AnomalyLab 0.2.4__tar.gz → 0.2.6__tar.gz

{anomalylab-0.2.4 → anomalylab-0.2.6/AnomalyLab.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: AnomalyLab
-Version: 0.2.4
+Version: 0.2.6
 Summary: A Python package for empirical asset pricing analysis.
 Author: FinPhd
 Classifier: Programming Language :: Python :: 3

{anomalylab-0.2.4/AnomalyLab.egg-info → anomalylab-0.2.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: AnomalyLab
-Version: 0.2.4
+Version: 0.2.6
 Summary: A Python package for empirical asset pricing analysis.
 Author: FinPhd
 Classifier: Programming Language :: Python :: 3

{anomalylab-0.2.4 → anomalylab-0.2.6}/anomalylab/empirical/fm_regression.py

@@ -38,7 +38,8 @@ class FamaMacBethRegression(Empirical):
                 OutlierHandler(panel_data=self.panel_data)
                 .winsorize(
                     columns=exog,
-                    process_all_characteristics=False,
+                    method="winsorize",
+                    group_columns=self.panel_data.time,
                 )
                 .panel_data
             )
@@ -317,10 +318,10 @@ if __name__ == "__main__":
         # exog="MktCap",
         exog_order=["MktCap"],
         regs=[
-            "return",
-            "MktCap",
-            # ["return", "Illiq"],
-            # ["return", "IdioVol"],
+            # "return",
+            # "MktCap",
+            ["return", "Illiq"],
+            ["return", "IdioVol"],
             # ["return", "MktCap", "Illiq", "IdioVol"],
         ],
         # models=[
@@ -332,7 +333,7 @@ if __name__ == "__main__":
         industry="industry",
         industry_weighed_method="value",
         weight="MktCap",
-        # is_winsorize=True,
+        is_winsorize=True,
         is_normalize=True,
         # decimal=2,
     )

{anomalylab-0.2.4 → anomalylab-0.2.6}/anomalylab/structure/panel_data.py

@@ -61,12 +61,15 @@ class PanelData(Data):
         self.df[self.time] = pd.to_datetime(self.df[self.time], format="ISO8601")
         self.df[self.time] = self.df[self.time].dt.to_period(freq=self.frequency)
         self.df = self.df.sort_values(by=[self.time, self.id])
+        basic_column = (
+            [self.id, self.time] if self.ret is None else [self.id, self.time, self.ret]
+        )
         # Identify remaining columns and set them as firm characteristics, excluding classifications
         self.firm_characteristics: set[str] = set(
             filter(
                 lambda x: (
                     x
-                    not in [self.id, self.time, self.ret]
+                    not in basic_column
                     + (
                         self.classifications
                         if isinstance(self.classifications, list)
@@ -111,9 +114,10 @@ class PanelData(Data):
         if isinstance(self.classifications, str):
             self.classifications = [self.classifications]
         # Check if the required columns are present in the DataFrame
-        required_columns: set[str] = set(
-            [self.id, self.time, self.ret] + (self.classifications or [])
+        basic_column = (
+            [self.id, self.time] if self.ret is None else [self.id, self.time, self.ret]
         )
+        required_columns: set[str] = set(basic_column + (self.classifications or []))
         missing_columns: set[str] = required_columns - set(self.df.columns)
         if missing_columns:
             raise ValueError(f"Missing columns in the DataFrame: {missing_columns}")
@@ -201,6 +205,7 @@ if __name__ == "__main__":
         name="Stocks",
         id="permno",
         time="date",
+        ret="return",
         classifications="industry",
         drop_all_chars_missing=True,
     )

{anomalylab-0.2.4 → anomalylab-0.2.6}/setup.py

@@ -2,7 +2,7 @@ from setuptools import find_packages, setup
 
 setup(
     name="AnomalyLab",
-    version="0.2.4",
+    version="0.2.6",
     author="FinPhd",
     # author_email="your.email@example.com",
     description="A Python package for empirical asset pricing analysis.",