AnomalyLab 0.4.0__tar.gz → 0.4.2__tar.gz

{anomalylab-0.4.0 → anomalylab-0.4.2}/AnomalyLab.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: AnomalyLab
-Version: 0.4.0
+Version: 0.4.2
 Summary: A Python package for empirical asset pricing analysis.
 Author: FinPhd
 Author-email: chenhaiwei@stu.sufe.edu.cn

{anomalylab-0.4.0 → anomalylab-0.4.2}/AnomalyLab.egg-info/SOURCES.txt

@@ -1,6 +1,5 @@
 .gitattributes
 .gitignore
-.png
 LICENSE
 MANIFEST.in
 README.md

{anomalylab-0.4.0 → anomalylab-0.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: AnomalyLab
-Version: 0.4.0
+Version: 0.4.2
 Summary: A Python package for empirical asset pricing analysis.
 Author: FinPhd
 Author-email: chenhaiwei@stu.sufe.edu.cn

{anomalylab-0.4.0 → anomalylab-0.4.2}/anomalylab/core/core.py

@@ -499,12 +499,20 @@ class Panel:
             DataFrame: If inplace=False (default), returns a new DataFrame with grouped variables.
             None: If inplace=True, modifies the original dataset and returns None.
         """
-        return self.portfolio_analysis_processor(endog=endog, weight=weight).GroupN(
-            vars=vars,
-            groups=groups,
-            sort_type=sort_type,
-            inplace=inplace,
-        )
+        if inplace:
+            self.panel_data.df = self.portfolio_analysis_processor(
+                endog=endog, weight=weight
+            ).GroupN(
+                vars=vars,
+                groups=groups,
+                sort_type=sort_type,
+            )
+        else:
+            return self.portfolio_analysis_processor(endog=endog, weight=weight).GroupN(
+                vars=vars,
+                groups=groups,
+                sort_type=sort_type,
+            )
 
     def univariate_analysis(
         self,
@@ -618,7 +626,6 @@ class Panel:
         industry_weighed_method: Literal["value", "equal"] = "value",
         is_winsorize: bool = False,
         is_normalize: bool = False,
-        dummy_no_norm: Optional[list[str] | str] = None,
         decimal: Optional[int] = None,
         return_intermediate: bool = False,
     ) -> DataFrame:
@@ -639,8 +646,6 @@ class Panel:
             industry_weighed_method (Literal["value", "equal"]): Method for weighting industries.
             is_winsorize (bool): Indicates whether to apply winsorization.
             is_normalize (bool): Indicates whether to normalize exogenous variables.
-            dummy_no_norm (Optional[list[str] | str]): Name(s) of dummy variables (e.g., 0 or 1)
-                that should be excluded from normalization.
             decimal (Optional[int]): Number of decimal places for rounding in output.
             return_intermediate (bool): If True, returns the intermediate results (e.g., coefficients for each time period).
 
@@ -658,7 +663,6 @@ class Panel:
             industry_weighed_method=industry_weighed_method,
             is_winsorize=is_winsorize,
             is_normalize=is_normalize,
-            dummy_no_norm=dummy_no_norm,
             decimal=decimal,
             return_intermediate=return_intermediate,
         )
@@ -739,30 +743,37 @@ if __name__ == "__main__":
     panel.winsorize(method="winsorize", group_columns="date")
     pp(panel)
 
-    summary = panel.summary()
-    pp(summary)
-
-    correlation = panel.correlation()
-    pp(correlation)
-
-    persistence = panel.persistence(periods=[1, 3, 6, 12, 36, 60])
-    pp(persistence)
-    pp(
-        panel.transition_matrix(
-            var="MktCap",
-            group=10,
-            lag=12,
-            draw=False,
-            # path=str(resources.files("anomalylab.datasets")) + "/transition_matrix.png",
-            path="...",
-            decimal=2,
-        )
-    )
+    # summary = panel.summary()
+    # pp(summary)
+
+    # correlation = panel.correlation()
+    # pp(correlation)
+
+    # persistence = panel.persistence(periods=[1, 3, 6, 12, 36, 60])
+    # pp(persistence)
+    # pp(
+    #     panel.transition_matrix(
+    #         var="MktCap",
+    #         group=10,
+    #         lag=12,
+    #         draw=False,
+    #         # path=str(resources.files("anomalylab.datasets")) + "/transition_matrix.png",
+    #         path="...",
+    #         decimal=2,
+    #     )
+    # )
 
