# 数据替换和截取以后用105 和106，（都从2022.1.3开始）然后2022年以前的部分：105前边接76的数据 106前边接77的数据

ai/EstimateMarketTrendV20.py

+import json
 from typing import List
 
-from py_jftech import autowired
+from py_jftech import autowired, parse_date, prev_workday, format_date
 
-from ai.dao.robo_datas import get_base_info
+from ai.dao.robo_datas import get_base_info, get_index_list, get_fund_list
 from ai.data_access import DataAccess
 from ai.model_trainer import ModelTrainer
-from ai.noticer import upload_predict
 from ai.training_data_builder import TrainingDataBuilder
 from api import DataSync
 
+
 # 截止日期
 # max_date = None
-max_date = '2024-01-05'
+# max_date = '2023-10-06'
+# max_date = '2023-10-13'
+# max_date = '2023-10-20'
+# max_date = '2023-10-27'
+# max_date = '2023-11-03'
+# max_date = '2023-11-10'
+# max_date = '2023-11-17'
+# max_date = '2023-11-24'
+# max_date = '2023-12-01'
+# max_date = '2023-12-08'
+max_date = '2023-12-15'
 
 # 待预测指数
-PREDICT_LIST = [67, 121, 122, 123]
-# PREDICT_LIST = [67, 121, 122, 123, 155, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 168, 169, 170, 171, 174, 175]
+# PREDICT_LIST = [67, 121, 122, 123]
+PREDICT_LIST = [67, 121, 122, 123, 155, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 168, 169, 170, 171, 174, 175]
 eco = [65, 66, 74, 134]
-index = [67, 68, 69, 70, 71, 72, 73, 75, 116, 117, 138, 139, 142, 143, 140, 141, 144, 145, 146]
+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, 155, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 168, 169, 170, 171, 174, 175]
 
 
@@ -36,13 +47,43 @@ def predictionFromMoel(the_model, scaledX_forecast, predict_item, indexDict: dic
     content = f"""\n On day {forecastDay.strftime("%m/%d/%Y")}, the model predicts {predict_item} to be {predictionStr} in {str(numForecastDays)} business days. \n"""
     print(content)
     # 上传预测结果
-    key = [k for k, v in indexDict.items() if v == predict_item]
-    index_info = get_base_info(key)[0]
-    upload_predict(index_info['ticker'], forecastDay, predictionStr)
+    # key = [k for k, v in indexDict.items() if v == predict_item]
+    # index_info = get_base_info(key)[0]
+    # upload_predict(index_info['ticker'], forecastDay, predictionStr)
     # send(content)
     return prediction
 
 
+def judgement(id, type, predict):
+    from datetime import datetime
+    predict_term = 21
+    start = parse_date(max_date) if max_date else prev_workday(datetime.today())
+    navs = []
+    if type == 'INDEX':
+        navs = get_index_list(index_ids=id, min_date=start, limit=predict_term)
+        navs = [nav['rid_close'] for nav in navs]
+    elif type == 'FUND':
+        navs = get_fund_list(fund_ids=id, min_date=start, limit=predict_term)
+        navs = [nav['rfn_nav_cal'] for nav in navs]
+    if len(navs) == predict_term:
+        upper = True if navs[-1] >= navs[0] else False
+        result = {}
+        for k, v, in predict.items():
+            pred = True if v[0] > 0 else False
+            if upper == pred:
+                result[k] = True
+            else:
+                result[k] = False
+        j = {
+            'id': id,
+            'date': format_date(start),
+            'result': result
+        }
+        with open('predict.txt', 'a+') as file:
+            file.write(json.dumps(j))
+            file.write('\n')
+
+
 ########################################
 if __name__ == '__main__':
     sync()
@@ -55,6 +96,7 @@ if __name__ == '__main__':
     theThreshold = 0.0
     ids = set(PREDICT_LIST) | set(eco) | set(index) | set(fund)
     infos = get_base_info(ids)
+    infos_type = {info['id']: info['type'] for info in infos}
     indexDict = {info['id']: info['ticker'].replace(' Index', '').replace(' Equity', '').replace(' ', '_') for info in
                  infos}
     ###################
@@ -85,9 +127,11 @@ if __name__ == '__main__':
         gbt_model = trainer.train_GBT(X_train, y_train, X_test, y_test)
         svc_model = trainer.train_SVC(X_train, y_train, X_test, y_test)
         ensemble_model = trainer.ensemble_model(rf_model, gbt_model, svc_model, X_train, y_train, X_test, y_test)
-        print(f'forest predict{rf_model.predict(scaledX_forecast)}'.center(60, '+'))
-        print(f'gbt predict{gbt_model.predict(scaledX_forecast)}'.center(60, '+'))
-        print(f'svc predict{svc_model.predict(scaledX_forecast)}'.center(60, '+'))
-        print(f'ensemble predict{ensemble_model.predict(scaledX_forecast)}'.center(60, '+'))
+        model_predict = {'forest': rf_model.predict(scaledX_forecast),
+                         'gbt': gbt_model.predict(scaledX_forecast),
+                         'svc': svc_model.predict(scaledX_forecast),
+                         'ensemble': ensemble_model.predict(scaledX_forecast)}
+        print(f'预测结果：{model_predict}'.center(60, '+'))
+        judgement(pid, infos_type[pid], model_predict)
         if toForecast:
             predictionFromMoel(ensemble_model, scaledX_forecast, indexDict[pid], indexDict)

