classifier-toolkit 0.1.3__tar.gz → 0.1.4__tar.gz

{classifier_toolkit-0.1.3 → classifier_toolkit-0.1.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: classifier-toolkit
-Version: 0.1.3
+Version: 0.1.4
 Summary: 
 Author: gauthier.marquand
 Author-email: gauthier.marquand@qonto.com

{classifier_toolkit-0.1.3 → classifier_toolkit-0.1.4}/classifier_toolkit/eda/eda_toolkit.py

@@ -206,12 +206,20 @@ class EDAToolkit:
         self.first_glance.super_vision()
         self.first_glance.check_duplicates()
 
-    def plot_target_evolution(self):
+    def plot_target_evolution(self, time_column: str, evolving_numeric: str):
         """
         Plot the target balance and evolution over time.
+
+        Parameters
+        ----------
+        time_column : str
+            The name of the time column.
+        evolving_numeric : str
+            The name of the numerical column to plot that we want to see the evolution of
+            which helps us understanding the behavior of the target column.
         """
         self.visualizations.plot_target_balance()
-        self.visualizations.plot_target_evolution("scheduled_at", "min_balance_3m")
+        self.visualizations.plot_target_evolution(time_column, evolving_numeric)
 
     def plot_numerical_distributions(self, sub_plots: bool = False):
         """
@@ -232,7 +240,7 @@ class EDAToolkit:
         """
         self.visualizations.plot_categorical_value_counts()
         self.visualizations.visualize_high_cardinality(
-            excluded_vars=self.exclusion, id_column=self.id_column
+            excluded_columns=self.exclusion, id_column=self.id_column
         )
         self.visualizations.visualize_low_cardinality()
 
@@ -377,7 +385,7 @@ class EDAToolkit:
         """
         _, filtered_cramers = self.univariate_analysis.plot_cramers_v(
             self.numerical_columns,
-            excluded_vars=self.exclusion,
+            excluded_columns=self.exclusion,
             filter_threshold=threshold_c,
         )
 

{classifier_toolkit-0.1.3 → classifier_toolkit-0.1.4}/classifier_toolkit/eda/feature_engineering.py

@@ -364,9 +364,11 @@ class FeatureEngineering:
                 raise ValueError(f"Column {column} not found in transformed data")
 
         self.data = updated_data
-        self._log_transformation(
-            "apply_transformations", {"columns_to_keep": columns_to_keep}
-        )
+
+        for transform in self.transformations:
+            if transform["method"] == "normality_transform":
+                transform["selected_columns"] = columns_to_keep
+
         return self.data
 
     def handle_high_cardinality(
@@ -990,7 +992,10 @@ class FeatureEngineering:
 
         self.data = data
         self.data.info()
-        self._log_transformation("encoding_categorical", {"method": method})
+        self._log_transformation(
+            "encoding_categorical",
+            {"method": method, "selected_columns": self.encode_list},
+        )
         return self.data
 
     ####### FEATURE ENGINEERING: OPTIONAL FUNCTIONS #######
@@ -1264,47 +1269,3 @@ class FeatureEngineering:
         return self.data
 
     percentile_capping = apply_winsorization
-
-
-'''
-    def apply_winsorization(
-        self, selected_columns: List[str], percentile: float = 0.05
-    ) -> pd.DataFrame:
-        """
-        Apply winsorization to numerical columns to limit extreme values.
-
-        Parameters
-        ----------
-        selected_columns : List[str]
-            List of columns to apply winsorization to.
-        percentile : float, optional
-            The percentage of data to be considered as extreme values on each side, by default 0.05.
-
-        Returns
-        -------
-        pd.DataFrame
-            DataFrame with winsorized columns.
-        """
-        if len(selected_columns) == 0:
-            selected_columns = self.numerical_columns
-
-        for column in selected_columns:
-            if column == self.target_column:
-                print(f"{column} is the target column. Skipping winsorization.")
-                continue
-
-            lower_bound = np.percentile(self.data[column], percentile * 100)
-            upper_bound = np.percentile(self.data[column], (1 - percentile) * 100)
-            self.data[column] = np.clip(self.data[column], lower_bound, upper_bound)
-
-        print(f"\nWinsorization applied with {percentile * 100}% capping on each side.")
-        print(self.data[selected_columns].describe())
-
-        self._log_transformation(
-            "winsorization",
-            {"selected_columns": selected_columns, "percentile": percentile},
-        )
-        return self.data
-
-    percentile_capping = apply_winsorization
-'''

{classifier_toolkit-0.1.3 → classifier_toolkit-0.1.4}/classifier_toolkit/eda/first_glance.py

@@ -112,7 +112,7 @@ values in more detail, please call the see_duplicates method
         top_n : int, optional
             Number of top values to display, by default 10.
         """
-        for col in self.columns:
+        for col in self.categorical_columns:
             print(Fore.GREEN + f"\nColumn: {col}")
             value_counts = self.data[col].value_counts().head(top_n)
             for value, count in value_counts.items():

{classifier_toolkit-0.1.3 → classifier_toolkit-0.1.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "classifier-toolkit"
-version = "0.1.3"
+version = "0.1.4"
 description = ""
 authors = [
     "gauthier.marquand <gauthier.marquand@qonto.com>",