1、项目介绍
- 背景
携程作为中国领先的综合性旅行服务公司，每天向超过2.5亿会员提供全方位的旅行服务，在这海量的网站访问量中，我们可分析用户的行为数据来挖掘潜在的信息资源。其中，客户流失率是考量业务成绩的一个非常关键的指标。本项目的目的是为了深入了解用户画像及行为偏好，找到最优算法，挖掘出影响用户流失的关键因素，从而更好地完善产品设计、提升用户体验。 - 评估标准
评分指标为97%精确度下的召回率，即：在precision>=0.97的recall中，选取max(recall)。 -
数据集
数据集包括49个指标（某一周的数据），预测的目标样本为流失样本(即label=1)，将这些指标按订单相关、酒店相关和客户行为相关进行归类。
指标分类.png
2、项目流程
2.1 数据处理
2.1.1 目标特征分布
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from datetime import datetime
from sklearn.cluster import KMeans
from sklearn import preprocessing
from sklearn.preprocessing import StandardScaler,OneHotEncoder
from sklearn.model_selection import StratifiedKFold
from sklearn import metrics
df_orign = pd.read_csv('userlostprob_train.txt', sep='\t')
df = df_orign.copy()
df['label'].value_counts()
返回
label字段分布.PNG
流失和未流失的用户比例2:5，样本不算特别不平衡，此处不做处理。
2.1.2 处理异常值
-
通过describe函数发现，部分与价格有关的字段（delta_price1、delta_price2、lowestprice）存在负值的情况。
价格字段存在负值.PNG
存在负值的具体数量如下：
价格字段负值记录数.PNG
三个字段的分布如下：
delta_price1分布.PNG
delta_price2分布图.PNG
lowestprice分布图.PNG
根据上图可见，delta_price1【负值>=25%】、delta_price2【负值>=25%】、lowestprice【仅有1条负值记录】，考虑到字段的分布情况（近似正态分布）以及实际需求，此处用0来替换价格异常值。
df[['delta_price1','delta_price2','lowestprice']] = df[['delta_price1','delta_price2','lowestprice']].applymap(lambda x: 0 if x<0 else x)
- 24小时内登陆时长内登录时长不应该超过24小时，将大于24的值改为24
df.loc[df['landhalfhours']>24,['landhalfhours']] = 24
2.1.3 处理缺失值
各个字段缺失值情况：
nan.png
根据上图显示：几乎所有字段都存在缺失值，存在缺失值的字段均为连续性字段，其中historyvisit_7ordernum缺失值超过80%，已没有分析的必要，考虑将其删除。
剩余存在缺失值的字段，考虑用其他值来填充空值。
- 用其他字段填充
计算字段的相关性发现：
commentnums_pre和novoters_pre相关性较强；
commentnums_pre2和novoters_pre2相关性较强。
(df['commentnums_pre']/df['novoters_pre']).describe()
返回
评分率.PNG
此处取上图结果的中位数65%作为评分率，考虑用novoters_pre*65%来填充commentnums_pre,commentnums_pre/65%来填充novoters_pre。
def fill_commentnum_novoter_pre(x):
if (x.isnull()['commentnums_pre'])&(x.notnull()['novoters_pre']):
x['commentnums_pre'] = x['novoters_pre']*0.65
elif (x.notnull()['commentnums_pre'])&(x.isnull()['novoters_pre']):
x['novoters_pre'] = x['commentnums_pre']/0.65
else:
return x
return x
df[['commentnums_pre','novoters_pre']] = df[['commentnums_pre','novoters_pre']].apply(fill_commentnum_novoter_pre,axis=1)
df[['commentnums_pre','novoters_pre']].info()
返回
填充之后的缺失值情况.PNG
填充了commentnums_pre和novoters_pre的部分缺失值，剩余缺失值用中位数填充。
同上，填充commentnums_pre2和novoters_pre2字段，剩余缺失值用均值填充。
def fill_commentnum_novoter_pre2(x):
if (x.isnull()['commentnums_pre2'])&(x.notnull()['novoters_pre2']):
x['commentnums_pre2'] = x['novoters_pre2']*0.65
elif (x.notnull()['commentnums_pre2'])&(x.isnull()['novoters_pre2']):
x['novoters_pre2'] = x['commentnums_pre2']/0.65
else:
return x
return x
df[['commentnums_pre2','novoters_pre2']] = df[['commentnums_pre2','novoters_pre2']].apply(fill_commentnum_novoter_pre2,axis=1)
- 均值、中位数、0填充
#均值（极端值影响不大，符合近似正态分布的字段）
fill_mean = ['cancelrate','landhalfhours','visitnum_oneyear','starprefer','price_sensitive','lowestprice','customereval_pre2',
'uv_pre2','lowestprice_pre2','novoters_pre2','commentnums_pre2','businessrate_pre2','lowestprice_pre','hotelcr','cancelrate_pre']
df[fill_mean] = df[fill_mean].apply(lambda x:x.fillna(x.mean()))
#中位数
fill_median = ['ordernum_oneyear','commentnums_pre','novoters_pre','uv_pre','ordercanncelednum','ordercanceledprecent',
'lasthtlordergap','cityuvs','cityorders','lastpvgap','historyvisit_avghotelnum','businessrate_pre','cr','uv_pre','cr_pre'