ai/dao/robo_datas.py

@@ -2,7 +2,8 @@ from py_jftech import read, to_tuple, where
 
 
 @read
-def get_index_list(index_ids=None, min_date=None, max_date=None):
+def get_index_list(index_ids=None, min_date=None, max_date=None, limit=None):
+    limit_sql = f'limit {limit}' if limit else ''
     sqls = []
     if min_date:
         sqls.append(f"rid_date >= '{min_date}'")
@@ -10,7 +11,7 @@ def get_index_list(index_ids=None, min_date=None, max_date=None):
         sqls.append(f"rid_date <= '{max_date}'")
     return f'''
     select * from robo_index_datas 
-    {where(*sqls, rid_index_id=to_tuple(index_ids))} order by rid_index_id, rid_date
+    {where(*sqls, rid_index_id=to_tuple(index_ids))} order by rid_index_id, rid_date {limit_sql}
     '''
 
 
@@ -27,7 +28,8 @@ def get_eco_list(eco_ids=None, min_date=None, max_date=None):
     '''
 
 @read
-def get_fund_list(fund_ids=None, min_date=None, max_date=None):
+def get_fund_list(fund_ids=None, min_date=None, max_date=None, limit=None):
+    limit_sql = f'limit {limit}' if limit else ''
     sqls = []
     if min_date:
         sqls.append(f"rfn_date >= '{min_date}'")
@@ -35,7 +37,7 @@ def get_fund_list(fund_ids=None, min_date=None, max_date=None):
         sqls.append(f"rfn_date <= '{max_date}'")
     return f'''
     select * from robo_fund_navs 
-    {where(*sqls, rfn_fund_id=to_tuple(fund_ids))} order by rfn_fund_id, rfn_date
+    {where(*sqls, rfn_fund_id=to_tuple(fund_ids))} order by rfn_fund_id, rfn_date {limit_sql}
     '''
 
 @read

ai/data_access.py

@@ -21,6 +21,14 @@ class DataAccess(ABC):
         indexData = indexData[
             ["rid_index_id", "rid_date", "rid_high", "rid_open", "rid_low", "rid_close", "rid_pe", "rid_pb",
              "rid_volume", "rid_frdpe", "rid_frdpes", "rid_pc"]]
+        # 数据替换和截取以后用105 和106，（都从2022.1.3开始）然后2022年以前的部分：105前边接76的数据 106前边接77的数据
+        condition1 = ((indexData['rid_index_id'] == 76) & (indexData['rid_date'] > '2022-01-03'))
+        condition2 = ((indexData['rid_index_id'] == 77) & (indexData['rid_date'] > '2022-01-03'))
+        condition3 = ((indexData['rid_index_id'] == 105) & (indexData['rid_date'] <= '2022-01-03'))
+        condition4 = ((indexData['rid_index_id'] == 106) & (indexData['rid_date'] <= '2022-01-03'))
+        indexData.drop(indexData[condition1 | condition2 | condition3 | condition4].index, inplace=True)
+        indexData.loc[indexData['rid_index_id'] == 76, 'rid_index_id'] = 105
+        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)
@@ -58,7 +66,7 @@ class DataAccess(ABC):
         return vixData
 
