# 模块
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import scipy.stats as st
plt.rc("font",family="SimHei",size="12")  #解决中文无法显示的问题

# 导入数据
dianxin=pd.read_csv('F:\python\电信用户数据\WA_Fn-UseC_-Telco-Customer-Churn.csv')


train_data.head()
train_data.describe()
train_data.info()
train_data.shape  #(7043, 21)

#类别特征
object_col=dianxin.select_dtypes(include=[np.object]).columns
'''
Index(['customerID', 'gender', 'Partner', 'Dependents', 'PhoneService',
       'MultipleLines', 'InternetService', 'OnlineSecurity', 'OnlineBackup',
       'DeviceProtection', 'TechSupport', 'StreamingTV', 'StreamingMovies',
       'Contract', 'PaperlessBilling', 'PaymentMethod', 'TotalCharges',
       'Churn'],
      dtype='object')
'''

#数值特征
num_col=dianxin.select_dtypes(include=[np.number]).columns
'''
Index(['SeniorCitizen', 'tenure', 'MonthlyCharges'], dtype='object')
'''


#单变量可视化
#首先看一些大体的分布如何，后面才好画图
for i in object_col:
    print(i,train_data[i].nunique())


#customerID，TotalCharges,可以不用画图
object_col=['gender', 'Partner', 'Dependents', 'PhoneService',
       'MultipleLines', 'InternetService', 'OnlineSecurity', 'OnlineBackup',
       'DeviceProtection', 'TechSupport', 'StreamingTV', 'StreamingMovies',
       'Contract', 'PaperlessBilling', 'PaymentMethod', 
       'Churn']

fig = plt.figure(figsize=[16,40])
for col,i in zip(object_col,range(1,17)):
    axes = fig.add_subplot(9,2,i)
    sns.countplot(train_data[col],ax=axes)
plt.show()

for i in object_col:
    for j in train_data[i].value_counts(normalize = True).index:
        print(i,'=',j,":",round(train_data[i].value_counts(normalize = True)[j]*100,2),'%')
    print('                                                                               ')

'''
1.样本是否均匀
gender：性别。（Female & Male） 比较平均
Partner ：是否有配偶 （Yes or No）比较平均
Dependents ：是否经济独立 （Yes or No）不独立的占比约60%
PhoneService ：是否开通电话服务业务 （Yes or No） 很不均衡，开通的约占80%多
MultipleLines：是否开通了多线业务（Yes 、No or No phoneservice 三种）
InternetService：是否开通互联网服务 （No, DSL数字网络，fiber optic光纤网络 三种）
OnlineSecurity：是否开通网络安全服务（Yes，No，No internetserive 三种）
OnlineBackup：是否开通在线备份业务（Yes，No，No internetserive 三种）
DeviceProtection：是否开通了设备保护业务（Yes，No，No internetserive 三种）
TechSupport：是否开通了技术支持服务（Yes，No，No internetserive 三种）
StreamingTV：是否开通网络电视（Yes，No，No internetserive 三种）
StreamingMovies：是否开通网络电影（Yes，No，No internetserive 三种）
Contract：签订合同方式 （按月，一年，两年）
PaperlessBilling：是否开通电子账单（Yes or No）
PaymentMethod：付款方式（bank transfer，credit card，electronic check，mailed check）
Churn：该用户是否流失（Yes or No）
'''

#但是我们注意到下面，有三个值（类似于No phone service和No）其实是二个值
two_no_col=['MultipleLines' , 'OnlineSecurity', 'OnlineBackup', 'DeviceProtection', 'TechSupport', 'StreamingTV', 'StreamingMovies']
dict1={'No phone service':'No',
      'No':'No',
      'Yes':'Yes'}
train_data['MultipleLines']=train_data['MultipleLines'].map(dict1)

dict2={'No internet service':'No',
      'No':'No',
      'Yes':'Yes'}
for i in ['OnlineSecurity', 'OnlineBackup', 'DeviceProtection', 'TechSupport', 'StreamingTV', 'StreamingMovies']:
    train_data[i]=train_data[i].map(dict2)

fig = plt.figure(figsize=[16,20])
for col,i in zip(two_no_col,range(1,8)):
    axes = fig.add_subplot(4,2,i)
    sns.countplot(train_data[col],ax=axes)
plt.show()

for i in two_no_col:
    for j in train_data[i].value_counts(normalize = True).index:
        print(i,'=',j,":",round(train_data[i].value_counts(normalize = True)[j]*100,2),'%')
    print('                                                                               ')

