加入MySQL 连接

model/xgboost.py

@@ -32,14 +32,6 @@ def split_train_val(df, trainsplit = 'random', trainsplitRatio = 0.8, sort_col=N
         val = None
     return train,val
 
-# log 损失函数
-def logregobj(preds, dtrain):
-    labels = dtrain.get_label()
-    preds = 1.0 / (1.0 + np.exp(-preds))
-    grad = preds - labels
-    hess = preds * (1.0 - preds)
-    return grad, hess
-
 
 def buildClf(max_depth=2,learning_rate=0.1, n_estimators=5000, gamma=0,
                   min_child_weight=1, max_delta_step=0, subsample=0.8, colsample_bytree=0.8, reg_alpha=0, reg_lambda=1,
@@ -105,12 +97,12 @@ def automodelfit(clf,param_grid,dftrain,features,resp, kfold=10,scoring='roc_auc
     return grid_search
 
 
-def modelfit(clf, dftrain, features, resp, dfval=None,useTrainCV = True, cv_folds=10, eval_metric='auc',early_stopping_rounds=20):
+def modelfit(clf, dftrain, features, resp,useTrainCV = True, cv_folds=10, eval_metric='auc',early_stopping_rounds=20):
     '''
     模型训练
+    :type useTrainCV: object
     :param clf:XGBClassifier
     :param dftrain:训练集
-    :param dfval 验证集用于模型训练，early_stopping_rounds
     :param features: 特征
     :param resp:label
     :param useTrainCV:if True  call cv function,目的是调节参数 n_estimators
@@ -126,13 +118,7 @@ def modelfit(clf, dftrain, features, resp, dfval=None,useTrainCV = True, cv_fold
             metrics=eval_metric, early_stopping_rounds=early_stopping_rounds,verbose_eval=True)
         clf.set_params(n_estimators=cvresult.shape[0])
 
-    # Fit the algorithm on the data and save the model
-    if not dfval==None:
-        #== 如果有验证集的话，则无需进行cv运算 基于验证集auc early_stopping_rounds
-        clf.fit(dftrain[features], dftrain[resp],eval_set=[(dftrain[features], dftrain[resp]), (dfval[features], dfval[resp])],
-                eval_metric=eval_metric,early_stopping_rounds=early_stopping_rounds)
-    else:
-        clf.fit(dftrain[features], dftrain[resp],eval_metric=eval_metric)
+    clf.fit(dftrain[features], dftrain[resp],eval_metric=eval_metric)
     return clf