,'novoters_pre','commentnums_pre','novoters','hoteluv','ctrip_profits','customer_value_profit']
df[fill_median] = df[fill_median].apply(lambda x:x.fillna(x.median()))
#0填充
df[['deltaprice_pre2_t1','historyvisit_visit_detailpagenum']] = df[['deltaprice_pre2_t1','historyvisit_visit_detailpagenum']].apply(lambda x:x.fillna(0))
- 聚类填充
commentnums和novoters、cancelrate、hoteluv存在较强相关性，考虑通过聚类取中位数的方式来填充commentnums。
#commentnums：当前酒店点评数
from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler
km = KMeans(n_clusters=4)
data = df.loc[:,['commentnums','novoters','cancelrate','hoteluv']]
ss = StandardScaler() # 聚类算距离，需要先标准化
data[['novoters','cancelrate','hoteluv']] = pd.DataFrame(ss.fit_transform(data[['novoters','cancelrate','hoteluv']]))
km.fit(data.iloc[:,1:])
label_pred = km.labels_
data['label_pred'] = label_pred
#metrics.calinski_harabaz_score(data.iloc[:,1:],km.labels_)
data.loc[(data['commentnums'].isnull())&(data['label_pred']==0),['commentnums']] = (data.loc[data['label_pred'] == 0,'commentnums']).median()
data.loc[(data['commentnums'].isnull())&(data['label_pred']==1),['commentnums']] = (data.loc[data['label_pred'] == 1,'commentnums']).median()
data.loc[(data['commentnums'].isnull())&(data['label_pred']==2),['commentnums']] = (data.loc[data['label_pred'] == 2,'commentnums']).median()
data.loc[(data['commentnums'].isnull())&(data['label_pred']==3),['commentnums']] = (data.loc[data['label_pred'] == 3,'commentnums']).median()
df['commentnums'] = data['commentnums']
同理，取starprefer和consuming_capacity聚类后每类avgprice的均值来填充avgprice的空值
#avgprice：starprefer,consuming_capacity
km = KMeans(n_clusters=5)
data = df.loc[:,['avgprice','starprefer','consuming_capacity']]
ss = StandardScaler() # 聚类算距离，需要先标准化
data[['starprefer','consuming_capacity']] = pd.DataFrame(ss.fit_transform(data[['starprefer','consuming_capacity']]))
km.fit(data.iloc[:,1:])
label_pred = km.labels_
data['label_pred'] = label_pred
#metrics.calinski_harabaz_score(data.iloc[:,1:],km.labels_)
data.loc[(data['avgprice'].isnull())&(data['label_pred']==0),['avgprice']] = (data.loc[data['label_pred'] == 0,'avgprice']).mean()
data.loc[(data['avgprice'].isnull())&(data['label_pred']==1),['avgprice']] = (data.loc[data['label_pred'] == 1,'avgprice']).mean()
data.loc[(data['avgprice'].isnull())&(data['label_pred']==2),['avgprice']] = (data.loc[data['label_pred'] == 2,'avgprice']).mean()
data.loc[(data['avgprice'].isnull())&(data['label_pred']==3),['avgprice']] = (data.loc[data['label_pred'] == 3,'avgprice']).mean()
data.loc[(data['avgprice'].isnull())&(data['label_pred']==4),['avgprice']] = (data.loc[data['label_pred'] == 4,'avgprice']).mean()
df['avgprice'] = data['avgprice']
取consuming_capacity和avgprice聚类后的中位数来填充delta_price1
#delta_price1：consuming_capacity,avgprice
km = KMeans(n_clusters=6)
data = df.loc[:,['delta_price1','consuming_capacity','avgprice']]
ss = StandardScaler() # 聚类算距离，需要先标准化
data[['consuming_capacity','avgprice']] = pd.DataFrame(ss.fit_transform(data[['consuming_capacity','avgprice']]))
km.fit(data.iloc[:,1:])
label_pred = km.labels_
data['label_pred'] = label_pred
#metrics.calinski_harabaz_score(data.iloc[:,1:],km.labels_)
data.loc[(data['delta_price1'].isnull())&(data['label_pred']==0),['delta_price1']] = 187#data['fill0']
