特征工程优化

train/train_service.py

@@ -223,7 +223,6 @@ if __name__ == '__main__':
 
     # 获取训练数据
     train_data = getDataSet(df_train,shuffleSize=trainSize,)
-    test_data = getDataSet(df_test,shuffleSize=testSize)
 
 
     print("train start...")
@@ -232,6 +231,8 @@ if __name__ == '__main__':
     timestmp4 = int(round(time.time()))
     print("train end...耗时h:{}".format((timestmp4 - timestmp3)/60/60))
 
+    if(testSize > 0):
+        test_data = getDataSet(df_test,shuffleSize=testSize)
         evaluate(model,test_data)