[一周算法进阶]--任务三-模型融合

Task3.模型融合

用你目前评分最高的模型作为基准模型，和其他模型进行stacking融合，得到最终模型及评分果。

1.导入相关包&读取数据

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.preprocessing import LabelBinarizer,OneHotEncoder,Imputer

%matplotlib inline
import warnings
warnings.filterwarnings('ignore')

data_original=pd.read_csv('data.csv',skipinitialspace=True)
data=data_original.copy()
data.head(5)

	Unnamed: 0	custid	trade_no	bank_card_no	low_volume_percent	middle_volume_percent	take_amount_in_later_12_month_highest	trans_amount_increase_rate_lately	trans_activity_month	trans_activity_day	...	loans_max_limit	loans_avg_limit	consfin_credit_limit	consfin_credibility	consfin_org_count_current	consfin_product_count	consfin_max_limit	consfin_avg_limit	latest_query_day	loans_latest_day
0	5	2791858	20180507115231274000000023057383	卡号1	0.01	0.99	0	0.90	0.55	0.313	...	2900.0	1688.0	1200.0	75.0	1.0	2.0	1200.0	1200.0	12.0	18.0
1	10	534047	20180507121002192000000023073000	卡号1	0.02	0.94	2000	1.28	1.00	0.458	...	3500.0	1758.0	15100.0	80.0	5.0	6.0	22800.0	9360.0	4.0	2.0
2	12	2849787	20180507125159718000000023114911	卡号1	0.04	0.96	0	1.00	1.00	0.114	...	1600.0	1250.0	4200.0	87.0	1.0	1.0	4200.0	4200.0	2.0	6.0
3	13	1809708	20180507121358683000000388283484	卡号1	0.00	0.96	2000	0.13	0.57	0.777	...	3200.0	1541.0	16300.0	80.0	5.0	5.0	30000.0	12180.0	2.0	4.0
4	14	2499829	20180507115448545000000388205844	卡号1	0.01	0.99	0	0.46	1.00	0.175	...	2300.0	1630.0	8300.0	79.0	2.0	2.0	8400.0	8250.0	22.0	120.0

5 rows × 90 columns

pd.set_option('display.max_columns', None)
pd.set_option('display.max_rows', None)

2. 删除无关特征

data.drop(['Unnamed: 0', 'custid', 'trade_no', 'bank_card_no', 'source','id_name'], axis=1, inplace=True)
object_cols = [col for col in data.columns if data[col].dtypes == 'O']
data_obj=data[object_cols]
data_num=data.drop(object_cols,axis=1)

3.缺失值填充和热编码

#缺失值填充
imputer=Imputer(strategy='mean')
mean_num=imputer.fit_transform(data_num)
data_num=pd.DataFrame(mean_num,columns=data_num.columns)
data_obj.ffill(inplace=True)
#One-HotEncoder
encoder = LabelBinarizer()
reg_preference_1hot = encoder.fit_transform(data_obj[['reg_preference_for_trad']])
data_obj.drop(['reg_preference_for_trad'], axis=1, inplace=True)
reg_preference_df = pd.DataFrame(reg_preference_1hot, columns=encoder.classes_)
data_obj = pd.concat([data_obj, reg_preference_df], axis=1)

#['latest_query_time']  ['loans_latest_time']
data_obj['latest_query_time'] = pd.to_datetime(data_obj['latest_query_time'])
data_obj['latest_query_time_month'] = data_obj['latest_query_time'].dt.month
data_obj['latest_query_time_weekday'] = data_obj['latest_query_time'].dt.weekday

data_obj['loans_latest_time'] = pd.to_datetime(data_obj['loans_latest_time'])
data_obj['loans_latest_time_month'] = data_obj['loans_latest_time'].dt.month
data_obj['loans_latest_time_weekday'] = data_obj['loans_latest_time'].dt.weekday

data_obj = data_obj.drop(['latest_query_time', 'loans_latest_time'], axis=1)

data=pd.concat([data_num,data_obj],axis=1)
data.shape

(4754, 90)

