-UseC_-Telco-Customer-Churn.csv')

# 查看基本信息
df.info()
 
# 查看是否存在重复值--无重复值
df.duplicated().sum()

for i in df.columns:
    if i == 'SeniorCitizen':
        print(i,df[i].isnull().sum())
    elif i == 'tenure':
        print(i,df[i].isnull().sum())
    elif i == 'MonthlyCharges':  
        print(i,df[i].isnull().sum())
    else:
        print(i,df[df[i] == ' '][i].count())

# 查看分类变量的所有取值
for i in df.columns:
    if i not in ('customerID','MonthlyCharges','TotalCharges'):
        print(i,df[i].unique())

# 离散型变量分布
pic = plt.figure(figsize=(9,3),dpi=80)
pic.add_subplot(1,2,1)#第一个子图（行数，列数，本子图位置）
plt.boxplot(df["MonthlyCharges"])
plt.title('MonthlyCharges3152')
pic.add_subplot(1,2,2)#第一个子图（行数，列数，本子图位置）
plt.boxplot(df["TotalCharges"])
plt.title('TotalCharges3152')
# 子图间距
plt.subplots_adjust(left=None, bottom=None, right=None, top=None, wspace=0.5, hspace=0.5)
plt.show()

流失客户属性分析

pic = plt.figure(figsize=(12,6),dpi=80)
pic.subplots_adjust(wspace=0.3,hspace=0.3)
for i,j in zip(df.iloc[:,1:5].columns,range(1,5)):
    df_count = df.pivot_table(index='Churn',columns=i,values='customerID',aggfunc='count')
    df_ratio = df_count.div(df_count.sum())
    #print(df_ratio)
    pic.add_subplot(2,2,j)
    plt.title('Churn by '+ i++ '3152')
    plt.bar([0,1],df_ratio.iloc[0,:],label = df_ratio.index.values[0],width=0.5)
    plt.bar([0,1],df_ratio.iloc[1,:],bottom = df_ratio.iloc[0,:],label=df_ratio.index.values[1],width=0.5)
    plt.xticks([0,1],df_count.columns.values)
    for a,b in zip(range(df_ratio.shape[1]),df_ratio.iloc[1,:]):
        plt.text(a,0.88,round(b,4),va='bottom',ha='center',fontsize=12)
    plt.legend()  
plt.show()

服务属性

pic = plt.figure(figsize=(16,9),dpi=80)
pic.subplots_adjust(wspace=0.3,hspace=0.3)
for i,j in zip(df.iloc[:,6:15].columns,range(1,10)):
    df_count = df.pivot_table(index='Churn',columns=i,values='customerID',aggfunc='count')
    df_ratio = df_count.div(df_count.sum())
    
    pic.add_subplot(3,3,j)
    plt.title('Churn by '+ i+ '3152')
    plt.bar(range(df_ratio.shape[1]),df_ratio.iloc[0,:],label = df_ratio.index.values[0],width=0.5)
    plt.bar(range(df_ratio.shape[1]),df_ratio.iloc[1,:],bottom = df_ratio.iloc[0,:],label=df_ratio.index.values[1],width=0.5)
    plt.xticks(range(df_ratio.shape[1]),df_count.columns.values)
    for a,b in zip(range(df_ratio.shape[1]),df_ratio.iloc[1,:]):
        plt.text(a,0.88,round(b,4),va='bottom',ha='center',fontsize=12)
    if i=='PhoneService':
        plt.legend()  
plt.show()

消费属性

pic = plt.figure(figsize=(20,9),dpi=120)
pic.subplots_adjust(wspace=0.3,hspace=0.3)
for i,j in zip(df.iloc[:,15:18].columns,range(1,4)):
    df_count = df.pivot_table(index='Churn',columns=i,values='customerID',aggfunc='count')
    df_ratio = df_count.div(df_count.sum())
   
    pic.add_subplot(2,2,j)
    plt.title('Churn by '+ i + '3152')
    plt.bar(range(df_ratio.shape[1]),df_ratio.iloc[0,:],label = df_ratio.index.values[0],width=0.5)
    plt.bar(range(df_ratio.shape[1]),df_ratio.iloc[1,:],bottom = df_ratio.iloc[0,:],label=df_ratio.index.values[1],width=0.5)
    plt.xticks(range(df_ratio.shape[1]),df_count.columns.values)
    for a,b in zip(range(df_ratio.shape[1]),df_ratio.iloc[1,:]):
        plt.text(a,0.95,round(b,4),va='bottom',ha='center',fontsize=12)
    if i=='PaperlessBilling':   
        plt.legend()  
plt.show()

import seaborn as sns 
sns.distplot(df.query("Churn == 'Yes'")["MonthlyCharges"])
plt.title("MonthlyCharges3152")
plt.show()
 
sns.distplot(df.query("Churn == 'Yes'")["TotalCharges"])
plt.title("TotalCharges3152")
plt.show()