-    group_result = panel.group("return", "MktCap", "Illiq", 10)
+    panel.group("return", "MktCap", "Illiq", 10, inplace=True)
 
     uni_ew, uni_vw = panel.univariate_analysis(
-        "return", "MktCap", "Illiq", 10, Models, time_series, factor_return=False
+        "return",
+        "MktCap",
+        "Illiq",
+        10,
+        Models,
+        time_series,
+        factor_return=False,
+        already_grouped=True,
     )
     pp(uni_ew)
     pp(uni_vw)

{anomalylab-0.4.0 → anomalylab-0.4.2}/anomalylab/empirical/fm_regression.py

@@ -92,7 +92,6 @@ class FamaMacBethRegression(Empirical):
         df: DataFrame,
         reg: RegModel,
         is_normalize: bool,
-        dummy_no_norm: list[str] = [],
         return_intermediate: bool = False,
     ) -> RegResult:
         """Performs Fama-MacBeth regression on the provided DataFrame.
@@ -105,9 +104,6 @@ class FamaMacBethRegression(Empirical):
             df (DataFrame): DataFrame containing the data for regression.
             reg (RegModel): Model specification containing endogenous and exogenous variables.
             is_normalize (bool): Indicates whether to normalize the exogenous variables.
-            dummy_no_norm (list[str]): List of variable names that should be excluded from normalization.
-                Typically, these are dummy variables that take values like 0 or 1,
-                where normalization may not make sense.
             return_intermediate (bool): If True, returns intermediate regression results
                 (e.g., coefficients, t-values, and R²) for each time period.
 
@@ -121,26 +117,9 @@ class FamaMacBethRegression(Empirical):
         df = df.groupby(self.time).filter(lambda x: len(x) > 1)
         lag: int = math.ceil(4 * (df[self.time].nunique() / 100) ** (4 / 25))
         if is_normalize:
-            dummy_no_norm = [col for col in dummy_no_norm if col in exogenous]
-
-            variables_to_normalize = [
-                col for col in exogenous if col not in dummy_no_norm
-            ]
-
-            for col in variables_to_normalize:
-                grouped_std = df.groupby(self.time)[col].std()
-
-                if (grouped_std == 0).any():
-                    problematic_group = grouped_std[grouped_std == 0].index.tolist()
-                    raise ValueError(
-                        f"Standard deviation is 0 for variable '{col}' in group(s) {problematic_group}. "
-                        f"Cannot normalize this variable. If '{col}' is a dummy variable, please add it to `dummy_no_norm`."
-                    )
-
-            if variables_to_normalize:
-                df[variables_to_normalize] = df.groupby(self.time)[
-                    variables_to_normalize
-                ].transform(func=lambda x: (x - x.mean()) / x.std())
+            df[exogenous] = df.groupby(self.time)[exogenous].transform(
+                func=lambda x: (x - x.mean()) / x.std()
+            )
 