data.loc[(data['delta_price1'].isnull())&(data['label_pred']==1),['delta_price1']] = 100#data['fill1']
data.loc[(data['delta_price1'].isnull())&(data['label_pred']==2),['delta_price1']] = 26#data['fill2']
data.loc[(data['delta_price1'].isnull())&(data['label_pred']==3),['delta_price1']] = 1269#data['fill0']
data.loc[(data['delta_price1'].isnull())&(data['label_pred']==4),['delta_price1']] = 323#data['fill0']
data.loc[(data['delta_price1'].isnull())&(data['label_pred']==5),['delta_price1']] = 573#data['fill0']
df['delta_price1'] = data['delta_price1']
取 consuming_capacity和avgprice聚类delta_price2的中位数来填充delta_price2
#delta_price2: consuming_capacity,avgprice
km = KMeans(n_clusters=5)
data = df.loc[:,['delta_price2','avgprice','consuming_capacity']]
ss = StandardScaler() # 聚类算距离，需要先标准化
data[['avgprice','consuming_capacity']] = pd.DataFrame(ss.fit_transform(data[['avgprice','consuming_capacity']]))
km.fit(data.iloc[:,1:])
label_pred = km.labels_
data['label_pred'] = label_pred
#metrics.calinski_harabaz_score(data.iloc[:,1:],km.labels_)
data.loc[(data['delta_price2'].isnull())&(data['label_pred']==0),['delta_price2']] = 91#data['fill0']
data.loc[(data['delta_price2'].isnull())&(data['label_pred']==1),['delta_price2']] = 419#data['fill1']
data.loc[(data['delta_price2'].isnull())&(data['label_pred']==2),['delta_price2']] = 18#data['fill2']
data.loc[(data['delta_price2'].isnull())&(data['label_pred']==3),['delta_price2']] = 205#data['fill0']
data.loc[(data['delta_price2'].isnull())&(data['label_pred']==4),['delta_price2']] = 1042#data['fill0']
df['delta_price2'] = data['delta_price2']
-
分段填充
consuming_capacity和starprefer相关，考虑通过starprefer分段来填充consuming_capacity。
看一下这两个字段的描述情况：
描述0.PNG
描述1.PNG
描述2.PNG
描述3.PNG
根据上述描述情况，将starprefer分成三段，将每块区域内consuming_capacity的均值来填充consuming_capacity的空值。
fill1 = df.loc[df['starprefer']<60,['consuming_capacity']].mean()
fill2 = df.loc[(df['starprefer']<80)&(df['starprefer']>=60),['consuming_capacity']].mean()
fill3 = df.loc[df['starprefer']>=80,['consuming_capacity']].mean()
def fill_consuming_capacity(x):
if x.isnull()['consuming_capacity']:
if x['starprefer']<60:
x['consuming_capacity'] = fill1
elif (x['starprefer']<80)&(x['starprefer']>=60):
x['consuming_capacity'] = fill2
else:
x['consuming_capacity'] = fill3
else:
return x
return x
df[['consuming_capacity','starprefer']] = df[['consuming_capacity','starprefer']].apply(fill_consuming_capacity,axis=1)
以上，缺失值处理完毕
2.2 特征工程
2.2.1 新增字段
- 时间字段
新增字段：访问日期和入住日期间隔天数booking_gap、入住日期是星期几week_day、入住日期是否是周末is_weekend
#格式为年-月-日
df[['d','arrival']] = df[['d','arrival']].apply(lambda x:pd.to_datetime(x,format='%Y-%m-%d'))
#访问日期和入住日期间隔天数
df['booking_gap'] = ((df['arrival']-df['d'])/np.timedelta64(1,'D')).astype(int)
#入住日期是星期几
df['week_day'] = df['arrival'].map(lambda x:x.weekday())
#入住日期是否是周末
df['is_weekend'] = df['week_day'].map(lambda x: 1 if x in (5,6) else 0)
- 是否是同一个样本【选取部分客户行为指标】
查看字段sid，发现95%都是老用户，新用户很少，一周内部分用户可能会下多个订单，为了方便后续划分训练集和验证集，此处添加一个user_tag来区分是否是同一个用户的订单。
df['user_tag'] = df['ordercanceledprecent'].map(str) + df['ordercanncelednum'].map(str) + df['ordernum_oneyear'].map(str) +\
df['starprefer'].map(str) + df['consuming_capacity'].map(str) + \
df['price_sensitive'].map(str) + df['customer_value_profit'].map(str) + df['ctrip_profits'].map(str) +df['visitnum_oneyear'].map(str) + \
