bugfix

ai/data_access.py

@@ -31,7 +31,6 @@ class DataAccess(ABC):
         indexData.loc[indexData['rid_index_id'] == 77, 'rid_index_id'] = 106
         indexData.rename(columns={"rid_date": 'date'}, inplace=True)  # please use 'date'
         indexData["rid_index_id"] = indexData["rid_index_id"].map(self._indexDict)
-        indexData.fillna(method='ffill', inplace=True)
         return indexData
 
     def get_eco_datas(self):
@@ -63,6 +62,7 @@ class DataAccess(ABC):
             inplace=True)
         vixData.set_index('date', inplace=True)
         vixData.index = pd.to_datetime(vixData.index)
+        vixData.dropna(axis=1, inplace=True)
         return vixData
 
     def get_other_index(self, indexData):

ai/training_data_builder.py

@@ -147,6 +147,11 @@ class TrainingDataBuilder(ABC):
             DataAll[col].bfill(inplace=True)
             DataAll[col].ffill(inplace=True)
 
+        ###### clean NaN
+        DataAll.ffill(inplace=True)
+        DataAll.dropna(inplace=True)
+        DataAll.reset_index(inplace=True, drop=True)
+
         if (self._toForecast):
             # 处理CPI_YOY:美国城镇消费物价指数同比未经季 CPURNSA:美国消费者物价指数未经季调
             DataAllCopy = DataAll.copy()
@@ -157,13 +162,10 @@ class TrainingDataBuilder(ABC):
             DataAllCopy.drop(['futureR', 'yLabel'], axis=1, inplace=True)
             forecastDayIndex = DataAllCopy.index[DataAllCopy['date'] == forecastDay]
             forecastData = DataAllCopy.iloc[forecastDayIndex.to_list(), 1:]
+            forecastData.dropna(inplace=True, axis=1)
             X_forecast = forecastData.to_numpy()
             del DataAllCopy
 
-        ###### clean NaN
-        DataAll.dropna(inplace=True)
-        DataAll.reset_index(inplace=True, drop=True)
-
         ###### get X and y
         y = DataAll['yLabel'].to_numpy(copy=True)