     def get_other_index(self, indexData):
-        other_index = ["USGG10YR", "USGG2YR", "CCMP", "US0001M", "US0012M", "COI_TOTL", "LEI_TOTL", "MID",
+        other_index = ["USGG10YR", "USGG2YR", "CCMP", "TSFR1M", "TSFR12M", "COI_TOTL", "LEI_TOTL", "MID",
                        "OE4EKLAC", "OEA5KLAC", "OECNKLAC", "OEJPKLAC", "OEOTGTAC", "OEUSKLAC", "USRINDEX", "SPX"]
         cols = ['date', 'rid_close', 'rid_pe', 'rid_pb', 'rid_volume', 'rid_frdpe', 'rid_frdpes', 'rid_pc']
         indexOtherData = pd.DataFrame()

ai/predict.txt

+{"id": 67, "date": "2023-10-06", "result": {"forest": false, "gbt": true, "svc": true, "ensemble": true}}
+{"id": 121, "date": "2023-10-06", "result": {"forest": true, "gbt": true, "svc": false, "ensemble": true}}
+{"id": 122, "date": "2023-10-06", "result": {"forest": true, "gbt": true, "svc": false, "ensemble": true}}
+{"id": 123, "date": "2023-10-06", "result": {"forest": false, "gbt": false, "svc": true, "ensemble": false}}
+{"id": 67, "date": "2023-10-13", "result": {"forest": false, "gbt": true, "svc": true, "ensemble": true}}
+{"id": 121, "date": "2023-10-13", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 122, "date": "2023-10-13", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 123, "date": "2023-10-13", "result": {"forest": false, "gbt": false, "svc": true, "ensemble": false}}
+{"id": 67, "date": "2023-10-20", "result": {"forest": false, "gbt": false, "svc": true, "ensemble": false}}
+{"id": 121, "date": "2023-10-20", "result": {"forest": false, "gbt": true, "svc": false, "ensemble": true}}
+{"id": 122, "date": "2023-10-20", "result": {"forest": true, "gbt": true, "svc": false, "ensemble": true}}
+{"id": 123, "date": "2023-10-20", "result": {"forest": false, "gbt": false, "svc": true, "ensemble": false}}
+{"id": 67, "date": "2023-10-27", "result": {"forest": false, "gbt": true, "svc": true, "ensemble": true}}
+{"id": 121, "date": "2023-10-27", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 122, "date": "2023-10-27", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 123, "date": "2023-10-27", "result": {"forest": false, "gbt": false, "svc": true, "ensemble": false}}
+{"id": 67, "date": "2023-11-03", "result": {"forest": true, "gbt": true, "svc": true, "ensemble": true}}
+{"id": 121, "date": "2023-11-03", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 122, "date": "2023-11-03", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 123, "date": "2023-11-03", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 67, "date": "2023-11-17", "result": {"forest": false, "gbt": false, "svc": true, "ensemble": false}}
+{"id": 121, "date": "2023-11-17", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 122, "date": "2023-11-17", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 123, "date": "2023-11-17", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 67, "date": "2023-11-24", "result": {"forest": false, "gbt": false, "svc": true, "ensemble": false}}
+{"id": 121, "date": "2023-11-24", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 122, "date": "2023-11-24", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 123, "date": "2023-11-24", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 67, "date": "2023-12-01", "result": {"forest": false, "gbt": false, "svc": true, "ensemble": false}}
+{"id": 121, "date": "2023-12-01", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 122, "date": "2023-12-01", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 123, "date": "2023-12-01", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 67, "date": "2023-12-08", "result": {"forest": false, "gbt": false, "svc": true, "ensemble": false}}
+{"id": 121, "date": "2023-12-08", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 122, "date": "2023-12-08", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 123, "date": "2023-12-08", "result": {"forest": false, "gbt": false, "svc": false, "ensemble": false}}
+{"id": 67, "date": "2023-12-15", "result": {"forest": false, "gbt": false, "svc": true, "ensemble": false}}
+{"id": 121, "date": "2023-12-15", "result": {"forest": true, "gbt": true, "svc": true, "ensemble": true}}
+{"id": 122, "date": "2023-12-15", "result": {"forest": false, "gbt": false, "svc": true, "ensemble": false}}
+{"id": 123, "date": "2023-12-15", "result": {"forest": true, "gbt": true, "svc": true, "ensemble": true}}