df['historyvisit_avghotelnum'].map(str) + df['businessrate_pre2'].map(str) +\
df['historyvisit_visit_detailpagenum'].map(str) + \
df['delta_price2'].map(str) + \
df['commentnums_pre2'].map(str) + df['novoters_pre2'].map(str) +df['customereval_pre2'].map(str) + df['lowestprice_pre2'].map(str)
df['user_tag'] = df['user_tag'].apply(lambda x : hash(x))
df['user_tag'].unique().shape
返回670226，即实际这周有670226个用户下过订单。
- 用户字段和酒店字段
选取部分用户相关字段进行聚类创建用户字段user_group，选取部分酒店相关字段进行聚类创建酒店字段hotel_group。
user_group = ['ordercanceledprecent','ordercanncelednum','ordernum_oneyear',
'historyvisit_visit_detailpagenum','historyvisit_avghotelnum']
hotel_group = ['commentnums', 'novoters', 'lowestprice', 'hotelcr', 'hoteluv', 'cancelrate']
#聚类之前先标准化
km_user = pd.DataFrame(df[user_group])
km_hotel = pd.DataFrame(df[hotel_group])
ss = StandardScaler()
for i in range(km_user.shape[1]):
km_user[user_group[i]] = ss.fit_transform(df[user_group[i]].values.reshape(-1, 1)).ravel()
ss = StandardScaler()
for i in range(km_hotel.shape[1]):
km_hotel[hotel_group[i]] = ss.fit_transform(df[hotel_group[i]].values.reshape(-1, 1)).ravel()
df['user_group'] = KMeans(n_clusters=3).fit_predict(km_user)
# score = metrics.calinski_harabaz_score(km_user,KMeans(n_clusters=3).fit(km_user).labels_)
# print('数据聚calinski_harabaz指数为：%f'%(score)) #3:218580.269018 4:218580.416497 5:218581.368953 6:218581.203569
df['hotel_group'] = KMeans(n_clusters=5).fit_predict(km_hotel)
# score = metrics.calinski_harabaz_score(km_hotel,KMeans(n_clusters=3).fit(km_hotel).labels_)
# print('数据聚calinski_harabaz指数为：%f'%(score)) #3：266853.481135 4:268442.314369 5:268796.468103 6:268796.707149
2.2.2 连续特征离散化
historyvisit_avghotelnum大部分都小于5，将字段处理成小于等于5和大于5的离散值；
ordercanncelednum大部分都小于5，将字段处理成小于等于5和大于5的离散值；
sid等于1是新访设为0，其他设为1为老用户。
avgprice、lowestprice、starprefer、consuming_capacity和h进行数值分段离散化。
df['historyvisit_avghotelnum'] = df['historyvisit_avghotelnum'].apply(lambda x: 0 if x<=5 else 1)
df['ordercanncelednum'] = df['ordercanncelednum'].apply(lambda x: 0 if x<=5 else 1)
df['sid'] = df['sid'].apply(lambda x: 0 if x==1 else 1)
#分段离散化
def discrete_avgprice(x):
if x<=200:
return 0
elif x<=400:
return 1
elif x<=600:
return 2
else:
return 3
def discrete_lowestprice(x):
if x<=100:
return 0
elif x<=200:
return 1
elif x<=300:
return 2
else:
return 3
def discrete_starprefer(x):
if x==0:
return 0
elif x<=60:
return 1
elif x<=80:
return 2
else:
return 3
def discrete_consuming_capacity(x):
if x<0:
return 0
elif x<=20:
return 1
elif x<=40:
return 2
elif x<=60:
return 3
else:
return 4
def discrete_h(x):
if x>=0 and x<6:#凌晨访问
return 0
elif x<12:#上午访问
return 1
elif x<18:#下午访问
return 2
else:
return 3#晚上访问
df['avgprice'] = df['avgprice'].map(discrete_avgprice)
df['lowestprice'] = df['lowestprice'].map(discrete_lowestprice)
df['starprefer'] = df['starprefer'].map(discrete_starprefer)
df['consuming_capacity'] = df['consuming_capacity'].map(discrete_consuming_capacity)
df['h'] = df['h'].map(discrete_h)
对当前的数值型类别变量进行离散特征热编码，此处用OneHotEncoder方法
discrete_field = ['historyvisit_avghotelnum','ordercanncelednum'
,'avgprice','lowestprice','starprefer','consuming_capacity','user_group',
'hotel_group','is_weekend','week_day','sid','h']
encode_df = pd.DataFrame(preprocessing.OneHotEncoder(handle_unknown='ignore').fit_transform(df[discrete_field]).toarray())