#类别变量和y值的可视化
#但是要注意，barplot需要y值是数值型的，现在我们先把y值转化成数值型的，Churn=1即是逾期
train_data.Churn[train_data['Churn']=='No']=0
train_data.Churn[train_data['Churn']=='Yes']=1

fig = plt.figure(figsize=[16,40])
for col,i in zip(object_col,range(1,17)):
    axes = fig.add_subplot(8,2,i)
    sns.barplot(train_data[col],train_data['Churn'],ax=axes)
plt.show()

#不要y值
col=['gender', 'Partner', 'Dependents', 'PhoneService',
       'MultipleLines', 'InternetService', 'OnlineSecurity', 'OnlineBackup',
       'DeviceProtection', 'TechSupport', 'StreamingTV', 'StreamingMovies',
       'Contract', 'PaperlessBilling', 'PaymentMethod',]
for i in col:
    for j in train_data[i].value_counts(normalize = True).index:
        print(i,'=',j,"的违约概率:",round(train_data.Churn[train_data[i]==j].value_counts(normalize = True)[1]*100,2),'%')
    print('                                                                               ')

#单变量可视化（连续型）
#['SeniorCitizen', 'tenure', 'MonthlyCharges']  
#再加上上面的  TotalCharges
#仔细一卡，SeniorCitizen是否是老年人，这个字段也是离散型的，我们应该将他放到离散型里面，
#职业有74个值，而且还是加密的，我想把这个变量删除，如果是中文还好处理一点，但是是数值型就有点难处理了
num_col=['SeniorCitizen', 'tenure', 'MonthlyCharges','TotalCharges'] 
train_data[num_col]

#先看老年人这个字段
fig, axes = plt.subplots(1,2,figsize=(12,6))
train_data['SeniorCitizen'].value_counts().plot.bar(ax=axes[0])
sns.barplot(train_data['SeniorCitizen'],train_data['Churn'],ax=axes[1])
print(train_data['SeniorCitizen'].value_counts()/len(train_data))

#看一下职业的,太离散了，删除吧
#然后就是
#MonthlyCharges：月费用
#TotalCharges：总费用
#先把总费用转为数值型

train_data.TotalCharges.value_counts()
#发现有11个' '值
#反正只有11个值，删除了没有影响
train_data['TotalCharges'].replace(' ',np.nan,inplace=True)
train_data=train_data.dropna()
train_data.TotalCharges=train_data.TotalCharges.astype(np.float64)
train_data.TotalCharges.dtype  #dtype('float64')
#看一下两个费用相关性如何
train_data[['MonthlyCharges','TotalCharges']].corr()
'''
MonthlyCharges  TotalCharges
MonthlyCharges  1.000000    0.651065
TotalCharges    0.651065    1.000000
'''
#看看违约用户的费用的箱型图有啥区别
plt.boxplot((train_data.MonthlyCharges[train_data.Churn==0],train_data.MonthlyCharges[train_data.Churn==1]),labels=('Churn==0','Churn==1'))
plt.title('月费用')
plt.show()

plt.boxplot((train_data.TotalCharges[train_data.Churn==0],train_data.TotalCharges[train_data.Churn==1]),labels=('Churn==0','Churn==1'))
plt.title('总费用')
plt.show()

#费用的分布
fig, axes = plt.subplots(1,2,figsize=(12,6))
sns.distplot(  train_data.MonthlyCharges, ax=axes[0])
sns.distplot(  train_data.TotalCharges, ax=axes[1])


