排除节假日影响

ai/training_data_builder.py

@@ -79,6 +79,7 @@ class TrainingDataBuilder(ABC):
             for label, (lower, upper) in LABEL_RANGE.items():
                 if float(lower) <= ret < float(upper):
                     return label
+
         """
         @param pid: 需要预测的指数或基金id
         @return:
@@ -124,7 +125,7 @@ class TrainingDataBuilder(ABC):
         del (predictData['close'])
         return predictData
 
-    def build_train_test(self, pid, indexData, vixData, indexOtherData, cpiData, FDTRData, NAPMPMIData,TTM):
+    def build_train_test(self, pid, indexData, vixData, indexOtherData, cpiData, FDTRData, NAPMPMIData, TTM):
         ###### Merge Data to one table
         predictData = self.build_predict_data(indexData, pid)
         forecastDay = None
@@ -140,9 +141,13 @@ class TrainingDataBuilder(ABC):
         DataAll.set_index('date', inplace=True)
         DataAll.sort_index(inplace=True)
         DataAll.reset_index(inplace=True)
-        DataAll.ffill(inplace=True)
+        ###### fill eco data
+        for col in ['CPI_YOY', 'CPURNSA', 'CPI_MOM', 'CPI_MOM_Diff', 'FDTR', 'NAPMPMI', 'JIFU_SPX_OPEPS_CURRQ_TTM']:
+            DataAll[col].ffill(inplace=True)
         DataAll['EPS_TTM_YOY'] = (DataAll['JIFU_SPX_OPEPS_CURRQ_TTM'] / DataAll['JIFU_SPX_OPEPS_CURRQ_TTM'].shift(
             252) - 1.0)
+        DataAll.dropna(subset=[DataAll.columns[1]], inplace=True)
+        DataAll.ffill(inplace=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()