encode_df_new = pd.concat([df.drop(columns=discrete_field,axis=1),encode_df],axis=1)
2.2.3 删除字段
去掉两类字段：
d、arrival、sampleid、firstorder_bu这几个对分析没有意义的字段；
historyvisit_totalordernum和ordernum_oneyear这两个字段值相等，此处取ordernum_oneyear这个字段，删除historyvisit_totalordernum；
decisionhabit_user和historyvisit_avghotelnum数值较一致，此处选择historyvisit_avghotelnum，删除decisionhabit_user。
encode_df_new = encode_df_new.drop(columns=['d','arrival','sampleid','historyvisit_totalordernum','firstorder_bu','decisionhabit_user'],axis=1)
encode_df_new.shape
最终去除目标字段label和划分训练集字段user_tag，共有79个字段。
2.3 模型训练
2.3.1 划分训练集和验证集
为了保证训练集和验证集独立同分布，将数据按照user_tag进行排序，取前70%作为训练集，剩余的作为验证集。
ss_df_new = encode_df_new
num = ss_df_new.shape[0]
df_sort = ss_df_new.sort_values(by=['user_tag'],ascending=True)
train_df = df_sort.iloc[:int(num*0.7),:]
test_df = df_sort.iloc[int(num*0.7):,:]
train_y = train_df['label']
train_x = train_df.iloc[:,1:]
test_y = test_df['label']
test_x = test_df.iloc[:,1:]
2.3.2 比较各个模型的训练效果
所有模型的调参都采用GridSearchCV网格搜索进行。
- GBDT
#调整的参数：
#n_estimators
#max_depth和min_samples_split
#min_samples_split和min_samples_leaf
#max_features
#subsample
#learning_rate，需要配合调整n_estimators
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.model_selection import GridSearchCV
#最终的参数结果
gbc = GradientBoostingClassifier(loss='deviance',random_state=2019,learning_rate=0.05, n_estimators=200,min_samples_split=4,
min_samples_leaf=1,max_depth=11,max_features='sqrt', subsample=0.8)
gbc.fit(train_x,train_y)
predict_train = gbc.predict_proba(train_x)[:,1]
predict_test = gbc.predict_proba(test_x)[:,1]
pr_train,re_train,thre_train = metrics.precision_recall_curve(train_y,predict_train)
pr_test,re_test,thre_test = metrics.precision_recall_curve(test_y,predict_test)
auc_train = metrics.roc_auc_score(train_y,predict_train)
auc_test = metrics.roc_auc_score(test_y,predict_test)
prt_train = pd.DataFrame({'precision':pr_train,'recall':re_train})
prt_test = pd.DataFrame({'precision':pr_test,'recall':re_test})
print('调参之后：测试集中precision>=0.97对应的最大recall为：')
print(prt_test.loc[prt_test['precision']>=0.97,'recall'].max())
print('auc得分为：{}'.format(auc_test))
返回
0.15988300816140671
0.8808204850185188
- xgboost
#调整的参数：
#迭代器个数n_estimators
#min_child_weight以及max_depth
#gamma值
##subsample 和 colsample_bytree
#learning_rate，需要配合调整n_esgtimators
from xgboost.sklearn import XGBClassifier
xgbc = XGBClassifier(learning_rate=0.05, objective= 'binary:logistic', nthread=1, scale_pos_weight=1, seed=27,
subsample=0.6, colsample_bytree=0.6, gamma=0, reg_alpha= 0, reg_lambda=1,max_depth=38,min_child_weight=1,n_estimators=210)
xgbc.fit(train_x,train_y)
predict_train = xgbc.predict_proba(train_x)[:,1]
predict_test = xgbc.predict_proba(test_x)[:,1]
pr_train,re_train,thre_train = metrics.precision_recall_curve(train_y,predict_train)
pr_test,re_test,thre_test = metrics.precision_recall_curve(test_y,predict_test)
auc_train = metrics.roc_auc_score(train_y,predict_train)
auc_test = metrics.roc_auc_score(test_y,predict_test)
prt_train = pd.DataFrame({'precision':pr_train,'recall':re_train})
prt_test = pd.DataFrame({'precision':pr_test,'recall':re_test})
print('precision>=0.97时对应的最大recall为：')
print(prt_test.loc[prt_test['precision']>=0.97,'recall'].max())
print('auc得分为：{}'.format(auc_test))
返回
0.7640022417597814
0.9754939563495324
