add robust zscore processor & ALPHA360 support custom processors

qlib/contrib/data/handler.py

@@ -10,6 +10,28 @@ from inspect import getfullargspec
 import copy
 
 
+def check_transform_proc(proc_l, fit_start_time, fit_end_time):
+    new_l = []
+    for p in proc_l:
+        if not isinstance(p, Processor):
+            klass, pkwargs = get_cls_kwargs(p, processor_module)
+            args = getfullargspec(klass).args
+            if "fit_start_time" in args and "fit_end_time" in args:
+                assert (
+                    fit_start_time is not None and fit_end_time is not None
+                ), "Make sure `fit_start_time` and `fit_end_time` are not None."
+                pkwargs.update(
+                    {
+                        "fit_start_time": fit_start_time,
+                        "fit_end_time": fit_end_time,
+                    }
+                )
+            new_l.append({"class": klass.__name__, "kwargs": pkwargs})
+        else:
+            new_l.append(p)
+    return new_l
+
+
 class ALPHA360_Denoise(DataHandlerLP):
     def __init__(self, instruments="csi500", start_time=None, end_time=None, fit_start_time=None, fit_end_time=None):
         data_loader = {
@@ -83,8 +105,31 @@ class ALPHA360_Denoise(DataHandlerLP):
         return fields, names
 
 
+_DEFAULT_LEARN_PROCESSORS = [
+    {"class": "DropnaLabel"},
+    {"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}},
+]
+_DEFAULT_INFER_PROCESSORS = [
+    {"class": "ProcessInf", "kwargs": {}},
+    {"class": "ZScoreNorm", "kwargs": {}},
+    {"class": "Fillna", "kwargs": {}},
+]
+
+
 class ALPHA360(DataHandlerLP):
-    def __init__(self, instruments="csi500", start_time=None, end_time=None, fit_start_time=None, fit_end_time=None):
+    def __init__(
+        self,
+        instruments="csi500",
+        start_time=None,
+        end_time=None,
+        infer_processors=_DEFAULT_INFER_PROCESSORS,
+        learn_processors=_DEFAULT_LEARN_PROCESSORS,
+        fit_start_time=None,
+        fit_end_time=None,
+    ):
+        infer_processors = check_transform_proc(infer_processors, fit_start_time, fit_end_time)
+        learn_processors = check_transform_proc(learn_processors, fit_start_time, fit_end_time)
+
         data_loader = {
             "class": "QlibDataLoader",
             "kwargs": {
@@ -95,16 +140,6 @@ class ALPHA360(DataHandlerLP):
             },
         }
 
-        learn_processors = [
-            {"class": "DropnaLabel", "kwargs": {"fields_group": "label"}},
-            {"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}},
-        ]
-        infer_processors = [
-            {"class": "ProcessInf", "kwargs": {}},
-            {"class": "ZscoreNorm", "kwargs": {"fit_start_time": fit_start_time, "fit_end_time": fit_end_time}},
-            {"class": "Fillna", "kwargs": {}},
-        ]
-
         super().__init__(
             instruments,
             start_time,
@@ -168,33 +203,12 @@ class Alpha158(DataHandlerLP):
         start_time=None,
         end_time=None,
         infer_processors=[],
-        learn_processors=["DropnaLabel", {"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}}],
+        learn_processors=_DEFAULT_LEARN_PROCESSORS,
         fit_start_time=None,
         fit_end_time=None,
     ):
-        def check_transform_proc(proc_l):
+        infer_processors = check_transform_proc(infer_processors, fit_start_time, fit_end_time)
-            new_l = []
+        learn_processors = check_transform_proc(learn_processors, fit_start_time, fit_end_time)
-            for p in proc_l:
-                if not isinstance(p, Processor):
-                    klass, pkwargs = get_cls_kwargs(p, processor_module)
-                    args = getfullargspec(klass).args
-                    if "fit_start_time" in args and "fit_end_time" in args:
-                        assert (
-                            fit_start_time is not None and fit_end_time is not None
-                        ), "Make sure `fit_start_time` and `fit_end_time` are not None."
-                        pkwargs.update(
-                            {
-                                "fit_start_time": fit_start_time,
-                                "fit_end_time": fit_end_time,
-                            }
-                        )
-                    new_l.append({"class": klass.__name__, "kwargs": pkwargs})
-                else:
-                    new_l.append(p)
-            return new_l
-
-        infer_processors = check_transform_proc(infer_processors)
-        learn_processors = check_transform_proc(learn_processors)
 
         data_loader = {
             "class": "QlibDataLoader",

qlib/data/dataset/processor.py

@@ -166,7 +166,9 @@ class MinMaxNorm(Processor):
         return df
 
 
-class ZscoreNorm(Processor):
+class ZScoreNorm(Processor):
+    """ZScore Normalization"""
+
     def __init__(self, fit_start_time, fit_end_time, fields_group=None):
         self.fit_start_time = fit_start_time
         self.fit_end_time = fit_end_time
@@ -193,6 +195,40 @@ class ZscoreNorm(Processor):
         return df
 
 
+class RobustZScoreNorm(Processor):
+    """Robust ZScore Normalization
+
+    Use robust statistics for Z-Score normalization:
+        mean(x) = median(x)
+        std(x) = MAD(x) * 1.4826
+
+    Reference:
+        https://en.wikipedia.org/wiki/Median_absolute_deviation.
+    """
+
+    def __init__(self, fit_start_time, fit_end_time, fields_group=None, clip_outlier=True):
+        self.fit_start_time = fit_start_time
+        self.fit_end_time = fit_end_time
+        self.fields_group = fields_group
+        self.clip_outlier = clip_outlier
+
+    def fit(self, df):
+        df = fetch_df_by_index(df, slice(self.fit_start_time, self.fit_end_time), level="datetime")
+        self.cols = get_group_columns(df, self.fields_group)
+        X = df[self.cols].values
+        self.mean_train = np.nanmedian(X, axis=0)
+        self.std_train = np.nanmedian(np.abs(X - self.mean_train), axis=0)
+        self.std_train += EPS
+        self.std_train *= 1.4826
+
+    def __call__(self, df):
+        df.loc(axis=1)[self.cols] -= self.mean_train
+        df.loc(axis=1)[self.cols] /= self.std_train
+        if self.clip_outlier:
+            df.clip(-3, 3, inplace=True)
+        return df
+
+
 class CSZScoreNorm(Processor):
     """Cross Sectional ZScore Normalization"""