#数据集分割
from sklearn.model_selection import train_test_split
y=data['status']
X=data.drop(['status'],axis=1)
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=2018)

5.IV值与RF特征选择

X_train=X_train[['trans_amount_increase_rate_lately', 'trans_activity_day',
       'first_transaction_time', 'historical_trans_amount',
       'historical_trans_day', 'rank_trad_1_month', 'trans_amount_3_month',
       'top_trans_count_last_1_month', 'trans_top_time_last_1_month',
       'consume_top_time_last_1_month',
       'trans_fail_top_count_enum_last_1_month',
       'trans_fail_top_count_enum_last_6_month',
       'trans_fail_top_count_enum_last_12_month',
       'max_cumulative_consume_later_1_month', 'first_transaction_day',
       'trans_day_last_12_month', 'apply_score', 'loans_score', 'loans_count',
       'loans_settle_count', 'loans_overdue_count', 'latest_three_month_loan',
       'history_suc_fee', 'history_fail_fee', 'latest_one_month_suc',
       'latest_one_month_fail', 'consfin_credit_limit', 'consfin_avg_limit',
       'latest_query_day', 'loans_latest_day']]
X_test=X_test[['trans_amount_increase_rate_lately', 'trans_activity_day',
       'first_transaction_time', 'historical_trans_amount',
       'historical_trans_day', 'rank_trad_1_month', 'trans_amount_3_month',
       'top_trans_count_last_1_month', 'trans_top_time_last_1_month',
       'consume_top_time_last_1_month',
       'trans_fail_top_count_enum_last_1_month',
       'trans_fail_top_count_enum_last_6_month',
       'trans_fail_top_count_enum_last_12_month',
       'max_cumulative_consume_later_1_month', 'first_transaction_day',
       'trans_day_last_12_month', 'apply_score', 'loans_score', 'loans_count',
       'loans_settle_count', 'loans_overdue_count', 'latest_three_month_loan',
       'history_suc_fee', 'history_fail_fee', 'latest_one_month_suc',
       'latest_one_month_fail', 'consfin_credit_limit', 'consfin_avg_limit',
       'latest_query_day', 'loans_latest_day']]

X_train.head(5)

	trans_amount_increase_rate_lately	trans_activity_day	first_transaction_time	historical_trans_amount	historical_trans_day	rank_trad_1_month	trans_amount_3_month	top_trans_count_last_1_month	trans_top_time_last_1_month	consume_top_time_last_1_month	trans_fail_top_count_enum_last_1_month	trans_fail_top_count_enum_last_6_month	trans_fail_top_count_enum_last_12_month	max_cumulative_consume_later_1_month	first_transaction_day	trans_day_last_12_month	apply_score	loans_score	loans_count	loans_settle_count	loans_overdue_count	latest_three_month_loan	history_suc_fee	history_fail_fee	latest_one_month_suc	latest_one_month_fail	consfin_credit_limit	consfin_avg_limit	latest_query_day	loans_latest_day
110	0.96	0.405	20170217.0	181770.0	150.0	0.85	15610.0	1.00	0.0	0.0	6.0	9.0	9.0	220.0	458.0	99.0	535.0	498.0	92.0	77.0	7.0	3.0	85.0	52.0	0.0	3.0	10600.0	8228.0	0.0	9.0
3394	0.87	0.205	20170331.0	63350.0	74.0	0.65	12200.0	0.40	14.0	14.0	1.0	4.0	9.0	470.0	416.0	82.0	540.0	510.0	19.0	16.0	3.0	1.0	22.0	11.0	1.0	0.0	16300.0	7160.0	30.0	27.0
3052	1.98	0.205	20141110.0	97190.0	93.0	0.45	33280.0	0.30	11.0	11.0	0.0	4.0	21.0	1950.0	1288.0	82.0	516.0	482.0	16.0	16.0	2.0	0.0	20.0	5.0	0.0	0.0	10400.0	10320.0	3.0	137.0
490	1.49	0.555	20130817.0	373700.0	356.0	0.30	61940.0	0.10	15.0	15.0	8.0	8.0	8.0	3090.0	1738.0	82.0	491.0	448.0	40.0	22.0	7.0	3.0	40.0	78.0	0.0	10.0	6600.0	6418.0	20.0	51.0
1	1.28	0.458	20160402.0	302910.0	224.0	0.35	10590.0	0.05	13.0	13.0	0.0	3.0	3.0	2100.0	779.0	84.0	653.0	635.0	37.0	36.0	0.0	2.0	49.0	4.0	2.0	1.0	15100.0	9360.0	4.0	2.0