- 随机森林
#调整的参数：
#n_estimators
#max_depth
from sklearn.ensemble import RandomForestClassifier
rf = RandomForestClassifier(n_estimators=300,max_depth=50)
rf.fit(train_x,train_y)
predict_train = rf.predict_proba(train_x)[:,1]
predict_test = rf.predict_proba(test_x)[:,1]
pr_train,re_train,thre_train = metrics.precision_recall_curve(train_y,predict_train)
pr_test,re_test,thre_test = metrics.precision_recall_curve(test_y,predict_test)
auc_train = metrics.roc_auc_score(train_y,predict_train)
auc_test = metrics.roc_auc_score(test_y,predict_test)
prt_train = pd.DataFrame({'precision':pr_train,'recall':re_train})
prt_test = pd.DataFrame({'precision':pr_test,'recall':re_test})
print('precision>=0.97时对应的最大recall为：')
print(prt_test.loc[prt_test['precision']>=0.97,'recall'].max())
print('auc得分为：{}'.format(auc_test))
返回
0.666135416301797
0.9616117844760916
- Adaboost
bdt = AdaBoostClassifier(algorithm="SAMME",
n_estimators=600, learning_rate=1)
bdt.fit(train_x,train_y)
predict_train = bdt.predict_proba(train_x)[:,1]
predict_test = bdt.predict_proba(test_x)[:,1]
pr_train,re_train,thre_train = metrics.precision_recall_curve(train_y,predict_train)
pr_test,re_test,thre_test = metrics.precision_recall_curve(test_y,predict_test)
auc_train = metrics.roc_auc_score(train_y,predict_train)
auc_test = metrics.roc_auc_score(test_y,predict_test)
prt_train = pd.DataFrame({'precision':pr_train,'recall':re_train})
prt_test = pd.DataFrame({'precision':pr_test,'recall':re_test})
print('precision>=0.97时对应的最大recall为：')
print(prt_test.loc[prt_test['precision']>=0.97,'recall'].max())
print('auc得分为：{}'.format(auc_test))
返回
0.00019265123121650496
0.7300356696791559
- DecisionTree
from sklearn.tree import DecisionTreeClassifier
bdt = DecisionTreeClassifier(random_state=0,max_depth=30, min_samples_split=70)
bdt.fit(train_x,train_y)
predict_train = bdt.predict_proba(train_x)[:,1]
predict_test = bdt.predict_proba(test_x)[:,1]
pr_train,re_train,thre_train = metrics.precision_recall_curve(train_y,predict_train)
pr_test,re_test,thre_test = metrics.precision_recall_curve(test_y,predict_test)
auc_train = metrics.roc_auc_score(train_y,predict_train)
auc_test = metrics.roc_auc_score(test_y,predict_test)
prt_train = pd.DataFrame({'precision':pr_train,'recall':re_train})
prt_test = pd.DataFrame({'precision':pr_test,'recall':re_test})
print('precision>=0.97时对应的最大recall为：')
print(prt_test.loc[prt_test['precision']>=0.97,'recall'].max())
print('auc得分为：{}'.format(auc_test))
返回
0.0
0.8340018840954033
根据上述结果可知，xgboost的训练效果最好，当precision>=0.97时，recall最大能达到76.4%。
2.3.3 模型堆叠
后面也尝试了模型堆叠的方法，看是否能得到更好的效果，首先利用上述提到的各个模型，根据特征重要性选取了57个特征，然后利用KFold方法进行5折交叉验证，得到五种模型的验证集和测试集结果，分别作为第二层的训练数据集和测试数据集，并用逻辑回归模型来训练这五个特征，最终得到的结果是当precision>=0.97时，recall最大能达到78.3%，比原来的76.4%稍有提高。
- 选取重要特征
#筛选特征
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.tree import DecisionTreeClassifier
from xgboost.sklearn import XGBClassifier
def get_top_n_features(train_x, train_y):
# random forest
rf_est = RandomForestClassifier(n_estimators=300,max_depth=50)
rf_est.fit(train_x, train_y)
feature_imp_sorted_rf = pd.DataFrame({'feature': train_x.columns,
'importance': rf_est.feature_importances_}).sort_values('importance', ascending=False)
# AdaBoost
ada_est =AdaBoostClassifier(n_estimators=600,learning_rate=1)
ada_est.fit(train_x, train_y)
