To avoid data leak, test set should start from numForecastDays later

ai/training_data_builder.py

@@ -199,6 +199,6 @@ class TrainingDataBuilder(ABC):
             X_train, X_test, y_train, y_test = train_test_split(scaledX, y, test_size=0.04, shuffle=False)
             date_index = DataAll['date'][-len(X_test):-self._numForecastDays].to_numpy()
             # To avoid data leak, test set should start from numForecastDays later
-            X_test = X_test[:-self._numForecastDays]
-            y_test = y_test[:-self._numForecastDays]
+            X_test = X_test[self._numForecastDays:]
+            y_test = y_test[self._numForecastDays:]
         return X_train, X_test, y_train, y_test, scaledX_forecast, forecastDay, date_index