6.stacking模型融合

#数据归一化评价
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

from sklearn.linear_model import LogisticRegression
from sklearn import svm
from sklearn.tree import DecisionTreeClassifier
from xgboost.sklearn import XGBClassifier
from lightgbm.sklearn import LGBMClassifier
from sklearn.ensemble import RandomForestClassifier,GradientBoostingClassifier
from sklearn.metrics import accuracy_score,f1_score,precision_score,recall_score,roc_auc_score,roc_curve
from mlxtend.classifier import StackingClassifier

lr_model = LogisticRegression(C = 0.1, penalty = 'l1')
svm_model = svm.SVC(C = 0.01, kernel = 'linear', probability=True)
dt_model = DecisionTreeClassifier(max_depth=5,min_samples_split=50,min_samples_leaf=60, max_features=9, random_state =2333)
xgb_model = XGBClassifier(learning_rate =0.1, n_estimators=80, max_depth=3, min_child_weight=5, 
                    gamma=0.2, subsample=0.8, colsample_bytree=0.8, reg_alpha=1e-5, 
                    objective= 'binary:logistic', nthread=4,scale_pos_weight=1, seed=27)
lgbm_model = LGBMClassifier(learning_rate =0.1, n_estimators=100, max_depth=3, min_child_weight=11, 
                    gamma=0.1, subsample=0.5, colsample_bytree=0.9, reg_alpha=1e-5, 
                    nthread=4,scale_pos_weight=1, seed=27)
gbdt_model=GradientBoostingClassifier(n_estimators=100)
rf_model = RandomForestClassifier(class_weight='balanced', n_estimators=100)

sclf_model = StackingClassifier(classifiers=[lgb_model, gbdt_model, rf_model], use_probas=True,
                          average_probas=False,
                          meta_classifier=lr_model)

models={'LR':lr_model, 'SVM':svm_model, 'DT':dt_model, 'GBDT':gbdt_model, 
        'XGBoost':xgb_model, 'LGBM':lgbm_model,'Stack':sclf_model}

---------------------------------------------------------------------------

ModuleNotFoundError                       Traceback (most recent call last)

<ipython-input-13-bac9ce48d541> in <module>()
     12 from sklearn.ensemble import RandomForestClassifier,GradientBoostingClassifier
     13 from sklearn.metrics import accuracy_score,f1_score,precision_score,recall_score,roc_auc_score,roc_curve
---> 14 from mlxtend.classifier import StackingClassifier
     15 
     16 lr_model = LogisticRegression(C = 0.1, penalty = 'l1')


ModuleNotFoundError: No module named 'mlxtend'

df_result=pd.DataFrame(columns=('model','accuracy','precision','recall','f1_score','auc'))
row=0
#定义评价函数
def evaluate(y_pre,y):
    acc=accuracy_score(y,y_pre)
    p=precision_score(y,y_pre)
    r=recall_score(y,y_pre)
    f1=f1_score(y,y_pre)
    return acc,p,r,f1

for name,model in models.items():
    print(name,'start training...')
    model.fit(X_train,y_train)
    y_pred=model.predict(X_test)
    y_proba=model.predict_proba(X_test)
    acc,p,r,f1=evaluate(y_pred,y_test)
    auc=roc_auc_score(y_test,y_proba[:,1])
    df_result.loc[row]=[name,acc,p,r,f1,auc]
    row+=1
print(df_result)

ubuntu16不知怎么了，使用pip安装mlxten始终报错，先把程序写上，明天继续安装。