可以指定任意天数的预测

ai/EstimateMarketTrendV20.py

@@ -2,7 +2,7 @@ import json
 from typing import List
 
 import numpy as np
-from py_jftech import autowired, parse_date, prev_workday, format_date
+from py_jftech import autowired, parse_date, prev_workday, format_date, get_config
 
 from ai.config import LABEL_RANGE, LABEL_TAG
 from ai.dao import robo_predict
@@ -16,10 +16,10 @@ from api import DataSync
 # 截止日期
 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
-uploadData = False  # 开启会上传预测结果
-doReport = True  # 开启会生成Excel报告
+toForecast = get_config('robo-executor.to-forecast')
+doReport = get_config('robo-executor.export')
+numForecastDays = get_config('robo-executor.num-forecast-days')  # business days, 21 business days means one month
+
 # JIFU_SPX_OPEPS_CURRQ_TTM
 # JIFU_SPX_OPEPS_YMAE1
 # JIFU_SPX_OPEPS_YMAE2
@@ -39,6 +39,8 @@ fund = [156]
 
 @autowired
 def sync(syncs: List[DataSync] = None):
+    sync_data = get_config('robo-executor.sync-data')
+    if sync_data:
         for s in syncs:
             # if isinstance(s, (IndexSync, EcoSync)):
             s.do_sync()
@@ -52,29 +54,29 @@ def report_prediction(label, predict_item, indexDict: dict):
     # 上传预测结果
     key = [k for k, v in indexDict.items() if v == predict_item][0]
     index_info = get_base_info(key)[0]
+    uploadData = get_config('robo-executor.upload-data')
     if uploadData:
         if len(LABEL_RANGE) > 2:
-            data = {"rbd_id": key, "date": forecastDay, "predict": prediction}
+            data = {"rbd_id": key, "date": forecastDay, "predict": prediction, "remark": {"period": numForecastDays}}
             robo_predict.insert(data)
         else:
             from ai.noticer import upload_predict
             upload_predict(index_info['ticker'], forecastDay, predictionStr)
-    send(content)
+    # 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 + 1)
+        navs = get_index_list(index_ids=id, min_date=start, limit=numForecastDays + 1)
         navs = [nav['rid_close'] for nav in navs]
     elif type == 'FUND':
-        navs = get_fund_list(fund_ids=id, min_date=start, limit=predict_term + 1)
+        navs = get_fund_list(fund_ids=id, min_date=start, limit=numForecastDays + 1)
         navs = [nav['rfn_nav_cal'] for nav in navs]
-    if len(navs) == predict_term + 1:
+    if len(navs) == numForecastDays + 1:
         upper = True if navs[-1] >= navs[0] else False
         result = {}
         for k, v, in predict.items():
@@ -95,13 +97,11 @@ def judgement(id, type, predict):
 
 ########################################
 if __name__ == '__main__':
-    if syncData:
     sync()
     # define some parameters
     win1W = 5  # 1 week
     win1M = 21  # 1 Month
     win1Q = 63  # 1 Quarter
-    numForecastDays = 21  # business days, 21 business days means one month
     theThreshold = 0.0
     ids = set(PREDICT_LIST) | set(eco) | set(index) | set(fund)
     infos = get_base_info(ids)
@@ -155,7 +155,7 @@ if __name__ == '__main__':
             else:
                 report_prediction(ensemble_model.predict(scaledX_forecast), indexDict[pid], indexDict)
     if doReport:
-        if len(LABEL_RANGE) > 2:
+        if len(LABEL_RANGE) > 2 and toForecast:
             from ai.reporter import do_reporter2
 
             do_reporter2()

