电话邦跑

models/xgboost.py

@@ -77,6 +77,8 @@ def modelfit(clf, dftrain, features, resp,useTrainCV = True, kfold=10, eval_metr
     :param eval_metric 同 目标函数 objective 有关，取值https://xgboost.readthedocs.io/en/latest/python/python_api.html#
     :return:
     '''
+    if dftrain[features].shape[0]==0:
+        raise(' NO train data !!!! ')
     if useTrainCV:
         # kflod = StratifiedKFold(n_splits=kfold, shuffle=True, random_state=7)
         xgb_param = clf.get_xgb_params()

mvp/allocator.py

@@ -49,8 +49,14 @@ if __name__ == '__main__':
     # ]
     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,dhb.features,label,'','tmp.doc')
+    xgbreport.report(dftrain,dftest,features,label,'','tmp.doc',kfold=2)

mvp/xgbreport.py

@@ -7,7 +7,7 @@ from models import xgboost
 from matplotlib import pyplot as plt
 from data.graph import drawplot
 
-def report(dftrain,dftest,features,label,path,filename):
+def report(dftrain,dftest,features,label,path,filename,kfold=10):
     '''
     dftrain,dftest 中必然有 字段 applied_at,applied_channel,applied_type
     :param dftrain:
@@ -22,34 +22,34 @@ def report(dftrain,dftest,features,label,path,filename):
     document.add_heading('xgboost 算法运行报告')
     clf=xgboost.buildClf()
     document.add_paragraph('初始化参数运行{}'.format(clf.get_xgb_params()))
-    clf=xgboost.modelfit(clf,dftrain,features,label)
+    clf=xgboost.modelfit(clf,dftrain,features,label,kfold=kfold)
     document.add_paragraph('模型训练集{}'.format(xgboost.auc(clf,dftrain,features,label)))
     document.add_paragraph('模型测试集{}'.format(xgboost.auc(clf, dftest, features, label)))
 
     document.add_heading('调整参数')
     max_depth=[2,3]
     min_child_weight=range(1,4,1)
-    document, clf = tun_params(document, clf, dftrain, dftest, {'max_depth': max_depth,'min_child_weight':min_child_weight}, features, label)
+    document, clf = tun_params(document, clf, dftrain, dftest, {'max_depth': max_depth,'min_child_weight':min_child_weight}, features, label,kfold=kfold)
 
     # gamma
     gamma=[i/10 for i in range(0,5)]
-    document,clf=tun_params(document,clf,dftrain,dftest,{'gamma':gamma},features,label)
+    document,clf=tun_params(document,clf,dftrain,dftest,{'gamma':gamma},features,label,kfold=kfold)
 
     # subsample colsample_bytree
     subsample=[0.8,0.9,1]
     colsample_bytree=[0.8,0.9,1]
     document, clf = tun_params(document, clf, dftrain, dftest,
-                               {'subsample': subsample, 'colsample_bytree': colsample_bytree}, features, label)
+                               {'subsample': subsample, 'colsample_bytree': colsample_bytree}, features, label,kfold=kfold)
 
     # reg_alpha
     reg_alpha=[0.001,0.01,0.1,1,10]
     document, clf = tun_params(document, clf, dftrain, dftest,
-                               {'reg_alpha': reg_alpha}, features, label)
+                               {'reg_alpha': reg_alpha}, features, label,kfold=kfold)
 
     # reg_lambda
     reg_lambda = [0.001, 0.01, 0.1, 1, 10]
     document, clf = tun_params(document, clf, dftrain, dftest,
-                               {'reg_lambda': reg_lambda}, features, label)
+                               {'reg_lambda': reg_lambda}, features, label,kfold=kfold)
 
     #==生成模型最后的报告，各个特征的单变量图，PDP，liftchart
     dftrain=xgboost.predict(clf,dftrain,features)
@@ -103,10 +103,10 @@ def report(dftrain,dftest,features,label,path,filename):
 
 
 
-def tun_params(document,clf,dftrain,dftest,params,features,label):
+def tun_params(document,clf,dftrain,dftest,params,features,label,kfold=10):
     for i in dict(params).keys():
         document.add_paragraph('调参{},取值{}'.format(i,params[i]))
-    grid_search = xgboost.automodelfit(clf, params,dftrain, features, label)
+    grid_search = xgboost.automodelfit(clf, params,dftrain, features, label,kfold=kfold)
     clf = grid_search.best_estimator_
     document.add_paragraph('模型训练参数{}'.format(clf.get_xgb_params()))
     #==