update 之前的模型

data/datasource/dbquery.py

@@ -9,7 +9,7 @@ def mysql_query(sql,engine_sql):
     '''
     res=[]
     #== palo 每次查询不超过10000
-    tmp=pd.read_sql(sql,engine_sql,chunksize=5000)
+    tmp=pd.read_sql(sql,engine_sql,chunksize=5001)
     for tt in tmp:
         res.append(tt)
     return pd.concat(res)
\ No newline at end of file

data/samples/dhb.py

@@ -37,7 +37,10 @@ def query_sample(start_date,end_date,is_loan=True):
         ''' % (','.join(features),start_date,end_date)
     df=dbquery.mysql_query(sql,engine_risk_analysis)
     yewu=query_byloanid(df.loan_id.tolist())
+    df.loan_id=df.loan_id.astype(int)
+    yewu.loan_id=yewu.loan_id.astype(int)
     df=pd.merge(df,yewu,on='loan_id',how='inner')
+    df.applied_at=pd.to_datetime(df.applied_at)
     value_map = {
         "近3天": 1,
         "近4-5天": 2,

mvp/allocator.py

@@ -3,7 +3,8 @@ import numpy as np
 import datetime
 from mvp import xgbreport
 from data.analyis import datacal
-from mvp import dhb
+# from mvp import dhb
+from data.samples import dhb,sample
 
 if __name__ == '__main__':
     # features=[
@@ -47,16 +48,36 @@ if __name__ == '__main__':
     #     'third_data_source#xy_pan_newqueryAorgAcount',
     #     'third_data_source#xy_pan_newqueryAsumAcount'
     # ]
-    dhb = dhb.dhb(start_time_period='2019-01-19 11:00:00',end_time_period='2019-01-20 12:00:00')
-    df=dhb.dhb_features_extract()
-    print(df.columns.tolist())
-    print(df.target.unique())
-    label='target'
-    features=dhb.get_feature()
-    df[features]=df[features].astype(float)
-    df['target']=df['target'].astype(int)
-    print('----feature---',len(features))
+    # dhb = dhb.dhb(start_time_period='2019-01-19 11:00:00',end_time_period='2019-01-20 12:00:00')
+    # df=dhb.dhb_features_extract()
+    # print(df.columns.tolist())
+    # print(df.target.unique())
+    # label='target'
+    # features=dhb.get_feature()
+    # df[features]=df[features].astype(float)
+    # df['target']=df['target'].astype(int)
+    # print('----feature---',len(features))
     # df=pd.read_csv('test.csv')
-    dftrain,dftest=datacal.split_train_val(df,trainsplit='timeSeries',trainsplitRatio=0.8,sort_col='applied_at')
-
-    xgbreport.report(dftrain,dftest,features,label,'','tmp.doc',kfold=2)
+    #== 模型名称
+    model_name='dhb'
+    #== 目标是15天
+    passdue_day=15
+    df_log=sample.get_last_record(model_name)
+    if df_log.shape[0]==1:
+        start_date,end_date=sample.cal_sample_date(df_log.max_date[0],passdue_day)
+    else:
+        start_date, end_date = sample.cal_sample_date(passdue_day=passdue_day)
+    start_date='2019-01-01'
+    end_date='2019-01-10'
+    print(start_date,end_date)
+    df_sample=dhb.query_sample(start_date,end_date)
+    df_sample['applied_at'] = pd.to_datetime(df_sample['applied_at'])
+    df_sample['label']=1
+    df_sample.loc[df_sample.passdue_day >= passdue_day,'label']=0
+    dftrain,dftest=datacal.split_train_val(df_sample,trainsplit='timeSeries',trainsplitRatio=0.8,sort_col='applied_at')
+    # 记录样本信息
+    # sample.save_model_record(model_name,min_date=df_sample.applied_at.min(),max_date=df_sample.applied_at.max(),sample_cnt=df_sample.shape[0],
+    #                          train_min_date=dftrain.applied_at.min(),train_max_date=dftrain.applied_at.max(),train_cnt=dftrain.shape[0],
+    #                          test_min_date=dftest.applied_at.min(),test_max_date=dftest.applied_at.max(),test_cnt=dftest.shape[0])
+    #== xgboost gbtree
+    xgbreport.report(dftrain,dftest,dhb.get_feature(),'label','','xgboost_%s.doc' % datetime.datetime.now().date().strftime('%y%m%d'),kfold=2)