第七章 --- 航空预测

1.数据描述与探索

 

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
#对数据进行基本的探索
#返回缺失值个数以及最大最小值
import pandas as pd
 
datafile = './air_data.csv'#航空公司原始数据，第一行是属性名
result = 'explore.xlsx'
 
data = pd.read_csv(datafile, encoding='utf-8')
explore = data.describe( percentiles = [],include = 'all').T
 
explore['null'] = len(data)-explore['count']
 
explore1 = explore[['null','max','min']]
explore1.columns = [u'空值数',u'最大值',u'最小值']#重命名列名
 
explore1.to_excel(result)

（部分数据）

 

# 
from datetime import datetime
datafile = './air_data.csv'#航空公司原始数据，第一行是属性名

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

import matplotlib.pyplot as plt
fig = plt.figure(figsize=(10,6))  # 设置图框大小尺寸
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示中文标签
plt.hist(ffp_year,bins = 'auto',color = '#0488bb')
plt.xlabel('年份')
plt.ylabel('入会人数')
plt.title('3148-Tang各年份会员入会人数',fontsize=20)
plt.show()

 

from datetime import datetime
datafile = './air_data.csv'#航空公司原始数据，第一行是属性名

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

#绘制饼图
fig = plt.figure(figsize=(10,6))  # 设置图框大小尺寸
plt.pie([male,female],labels = ['男','女'],colors = ['lightskyblue','lightcoral'],autopct = '%1.1f%%')# 绘制饼图
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.title('3148-Tang会员性别比例（饼图）',fontsize=15)
plt.axis('equal')
plt.show()

 

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3148-tang')

 

 

?

1 2 3 4 5 6 7 8 9 10 11

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3148-tang') 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=(10,6))
plt.boxplot(lte,
            patch_artist=True,
            labels = ['时长'],
            boxprops = {'facecolor':'yellow'})
plt.title('会员最后乘机至结束时长分布箱型图3148-tang')

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

fig = plt.figure(figsize=(10,6))
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3148-tang')
plt.grid(axis='y')
plt.show()
plt.close

fig = plt.figure(figsize=(10,6))
plt.boxplot(sks,
            patch_artist=True,
            labels=['总飞行公里数'],
            boxprops = {'facecolor':'green'})
plt.title('客户总飞行公里数箱型图3148-tang')
plt.grid(axis='y')
plt.show()
plt.close

 

 

 

 

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3148-tang')
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':'green'})
plt.title('客户总累计积分箱型图3148-tang')
plt.grid(axis='y')
plt.show()
plt.close

 

 

 

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')

# 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='Accent')
plt.show()
plt.title('相关性热力图-Tang')
plt.close

2.清洗数据

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
 
df = pd.read_csv('./air_data.csv',header=0)
 
# 行数、列数
df.shape
# 预览数据
df.head()

# 查看每个特征的总条数以及五值分布：平均值、最大值、最小值、标准差、四分位数。
df.describe().T

 

# 将需要保留的记录筛选出来，丢弃异常数据
# 筛选 的记录
df_notnull = df.loc[df['SUM_YR_1'].notnull() & df['SUM_YR_2'].notnull(),:] #选取总票价非空的记录
 
idx_tmp1 = df_notnull['SUM_YR_1'] !=0  # Y1 票价不为0的 index
idx_tmp2 = df_notnull['SUM_YR_2'] !=0  # Y2 票价不为0的 index
idx_tmp3 = (df_notnull['avg_discount'] !=0) & (df_notnull['SEG_KM_SUM']>0)  # 平均折扣＞0 且飞行里程＞0的 index
idx_tmp4 = df_notnull['AGE'] >= 100 # 年龄≥100的异常数据的index
 
# 丢弃异常数据，并将数据存入csv文件
df_data_clean = df_notnull[(idx_tmp1|idx_tmp2) & idx_tmp3 & ~idx_tmp4]
df_data_clean.to_csv('data_clean.csv')
 
df_data_clean.shape
df_data_clean.describe().T

# 重新检查清洗后的数据
df_data_clean = pd.read_csv('./data_clean.csv', header=0)
# df_data_clean.isnull().sum().sort_values(ascending=False)
# 用年龄平均值填充年龄缺失值
df_data_clean['AGE'].fillna(df_data_clean['AGE'].mean(), inplace=True)
df_data_clean.isnull().sum().sort_values(ascending=False)

3.属性构造

 

data_clean = pd.read_csv('./data_clean.csv', header=0)
# 选择 LRFMC模型的6个属性
data_select = data_clean[['FFP_DATE','LOAD_TIME','LAST_TO_END', 'FLIGHT_COUNT','SEG_KM_SUM','avg_discount']]
 
# 构造指标L
L = pd.to_datetime(data_select['LOAD_TIME']) - pd.to_datetime(data_select['FFP_DATE']) # 日期差，但有 " days" 单位尾缀，需要删除单位
# L 值中存在" days"单位子串 
L = L.astype('str').str.split().str[0]
L=pd.to_numeric(L) # object -> int64
 
# 构造 LRFMC 模型指标
mdl_LRFMC = pd.concat([L, data_select.iloc[:, 2:]], axis=1)
mdl_LRFMC.columns = ['L','R','F','M','C']
mdl_LRFMC
# mdl_LRFMC.to_csv('LRFMC.csv')

 

 

mdl_LRFMC.describe().loc[['min','max','mean','std','50%']].T

 

# 数据标准化
def zscore_data(data):
    data2=(data-data.mean(axis=0))/data.std(axis=0)
    data2.columns=["Z"+i for i in data.columns]
    return data2
 
z_LRFMC = zscore_data(mdl_LRFMC)
z_LRFMC.head()

 

%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3148-tang')
plt.legend(legen)
plt.show()
plt.close

4.预测

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('./WA_Fn-UseC_-Telco-Customer-Churn.csv')
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('MonthlyCharges3148-tang')
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('TotalCharges3148-tang')
# 子图间距
plt.subplots_adjust(left=None, bottom=None, right=None, top=None, wspace=0.5, hspace=0.5)
plt.show()

 

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+ '3148-tang')
    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+ '3148-tang')
    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 + '3148-tang')
    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("MonthlyCharges3148-tang")
plt.show()
 
sns.distplot(df.query("Churn == 'Yes'")["TotalCharges"])
plt.title("TotalCharges3148tang")
plt.show()