ai/model_trainer.py

+import json
 from abc import ABC
 from datetime import datetime
 
 from lightgbm import LGBMClassifier
+from py_jftech import get_config
 from sklearn import svm
 from sklearn.ensemble import AdaBoostClassifier
 from sklearn.ensemble import RandomForestClassifier, VotingClassifier
@@ -41,9 +43,11 @@ class ModelTrainer(ABC):
         if doReport:
             if strMethod == "Ensemble Model":
                 datas = []
+                numForecastDays = get_config('robo-executor.num-forecast-days')
                 for predict, date in zip(y_pred, date_index):
                     datas.append(
-                        {'predict': predict, 'date': date, 'rbd_id': self._pid, 'create_time': datetime.now()})
+                        {'predict': predict, 'date': date, 'rbd_id': self._pid,
+                         "remark": json.dumps({"period": numForecastDays}), 'create_time': datetime.now()})
                 reporter.do_reporter2(records=datas, excel_name='Backtest_Report_chu.xlsx')
 
         # cm_display = ConfusionMatrixDisplay(confusion_matrix=result0, display_labels=labels)

ai/reporter.py

@@ -42,18 +42,20 @@ def do_reporter2(records=None, excel_name=None):
     if not records:
         records = robo_predict.get_list()
     for item in records:
+        predict_term = json.loads(item['remark'])['period']
         result, rtn, real = is_right(item['rbd_id'], info.get(item['rbd_id'])['type'], item['date'],
-                                     item['predict'])
+                                     item['predict'], predict_term)
         labels = list(LABEL_RANGE.keys())[::-1]
         data = {
             'Forcast On Date': item['date'],
             'Ticker': info.get(item['rbd_id'])['ticker'].replace(' Index', '').replace(' Equity', ''),
-            'In 21 business days': LABEL_TAG.get(item['predict']),
+            'Forecast Business Days After': predict_term,
+            'Forecast Label': LABEL_TAG.get(item['predict']),
             'real outcome label': LABEL_TAG.get(real),
             'random variable label': LABEL_TAG.get(random.randint(labels[0], labels[-1])),
             'Ticker Name': json.loads(info.get(item['rbd_id'])['datas'])['chineseName'],
             'Run On Time': item['create_time'].replace(minute=0, second=0),
-            'return in 21 business days': rtn,
+            'return on Forecast Label': rtn,
             'result': result
         }
         datas.append(data)
@@ -66,7 +68,9 @@ def do_reporter2(records=None, excel_name=None):
     pf['RMSE'] = RMSE
     pf['RefRMSE'] = RefRMSE
     pf['RevisedReferenceRMSE'] = RevisedReferenceRMSE
-    pf.to_excel(excel_name if excel_name else "Forcast_Report_chu.xlsx", index=False)
+    excel_name = excel_name if excel_name else "Forcast_Report_chu.xlsx"
+    with pd.ExcelWriter(excel_name, mode='a', if_sheet_exists='replace') as writer:
+        pf.to_excel(writer, sheet_name=f'{predict_term} business days', index=False)
 
 
 def map_to_label(ret):
@@ -82,9 +86,11 @@ def get_RMSE(datas):
     @return:
     """
     datas = [data for data in datas if data.get('real outcome label') is not None]
+    if not datas:
+        return 0
     tags = {v: k for k, v in LABEL_TAG.items()}
     return (sum(
-        [(tags.get(data['real outcome label']) - tags.get(data['In 21 business days'])) ** 2 for data in datas]) / len(
+        [(tags.get(data['real outcome label']) - tags.get(data['Forecast Label'])) ** 2 for data in datas]) / len(
         datas)) ** 0.5
 
 
@@ -95,6 +101,8 @@ def get_RefRMSE(datas):
     @return:
     """
     datas = [data for data in datas if data.get('real outcome label') is not None]
+    if not datas:
+        return 0
     tags = {v: k for k, v in LABEL_TAG.items()}
     return (sum(
         [(tags.get(data['real outcome label']) - tags.get(data['random variable label'])) ** 2 for data in
@@ -131,8 +139,7 @@ def get_RevisedReferenceRMSE(datas):
     return revised_ref_rmse
 
