update

ai/EstimateMarketTrendV20.py

@@ -17,14 +17,13 @@ from api import DataSync
 max_date = None
 
 toForecast = False  # False means test, True means forecast
-syncData = False  # 开启会同步数据库指数及基金数据
+syncData = True  # 开启会同步数据库指数及基金数据
 uploadData = False  # 开启会上传预测结果
 doReport = True  # 开启会生成Excel报告
 
 # 待预测指数
 # PREDICT_LIST = [67, 121, 122, 123]
-PREDICT_LIST = [67, 121, 122, 123, 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163,
-                164, 165, 166, 167, 168, 169, 170, 171, 174, 175, 177, 178]
+PREDICT_LIST = [67]
 eco = [65, 66, 74, 134]
 index = [67, 68, 69, 70, 71, 72, 73, 75, 76, 77, 105, 106, 116, 117, 138, 139, 142, 143, 140, 141, 144, 145, 146]
 fund = [121, 122, 123, 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165,

ai/training_data_builder.py

@@ -151,15 +151,9 @@ class TrainingDataBuilder(ABC):
         for col in ['NAPMPMI']:
             DataAll[col].bfill(inplace=True)
             DataAll[col].ffill(inplace=True)
-
         #  根据预测的数据删除节假日
         DataAll.dropna(subset=[DataAll.columns[1]], inplace=True)
-
-        for col in DataAll.columns:
-            if col not in ['CPI_YOY', 'CPURNSA', 'CPI_MOM', 'CPI_MOM_Diff', 'futureR', 'yLabel']:
-                DataAll[col].ffill(inplace=True)
-
-        if (self._toForecast):
+        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()
             for col in ['CPI_YOY', 'CPURNSA']:
@@ -202,7 +196,7 @@ class TrainingDataBuilder(ABC):
             date_index = []
         else:
             # Step 2: Split data into train set and test set
-            X_train, X_test, y_train, y_test = train_test_split(scaledX, y, test_size=0.02, shuffle=False)
+            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]