feature_imp_sorted_ada = pd.DataFrame({'feature': train_x.columns,
'importance': ada_est.feature_importances_}).sort_values('importance', ascending=False)
# GradientBoosting
gb_est = GradientBoostingClassifier(loss='deviance',random_state=2019,learning_rate=0.05, n_estimators=200,min_samples_split=4,
min_samples_leaf=1,max_depth=11,max_features='sqrt', subsample=0.8)
gb_est.fit(train_x, train_y)
feature_imp_sorted_gb = pd.DataFrame({'feature':train_x.columns,
'importance': gb_est.feature_importances_}).sort_values('importance', ascending=False)
# DecisionTree
dt_est = DecisionTreeClassifier(random_state=0,min_samples_split=70,max_depth=30)
dt_est.fit(train_x, train_y)
feature_imp_sorted_dt = pd.DataFrame({'feature':train_x.columns,
'importance': dt_est.feature_importances_}).sort_values('importance', ascending=False)
# xgbc
xg_est = XGBClassifier(learning_rate=0.05, objective= 'binary:logistic', nthread=1, scale_pos_weight=1, seed=27,
subsample=0.6, colsample_bytree=0.6, gamma=0, reg_alpha= 0, reg_lambda=1,max_depth=38,min_child_weight=1,n_estimators=210)
xg_est.fit(train_x, train_y)
feature_imp_sorted_xg = pd.DataFrame({'feature':train_x.columns,
'importance': xg_est.feature_importances_}).sort_values('importance', ascending=False)
return feature_imp_sorted_rf,feature_imp_sorted_ada,feature_imp_sorted_gb,feature_imp_sorted_dt,feature_imp_sorted_xg
feature_imp_sorted_rf,feature_imp_sorted_ada,feature_imp_sorted_gb,feature_imp_sorted_dt,feature_imp_sorted_xg = get_top_n_features(train_x, train_y)
top_n_features = 35
features_top_n_rf = feature_imp_sorted_rf.head(top_n_features)['feature']
features_top_n_ada = feature_imp_sorted_ada.head(top_n_features)['feature']
features_top_n_gb = feature_imp_sorted_gb.head(top_n_features)['feature']
features_top_n_dt = feature_imp_sorted_dt.head(top_n_features)['feature']
features_top_n_xg = feature_imp_sorted_xg.head(top_n_features)['feature']
features_top_n = pd.concat([features_top_n_rf, features_top_n_ada, features_top_n_gb, features_top_n_dt,features_top_n_xg],
ignore_index=True).drop_duplicates()
features_importance = pd.concat([feature_imp_sorted_rf, feature_imp_sorted_ada,
feature_imp_sorted_gb, feature_imp_sorted_dt,feature_imp_sorted_xg],ignore_index=True)
train_x_new = pd.DataFrame(train_x[features_top_n])
test_x_new = pd.DataFrame(test_x[features_top_n])
features_top_n
最终从79个特征中选取了57个。
- 第一层模型训练
#第一层
from sklearn.model_selection import KFold
ntrain = train_x_new.shape[0]
ntest = test_x_new.shape[0]
kf = KFold(n_splits = 5, random_state=0, shuffle=False)
def get_out_fold(clf, x_train, y_train, x_test):
oof_train = np.zeros((ntrain,))
oof_test = np.zeros((ntest,))
oof_test_skf = np.empty((5, ntest))
oof_train_prob = np.zeros((ntrain,))
oof_test_prob = np.zeros((ntest,))
oof_test_skf_prob = np.empty((5, ntest))
for i, (train_index, test_index) in enumerate(kf.split(x_train)):
x_tr = x_train[train_index]
y_tr = y_train[train_index]
x_te = x_train[test_index]
clf.fit(x_tr, y_tr)
oof_train[test_index] = clf.predict(x_te)
oof_test_skf[i, :] = clf.predict(x_test)
oof_train_prob[test_index] = clf.predict_proba(x_te)[:,1]
oof_test_skf_prob[i, :] = clf.predict_proba(x_test)[:,1]
print('现在是第{}层'.format(i))
print('训练集索引如下：')
print(train_index)
print('测试集索引如下：')
print(test_index)