 
-def is_right(id, type, start, predict):
-    predict_term = 21
+def is_right(id, type, start, predict, predict_term):
     navs = []
     if type == 'INDEX':
         navs = get_index_list(index_ids=id, min_date=start, limit=predict_term + 1)

config-ai.yml

+py-jftech:
+  logger:
+    version: 1
+    formatters:
+      brief:
+        format: "%(asctime)s - %(levelname)s - %(message)s"
+      simple:
+        format: "%(asctime)s - %(filename)s - %(levelname)s - %(message)s"
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        level: DEBUG
+        stream: ext://sys.stdout
+      file:
+        class: logging.handlers.TimedRotatingFileHandler
+        level: INFO
+        formatter: brief
+        filename: ${LOG_FILE:logs/info.log}
+        interval: 1
+        backupCount: 30
+        encoding: utf8
+        when: D
+#    loggers:
+#      basic.sync:
+#        level: DEBUG
+#        handlers: [console]
+#        propagate: no
+    root:
+      level: ${LOG_LEVEL:INFO}
+      handlers: ${LOG_HANDLERS:[ console ]}
+  database:
+    host: ${MYSQL_HOST:106.14.56.221}
+    port: ${MYSQL_PORT:3306}
+    user: ${MYSQL_USER:ai_user}
+    password: ${MYSQL_PWD:ai.predict*2025}
+    dbname: ${MYSQL_DBNAME:ai_predict}
+  injectable:
+    names:
+      backtest: robo_executor.BacktestExecutor
+      datum: basic.datum.DefaultDatum
+      hold-report: portfolios.holder.DivHoldReportor
+      mpt: portfolios.builder.PoemARCPortfoliosBuilder
+      dividend-holder: portfolios.holder.InvTrustPortfoliosHolder
+      navs-sync: basic.sync.FundNavSync
+  email:
+    server: smtphz.qiye.163.com
+    user: jft-ra@thizgroup.com
+    password: 5dbb#30ec6d3
+  mulit-process:
+    max-workers: ${MAX_PROCESS:4}
+basic: # 基础信息模块
+  sync:
+    start-date: 2018-08-26 # 同步数据开始日期
+  datum: # 资料模块
+    change:
+      date: ${DATUM_CHANGE_DATE}
+      file: ${DATUM_CHANGE_FILE}
+    excludes: # 排除的资料彭博ticker
+#      backtest:
+#        - 'TEMUSGI LX Equity'
+      real:
+        - 'FGFSACU LX Equity'
+        - 'TEMUSGI LX Equity'
+  navs: # 净值模块
+    exrate: # 汇率，如果不开启，整个这块注释掉
+      - from: EUR # 需要转换的货币类型
+        ticker: EURUSD BGN Curncy # 汇率值的彭博ticker
+robo-executor: # 执行器相关
+  to-forecast: off  # False means test, True means forecast
+  sync-data: ${SYNC_DATA:off} # 开启会同步数据库指数及基金数据
+  upload-data: off  # 开启会上传预测结果
+  export: ${EXPORT_ENABLE:on} # 是否开启报告
+  num-forecast-days: 21 # business days, 21 business days means one month
+
+  use: ${ROBO_EXECUTOR:backtest} # 执行哪个执行器，优先取系统环境变量ROBO_EXECUTOR的值，默认backtest
+  backtest: # 回测执行器相关
+    start-date: 2018-11-26 # 回测起始日期
+    end-date: 2019-01-13 # 回测截止日期
+    sealing-period: 10 #调仓封闭期
+    start-step: ${BACKTEST_START_STEP:1} # 回测从哪一步开始执行 1:计算资产池；2:计算最优投组：3:计算再平衡信号以及持仓投组
+    end-step: ${BACKTEST_END_STEP:3} # 回测从哪一步执行完成后结束执行 1:计算资产池；2:计算最优投组：3:计算再平衡信号以及持仓投组
+    clean-up: off
+  real: # 实盘执行器
+    export: ${EXPORT_ENABLE:off} # 是否开启报告
+    start-date: 2023-05-08 # 实盘开始时间
+    include-date: []
+
+
+
+