#特征工程
train=pd.read_csv('F:\python\电信用户数据\WA_Fn-UseC_-Telco-Customer-Churn.csv')
#1.缺失值处理,我们知道总费用有11个‘-’类型的缺失值，我们先使用空值填充，然后再删除
train['TotalCharges'].replace(' ',np.nan,inplace=True)
train=train.dropna()

#处理同一个意思，却有两种表达方式的特征
two_no_col=['MultipleLines' , 'OnlineSecurity', 'OnlineBackup', 'DeviceProtection', 'TechSupport', 'StreamingTV', 'StreamingMovies']
dict1={'No phone service':'No',
      'No':'No',
      'Yes':'Yes'}
train['MultipleLines']=train['MultipleLines'].map(dict1)

dict2={'No internet service':'No',
      'No':'No',
      'Yes':'Yes'}
for i in ['OnlineSecurity', 'OnlineBackup', 'DeviceProtection', 'TechSupport', 'StreamingTV', 'StreamingMovies']:
    train[i]=train[i].map(dict2)

#处理费用，首先我们先构造一个使用月长的字段，后面再做两个版本，一个是数值型特征有进行数据分箱，一个是没有分箱
#先将总费用的类型改为数值型
train.TotalCharges=train.TotalCharges.astype(np.float64)
train.TotalCharges.dtype  #dtype('float64')
#构造使用月长
train['use_month']=round(train.TotalCharges/train_data.MonthlyCharges,0)
#特征分箱，这次的版本先不用分箱

#类别特征做One-hot
#首先要删除customerID
customerID=train.pop('customerID')
train.pop('tenure')
train.columns
'''
Index(['gender', 'SeniorCitizen', 'Partner', 'Dependents', 'tenure',
       'PhoneService', 'MultipleLines', 'InternetService', 'OnlineSecurity',
       'OnlineBackup', 'DeviceProtection', 'TechSupport', 'StreamingTV',
       'StreamingMovies', 'Contract', 'PaperlessBilling', 'PaymentMethod',
       'MonthlyCharges', 'TotalCharges', 'Churn', 'use_month'],
      dtype='object')
'''
onehot_col=['gender', 'SeniorCitizen', 'Partner', 'Dependents', 
       'PhoneService', 'MultipleLines', 'InternetService', 'OnlineSecurity',
       'OnlineBackup', 'DeviceProtection', 'TechSupport', 'StreamingTV',
       'StreamingMovies', 'Contract', 'PaperlessBilling', 'PaymentMethod']
train[onehot_col] = train[onehot_col].astype(str)

feature_dummies = pd.get_dummies(train[onehot_col])
# feature_dummies.head()
train.drop(onehot_col, inplace=True, axis=1)
train = pd.concat((train, feature_dummies), axis=1)
train.head()

#首先要将特征值换成0,1
train.Churn[train['Churn']=='No']=0
train.Churn[train['Churn']=='Yes']=1
train.Churn=train.Churn.astype(np.int64)

plt.figure(figsize=(20,16))
sns.heatmap(train.corr(),xticklabels=train.corr().columns, yticklabels=train.corr().columns, 
                 linewidths=0.2, cmap="YlGnBu",annot=True)











#模型训练
#首先导入模快和分好x和y 
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import confusion_matrix, roc_curve,roc_auc_score,classification_report ,auc
from sklearn.model_selection import train_test_split
train_y=train['Churn'].values
train_x=train
x_train,x_test,y_train,y_test=train_test_split(train_x,train_y,test_size=0.3,random_state=0)
#逻辑回归
clf = LogisticRegression()
clf.fit(x_train.values,y_train)

#训练集测试auc
p=clf.predict(x_train)
fpr, tpr, p_threshold = metrics.roc_curve(y_train, p,
                                              drop_intermediate=False,
                                              pos_label=1)
auc(fpr, tpr) #1

#用测试集进行检验
p=clf.predict(x_test)
fpr, tpr, p_threshold = metrics.roc_curve(y_test, p,
                                              drop_intermediate=False,
                                              pos_label=1)
auc(fpr, tpr)  #1


#########################################################################
D