         df[self.time] = df[self.time].dt.to_timestamp()
         df = df.set_index([self.id, self.time])
@@ -172,7 +151,7 @@ class FamaMacBethRegression(Empirical):
             params=fmb.params,
             tvalues=fmb.tstats,
             pvalues=fmb.pvalues,
-            mean_obs=str(int(fmb.time_info["mean"])),
+            mean_obs=str(round(fmb.time_info["mean"])),
             rsquared=(
                 df.reset_index(level=df.index.names[0], drop=True)
                 .groupby(self.time)
@@ -301,7 +280,6 @@ class FamaMacBethRegression(Empirical):
         industry_weighed_method: Literal["value", "equal"] = "value",
         is_winsorize: bool = False,
         is_normalize: bool = False,
-        dummy_no_norm: Optional[list[str] | str] = None,
         decimal: Optional[int] = None,
         return_intermediate: bool = False,  # New parameter to control whether intermediate results are returned
     ) -> DataFrame:
@@ -322,8 +300,6 @@ class FamaMacBethRegression(Empirical):
             industry_weighed_method (Literal["value", "equal"]): Method for weighting industries.
             is_winsorize (bool): Indicates whether to apply winsorization.
             is_normalize (bool): Indicates whether to normalize exogenous variables.
-            dummy_no_norm (Optional[list[str] | str]): Name(s) of dummy variables (e.g., 0 or 1)
-                that should be excluded from normalization.
             decimal (Optional[int]): Number of decimal places for rounding in output.
             return_intermediate (bool): If True, returns the intermediate results (e.g., coefficients for each time period).
 
@@ -334,7 +310,6 @@ class FamaMacBethRegression(Empirical):
         reg_models: RegModels = self._model_parse(
             regs=regs, endog=endog, exog=columns_to_list(exog)
         )
-        dummy_no_norm = columns_to_list(dummy_no_norm)
         self._winsorize(is_winsorize=is_winsorize, exog=reg_models.exogenous)
         self._industry_weighted(
             endog=reg_models.dependent,
@@ -350,7 +325,6 @@ class FamaMacBethRegression(Empirical):
                     df=self.panel_data.df,
                     reg=model,
                     is_normalize=is_normalize,
-                    dummy_no_norm=dummy_no_norm,
                     return_intermediate=True,
                 )
                 for model in reg_models.models
@@ -366,7 +340,6 @@ class FamaMacBethRegression(Empirical):
                             df=self.panel_data.df,
                             reg=model,
                             is_normalize=is_normalize,
-                            dummy_no_norm=dummy_no_norm,
                             return_intermediate=False,
                         ),
                         decimal=decimal or self.decimal,

{anomalylab-0.4.0 → anomalylab-0.4.2}/anomalylab/structure/panel_data.py

@@ -112,9 +112,17 @@ class PanelData(Data):
         """Check if the required columns are present in the DataFrame.
 
         Raises:
+            ValueError: If any duplicate column names are found in the DataFrame.
             ValueError: If any required columns are missing from the DataFrame.
             ValueError: If there are no firm characteristics remaining after checking.
         """
+        # Check for duplicate column names
+        duplicated_columns = self.df.columns[self.df.columns.duplicated()].tolist()
+        if duplicated_columns:
+            raise ValueError(
+                f"Duplicate column names found in the DataFrame: {duplicated_columns}"
+            )
+
         if isinstance(self.classifications, str):
             self.classifications = [self.classifications]
         # Check if the required columns are present in the DataFrame

{anomalylab-0.4.0 → anomalylab-0.4.2}/anomalylab/structure/time_series.py

@@ -49,9 +49,17 @@ class TimeSeries(Data):
         Check if the required column is present in the DataFrame and ensure there are additional columns.
 
         Raises:
+            ValueError: If duplicate column names are found in the DataFrame.
             ValueError: If the time column is missing from the DataFrame.
             ValueError: If there are no additional columns for factor returns.
         """
+        # Check for duplicate column names
+        duplicated_columns = self.df.columns[self.df.columns.duplicated()].tolist()
+        if duplicated_columns:
+            raise ValueError(
+                f"Duplicate column names found in the DataFrame: {duplicated_columns}"
+            )
+
         if self.time not in self.df.columns:
             raise ValueError(f"Missing column in the DataFrame: {self.time}")
 

{anomalylab-0.4.0 → anomalylab-0.4.2}/setup.py

@@ -2,7 +2,7 @@ from setuptools import find_packages, setup
 
 setup(
     name="AnomalyLab",
-    version="0.4.0",
+    version="0.4.2",
     author="FinPhd",
     author_email="chenhaiwei@stu.sufe.edu.cn",
     description="A Python package for empirical asset pricing analysis.",