oof_test[:] = oof_test_skf.mean(axis=0)
oof_test_prob[:] = oof_test_skf_prob.mean(axis=0)
return oof_train.reshape(-1, 1), oof_test.reshape(-1, 1),oof_train_prob.reshape(-1, 1), oof_test_prob.reshape(-1, 1)
rf = RandomForestClassifier(n_estimators=300,max_depth=50)
ada = AdaBoostClassifier(n_estimators=600,learning_rate=1)
gb = GradientBoostingClassifier(loss='deviance',random_state=2019,learning_rate=0.05, n_estimators=200,min_samples_split=4,
min_samples_leaf=1,max_depth=11,max_features='sqrt', subsample=0.8)
dt = DecisionTreeClassifier(random_state=0,min_samples_split=70,max_depth=30)
x_train = train_x_new.values
x_test = test_x_new.values
y_train =train_y.values
rf_oof_train, rf_oof_test,rf_oof_train_prob, rf_oof_test_prob = get_out_fold(rf, x_train, y_train, x_test) # Random Forest
ada_oof_train, ada_oof_test,ada_oof_train_prob, ada_oof_test_prob = get_out_fold(ada, x_train, y_train, x_test) # AdaBoost
gb_oof_train, gb_oof_test,gb_oof_train_prob, gb_oof_test_prob = get_out_fold(gb, x_train, y_train, x_test) # Gradient Boost
dt_oof_train, dt_oof_test,dt_oof_train_prob, dt_oof_test_prob = get_out_fold(dt, x_train, y_train, x_test) # Decision Tree
xgbc = XGBClassifier(learning_rate=0.05, objective= 'binary:logistic', nthread=1, scale_pos_weight=1, seed=27,
subsample=0.6, colsample_bytree=0.6, gamma=0, reg_alpha= 0, reg_lambda=1,max_depth=38,min_child_weight=1,n_estimators=210)
xgbc_oof_train, xgbc_oof_test,xgbc_oof_train_prob, xgbc_oof_test_prob = get_out_fold(xgbc, x_train, y_train, x_test) # XGBClassifier
print("Training is complete")
- 第二层模型训练
将第一层的输出结果作为训练集和测试集
#划分训练集和测试集
train_x2_prob = pd.DataFrame(np.concatenate((rf_oof_train_prob, ada_oof_train_prob, gb_oof_train_prob, dt_oof_train_prob), axis=1),columns=['rf_prob','ada_prob','gb_prob','dt_prob'])
test_x2_prob = pd.DataFrame(np.concatenate((rf_oof_test_prob, ada_oof_test_prob, gb_oof_test_prob, dt_oof_test_prob), axis=1),columns=['rf_prob','ada_prob','gb_prob','dt_prob'])
#逻辑回归模型训练
from sklearn.linear_model import LogisticRegression
#调参
# param_rf4 = {'penalty': ['l1','l2'],'C':[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1]}
# rf_est4 = LogisticRegression()
# rfsearch4 = GridSearchCV(estimator=rf_est4,param_grid=param_rf4,scoring='roc_auc',iid=False,cv=5)
# rfsearch4.fit(train_x2_prob,train_y)
# print('每个参数值的平均得分：{}'.format(rfsearch4.cv_results_['mean_test_score']))
# print('最佳参数值为：{}'.format(rfsearch4.best_params_))
# print('最佳参数值roc_auc得分为：{}'.format(rfsearch4.best_score_))
#调参结果：C=0.1,penalty='l2'
lr = LogisticRegression(C=0.1,penalty='l2')
lr.fit(train_x2_prob,train_y)
predict_train = lr.predict_proba(train_x2_prob)[:,1]
predict_test = lr.predict_proba(test_x2_prob)[:,1]
pr_train,re_train,thre_train = metrics.precision_recall_curve(train_y,predict_train)
pr_test,re_test,thre_test = metrics.precision_recall_curve(test_y,predict_test)
auc_train = metrics.roc_auc_score(train_y,predict_train)
auc_test = metrics.roc_auc_score(test_y,predict_test)
prt_train = pd.DataFrame({'precision':pr_train,'recall':re_train})
prt_test = pd.DataFrame({'precision':pr_test,'recall':re_test})
print('precision>=0.97时对应的最大recall为：')
print(prt_test.loc[prt_test['precision']>=0.97,'recall'].max())
print('auc得分为：{}'.format(auc_test))
返回
0.7832498511331395
0.9763271659779821
通过堆叠的方法，将recall值从76.4%提高到78.3%。
