Merge remote-tracking branch 'microsoft/main' into online_srv

qlib/workflow/record_temp.py

@@ -1,7 +1,7 @@
 #  Copyright (c) Microsoft Corporation.
 #  Licensed under the MIT License.
 
-import re
+import re, logging
 import pandas as pd
 from pathlib import Path
 from pprint import pprint
@@ -13,10 +13,10 @@ from ..data.dataset.handler import DataHandlerLP
 from ..utils import init_instance_by_config, get_module_by_module_path
 from ..log import get_module_logger
 from ..utils import flatten_dict
-from ..contrib.eva.alpha import calc_ic, calc_long_short_return
+from ..contrib.eva.alpha import calc_ic, calc_long_short_return, calc_long_short_prec
 from ..contrib.strategy.strategy import BaseStrategy
 
-logger = get_module_logger("workflow", "INFO")
+logger = get_module_logger("workflow", logging.INFO)
 
 
 class RecordTemp:
@@ -166,6 +166,60 @@ class SignalRecord(RecordTemp):
         return super().load(name)
 
 
+class HFSignalRecord(SignalRecord):
+    """
+    This is the Signal Analysis Record class that generates the analysis results such as IC and IR. This class inherits the ``RecordTemp`` class.
+    """
+
+    artifact_path = "hg_sig_analysis"
+
+    def __init__(self, recorder, **kwargs):
+        super().__init__(recorder=recorder)
+
+    def generate(self):
+        pred = self.load("pred.pkl")
+        raw_label = self.load("label.pkl")
+        long_pre, short_pre = calc_long_short_prec(pred.iloc[:, 0], raw_label.iloc[:, 0], is_alpha=True)
+        ic, ric = calc_ic(pred.iloc[:, 0], raw_label.iloc[:, 0])
+        metrics = {
+            "IC": ic.mean(),
+            "ICIR": ic.mean() / ic.std(),
+            "Rank IC": ric.mean(),
+            "Rank ICIR": ric.mean() / ric.std(),
+            "Long precision": long_pre.mean(),
+            "Short precision": short_pre.mean(),
+        }
+        objects = {"ic.pkl": ic, "ric.pkl": ric}
+        objects.update({"long_pre.pkl": long_pre, "short_pre.pkl": short_pre})
+        long_short_r, long_avg_r = calc_long_short_return(pred.iloc[:, 0], raw_label.iloc[:, 0])
+        metrics.update(
+            {
+                "Long-Short Average Return": long_short_r.mean(),
+                "Long-Short Average Sharpe": long_short_r.mean() / long_short_r.std(),
+            }
+        )
+        objects.update(
+            {
+                "long_short_r.pkl": long_short_r,
+                "long_avg_r.pkl": long_avg_r,
+            }
+        )
+        self.recorder.log_metrics(**metrics)
+        self.recorder.save_objects(**objects, artifact_path=self.get_path())
+        pprint(metrics)
+
+    def list(self):
+        paths = [
+            self.get_path("ic.pkl"),
+            self.get_path("ric.pkl"),
+            self.get_path("long_pre.pkl"),
+            self.get_path("short_pre.pkl"),
+            self.get_path("long_short_r.pkl"),
+            self.get_path("long_avg_r.pkl"),
+        ]
+        return paths
+
+
 class SigAnaRecord(SignalRecord):
     """
     This is the Signal Analysis Record class that generates the analysis results such as IC and IR. This class inherits the ``RecordTemp`` class.