Add config file in trade

Update readme in trade
Update highfreq to delete nan order

examples/highfreq/workflow.py

@@ -9,7 +9,7 @@ import qlib
 import pickle
 import numpy as np
 import pandas as pd
-from qlib.config import HIGH_FREQ_CONFIG
+from qlib.config import REG_CN, HIGH_FREQ_CONFIG
 from qlib.contrib.model.gbdt import LGBModel
 from qlib.contrib.data.handler import Alpha158
 from qlib.contrib.strategy.strategy import TopkDropoutStrategy
@@ -24,17 +24,17 @@ from qlib.data.ops import Operators
 from qlib.data.data import Cal
 from qlib.tests.data import GetData
 
-from highfreq_ops import get_calendar_day, DayLast, FFillNan, BFillNan, Date, Select, IsNull
+from highfreq_ops import get_calendar_day, DayLast, FFillNan, BFillNan, Date, Select, IsNull, Cut
 
 
 class HighfreqWorkflow(object):
 
-    SPEC_CONF = {"custom_ops": [DayLast, FFillNan, BFillNan, Date, Select, IsNull], "expression_cache": None}
+    SPEC_CONF = {"custom_ops": [DayLast, FFillNan, BFillNan, Date, Select, IsNull, Cut], "expression_cache": None}
 
     MARKET = "all"
     BENCHMARK = "SH000300"
 
-    start_time = "2020-09-14 00:00:00"
+    start_time = "2020-09-15 00:00:00"
     end_time = "2021-01-18 16:00:00"
     train_end_time = "2020-11-30 16:00:00"
     test_start_time = "2020-12-01 00:00:00"
@@ -42,7 +42,6 @@ class HighfreqWorkflow(object):
     DATA_HANDLER_CONFIG0 = {
         "start_time": start_time,
         "end_time": end_time,
-        "freq": "1min",
         "fit_start_time": start_time,
         "fit_end_time": train_end_time,
         "instruments": MARKET,
@@ -51,7 +50,6 @@ class HighfreqWorkflow(object):
     DATA_HANDLER_CONFIG1 = {
         "start_time": start_time,
         "end_time": end_time,
-        "freq": "1min",
         "instruments": MARKET,
     }
 
@@ -125,8 +123,7 @@ class HighfreqWorkflow(object):
         backtest_train, backtest_test = dataset_backtest.prepare(["train", "test"])
         print(backtest_train, backtest_test)
 
-        del xtrain, xtest
-        del backtest_train, backtest_test
+        return
 
     def dump_and_load_dataset(self):
         """dump and load dataset state on disk"""
@@ -148,19 +145,73 @@ class HighfreqWorkflow(object):
             dataset_backtest = pickle.load(file_dataset_backtest)
 
         self._prepare_calender_cache()
-        ##=============reload_dataset=============
-        dataset.init(init_type=DataHandlerLP.IT_LS)
-        dataset_backtest.init()
+        ##=============reinit dataset=============
+        dataset.init(
+            handler_kwargs={
+                "init_type": DataHandlerLP.IT_LS,
+                "start_time": "2021-01-19 00:00:00",
+                "end_time": "2021-01-25 16:00:00",
+            },
+            segment_kwargs={
+                "test": (
+                    "2021-01-19 00:00:00",
+                    "2021-01-25 16:00:00",
+                ),
+            },
+        )
+        dataset_backtest.init(
+            handler_kwargs={
+                "start_time": "2021-01-19 00:00:00",
+                "end_time": "2021-01-25 16:00:00",
+            },
+            segment_kwargs={
+                "test": (
+                    "2021-01-19 00:00:00",
+                    "2021-01-25 16:00:00",
+                ),
+            },
+        )
 
         ##=============get data=============
-        xtrain, xtest = dataset.prepare(["train", "test"])
-        backtest_train, backtest_test = dataset_backtest.prepare(["train", "test"])
+        xtest = dataset.prepare(["test"])
+        backtest_test = dataset_backtest.prepare(["test"])
 
-        print(xtrain, xtest)
-        print(backtest_train, backtest_test)
-        del xtrain, xtest
-        del backtest_train, backtest_test
+        print(xtest, backtest_test)
+        return
+
+
+    def get_high_freq_data(self, data_path):
+        self._init_qlib()
+        self._prepare_calender_cache()
+
+        import os
+        dataset = init_instance_by_config(self.task["dataset"])
+        xtrain, xtest = dataset.prepare(["train", "test"])
+        normed_feature = pd.concat([xtrain, xtest]).sort_index()
+        dic = dict(tuple(normed_feature.groupby("instrument")))
+        feature_path = os.path.join(data_path, "normed_feature/")
+        if not os.path.exists(feature_path):
+            os.makedirs(feature_path)
+        for k, v in dic.items():
+            v.to_pickle(feature_path + f"{k}.pkl")
+
+
+        dataset_backtest = init_instance_by_config(self.task["dataset_backtest"])
+        backtest_train, backtest_test = dataset_backtest.prepare(["train", "test"])
+        backtest = pd.concat([backtest_train, backtest_test]).sort_index()
+        backtest['date'] = backtest.index.map(lambda x: x[1].date())
+        backtest.set_index('date', append=True, drop=True, inplace=True)
+        dic = dict(tuple(backtest.groupby("instrument")))
+        backtest_path = os.path.join(data_path, "backtest/")
+        if not os.path.exists(backtest_path):
+            os.makedirs(backtest_path)
+        for k, v in dic.items():
+            v.to_pickle(backtest_path + f"{k}.pkl.backtest")
 
 
 if __name__ == "__main__":
-    fire.Fire(HighfreqWorkflow)
+    #fire.Fire(HighfreqWorkflow)
+    data_path = '../data/'
+    workflow = HighfreqWorkflow()
+    workflow.get_high_freq_data(data_path)
+