update some little code

examples/high_freq/highfreq_handler.py

@@ -55,8 +55,8 @@ class HighFreqHandler(DataHandlerLP):
         names = []
 
         template_if = "If(IsNull({1}), {0}, {1})"
-        #template_paused = "Select(Eq($paused, 0.0), {0})"
-        template_paused="{0}"
+        template_paused = "Select(Eq($paused, 0.0), {0})"
+        # template_paused="{0}"
         template_fillnan = "FFillNan({0})"
         simpson_vwap = "($open + 2*$high + 2*$low + $close)/6"
         fields += [
@@ -128,7 +128,7 @@ class HighFreqHandler(DataHandlerLP):
         fields += [
             "Ref({0}, 240)/Ref(DayLast({0}), 240)".format(template_fillnan.format(template_paused.format("$close")))
         ]
-        
+
         fields += [
             "Ref({0}, 240)/Ref(DayLast({1}), 240)".format(
                 template_if.format(
@@ -196,17 +196,19 @@ class HighFreqBacktestHandler(DataHandler):
         names = []
 
         template_if = "If(Eq({1}, np.nan), {0}, {1})"
-        #template_paused = "Select(Eq($paused, 0.0), {0})"
-        template_paused="{0}"
+        template_paused = "Select(Eq($paused, 0.0), {0})"
+        # template_paused="{0}"
         template_fillnan = "FFillNan({0})"
         simpson_vwap = "($open + 2*$high + 2*$low + $close)/6"
-        #fields += [
+        # fields += [
         #    template_fillnan.format(template_paused.format("$close")),
-        #]
-        fields += [template_if.format(
-                    template_fillnan.format(template_paused.format("$close")),
-                    template_paused.format(simpson_vwap),
-                )]
+        # ]
+        fields += [
+            template_if.format(
+                template_fillnan.format(template_paused.format("$close")),
+                template_paused.format(simpson_vwap),
+            )
+        ]
         names += ["$vwap_0"]
         fields += [
             "If(IsNull({0}), 0, If(Or(Gt({1}, Mul(1.001, {3})), Lt({1}, Mul(0.999, {2}))), 0, {0}))".format(

examples/high_freq/highfreq_processor.py

@@ -58,7 +58,6 @@ class HighFreqNorm(Processor):
         # print("start_call_feature_reshape")
         idx = df_features.index.droplevel("datetime").drop_duplicates()
         idx.set_names(["instrument", "datetime"], inplace=True)
-        print(df_values.shape)
         feat = df_values[:, [0, 1, 2, 3, 4, 10]].reshape(-1, 6 * 240)
         feat_1 = df_values[:, [5, 6, 7, 8, 9, 11]].reshape(-1, 6 * 240)
         df_new_features = pd.DataFrame(

examples/high_freq/workflow.py

@@ -38,12 +38,12 @@ if __name__ == "__main__":
 
     MARKET = "all"
     BENCHMARK = "SH000300"
-    DROP_LOAD_DATASET = False # flag wether to test [drop and load dataset]
+    DROP_LOAD_DATASET = False  # flag wether to test [drop and load dataset]
 
-    #start_time = "2019-01-01 00:00:00"
-    #end_time = "2019-12-31 15:00:00"
-    #train_end_time = "2019-05-31 15:00:00"
-    #test_start_time = "2019-06-01 00:00:00"
+    # start_time = "2019-01-01 00:00:00"
+    # end_time = "2019-12-31 15:00:00"
+    # train_end_time = "2019-05-31 15:00:00"
+    # test_start_time = "2019-06-01 00:00:00"
     start_time = "2020-09-14 00:00:00"
     end_time = "2021-01-18 16:00:00"
     train_end_time = "2020-11-30 16:00:00"
@@ -108,11 +108,12 @@ if __name__ == "__main__":
         },
     }
     ##=============load the calendar for cache=============
-    Cal.calendar(freq="1min")
-    Cal.get_calendar_day(freq="1min")
+    # unnecessary, but may accelerate
+    Cal.calendar(freq="1min")  # load the calendar for cache
+    Cal.get_calendar_day(freq="1min")  # load the calendar for cache
 
     ##=============get data=============
-    
+
     dataset = init_instance_by_config(task["dataset"])
     xtrain, xtest = dataset.prepare(["train", "test"])
     print(xtrain, xtest)
@@ -124,7 +125,7 @@ if __name__ == "__main__":
     del xtrain, xtest
     del backtest_train, backtest_test
 
-
+    ## example to show how to save the dataset and reload it, and how to use different data
     if DROP_LOAD_DATASET:
 
         ##=============dump dataset=============
@@ -147,6 +148,7 @@ if __name__ == "__main__":
         dataset_backtest.init(init_type=DataHandlerLP.IT_LS)
 
         ##=============reinit qlib=============
+        ## Unless you want to modify the provider_uri and other configurations, reinit is unnecessary
         qlib.init(
             provider_uri=provider_uri,
             custom_ops=[DayFirst, DayLast, FFillNan, Date, Select, IsNull],
@@ -158,7 +160,7 @@ if __name__ == "__main__":
         Cal.calendar(freq="1min")  # load the calendar for cache
         Cal.get_calendar_day(freq="1min")  # load the calendar for cache
 
-        ##=============test dataset
+        ##=============test dataset=============
         xtrain, xtest = dataset.prepare(["train", "test"])
         backtest_train, backtest_test = dataset_backtest.prepare(["train", "test"])