特征工程优化

train/train_service.py

@@ -185,7 +185,7 @@ if __name__ == '__main__':
     print("读取数据...")
     timestmp1 = int(round(time.time()))
     df_train = loadData(data_path_train)
-    df_test = loadData(data_path_test)
+    # df_test = loadData(data_path_test)
     timestmp2 = int(round(time.time()))
     print("读取数据耗时s:{}".format(timestmp2 - timestmp1))
 
@@ -198,19 +198,20 @@ if __name__ == '__main__':
     print(datasColumns)
 
     df_train = df_train[datasColumns + ["label"]]
-    df_test = df_test[datasColumns + ["label"]]
+    # df_test = df_test[datasColumns + ["label"]]
 
     trainSize = df_train["label"].count()
-    testSize = df_test["label"].count()
-    print("trainSize:{},testSize{}".format(trainSize,testSize))
+    print("trainSize:{}".format(trainSize))
+    # testSize = df_test["label"].count()
+    # print("trainSize:{},testSize{}".format(trainSize,testSize))
 
     # 数据类型转换
     df_train = csvTypeConvert(datasColumns,df_train,data_vocab)
-    df_test = csvTypeConvert(datasColumns,df_test,data_vocab)
+    # df_test = csvTypeConvert(datasColumns,df_test,data_vocab)
 
     # 获取训练数据
     train_data = getDataSet(df_train,shuffleSize=trainSize,)
-    test_data = getDataSet(df_test,shuffleSize=testSize)
+    # test_data = getDataSet(df_test,shuffleSize=testSize)
 
 
     print("train start...")
@@ -219,7 +220,7 @@ if __name__ == '__main__':
     timestmp4 = int(round(time.time()))
     print("train end...耗时h:{}".format((timestmp4 - timestmp3)/60/60))
 
-    evaluate(model,test_data)
+    # evaluate(model,test_data)
 
 
     # predict(model_file,test_data)