dragon-ml-toolbox 1.4.3__tar.gz → 1.4.4__tar.gz

{dragon_ml_toolbox-1.4.3/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-1.4.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 1.4.3
+Version: 1.4.4
 Summary: A collection of tools for data science and machine learning projects
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-1.4.3 → dragon_ml_toolbox-1.4.4/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 1.4.3
+Version: 1.4.4
 Summary: A collection of tools for data science and machine learning projects
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-1.4.3 → dragon_ml_toolbox-1.4.4}/ml_tools/MICE_imputation.py

@@ -36,9 +36,9 @@ def apply_mice(df: pd.DataFrame, df_name: str, resulting_datasets: int=1, iterat
         raise ValueError("No imputed datasets were generated. Check the MICE process.")
     
     if resulting_datasets == 1:
-        imputed_dataset_names = [f"{df_name}_imputed"]
+        imputed_dataset_names = [f"{df_name}_MICE"]
     else:
-        imputed_dataset_names = [f"{df_name}_imputed_{i+1}" for i in range(resulting_datasets)]
+        imputed_dataset_names = [f"{df_name}_MICE_{i+1}" for i in range(resulting_datasets)]
     
     # Ensure indexes match
     for imputed_df, subname in zip(imputed_datasets, imputed_dataset_names):

{dragon_ml_toolbox-1.4.3 → dragon_ml_toolbox-1.4.4}/ml_tools/VIF_factor.py

@@ -26,6 +26,7 @@ def compute_vif(
     filename: Optional[str] = None,
     fontsize: int = 14,
     show_plot: bool = True,
+    verbose: bool = True
 ) -> pd.DataFrame:
     """
     Computes Variance Inflation Factors (VIF) for numeric columns in a DataFrame. Optionally, generates a bar plot of VIF values.
@@ -52,19 +53,20 @@ def compute_vif(
     if use_columns is None:
         sanitized_columns = df.select_dtypes(include='number').columns.tolist()
         missing_features = set(ground_truth_cols) - set(sanitized_columns)
-        if missing_features:
+        if missing_features and verbose:
             print(f"⚠️ These columns are not Numeric:\n{missing_features}")
     else:
         sanitized_columns = list()
         for feature in use_columns:
             if feature not in ground_truth_cols:
-                print(f"⚠️ The provided column '{feature}' is not in the DataFrame.")
+                if verbose:
+                    print(f"⚠️ The provided column '{feature}' is not in the DataFrame.")
             else:
                 sanitized_columns.append(feature)
     
     if ignore_columns is not None and use_columns is None:
         missing_ignore = set(ignore_columns) - set(ground_truth_cols)
-        if missing_ignore:
+        if missing_ignore and verbose:
             print(f"⚠️ Warning: The following 'columns to ignore' are not in the Dataframe:\n{missing_ignore}")
         sanitized_columns = [f for f in sanitized_columns if f not in ignore_columns]
 
@@ -182,7 +184,7 @@ def compute_vif_multi(input_directory: str,
                       max_features_to_plot: int = 20,
                       fontsize: int = 14):
     """
-    Computes Variance Inflation Factors (VIF) for numeric columns in a directory with CSV files (loaded as pandas DataFrames). 
+    Computes Variance Inflation Factors (VIF) for numeric columns in a directory with CSV files (loaded as pandas DataFrames). No plots or warnings will be displayed inline.
     Generates a bar plot of VIF values. Optionally drops columns with VIF >= 10 and saves as a new CSV file.
 
     Args:
@@ -210,10 +212,11 @@ def compute_vif_multi(input_directory: str,
                             fontsize=fontsize,
                             save_dir=output_plot_directory,
                             filename=df_name,
-                            show_plot=False)
+                            show_plot=False,
+                            verbose=False)
         
         if output_dataset_directory is not None:
-            new_filename = 'VIF_' + df_name
+            new_filename = df_name + '_VIF'
             result_df, dropped_cols = drop_vif_based(df=df, vif_df=vif_dataframe)
             
             if len(dropped_cols) > 0:

{dragon_ml_toolbox-1.4.3 → dragon_ml_toolbox-1.4.4}/ml_tools/data_exploration.py

@@ -153,7 +153,7 @@ def drop_columns_with_missing_data(df: pd.DataFrame, threshold: float = 0.7, sho
         
         result_df = df.drop(columns=cols_to_drop)
         if show_nulls_after:
-            show_null_columns(df=result_df).head(20)
+            print(show_null_columns(df=result_df))
         
         return result_df
     else:
@@ -259,7 +259,7 @@ def plot_correlation_heatmap(df: pd.DataFrame, save_dir: Union[str, None] = None
         os.makedirs(save_dir, exist_ok=True)
         full_path = os.path.join(save_dir, plot_title + ".svg")
         plt.savefig(full_path, bbox_inches="tight", format='svg')
-        print(f"Saved correlation heatmap to: {full_path}")
+        print(f"Saved correlation heatmap: '{plot_title}.svg'")
     
     plt.show()
     plt.close()
@@ -521,7 +521,8 @@ def clip_outliers_multi(
 
 def distribute_datasets_by_target(
     df: pd.DataFrame,
-    target_columns: list[str]
+    target_columns: list[str],
+    verbose: bool = False
 ) -> Iterator[Tuple[str, pd.DataFrame]]:
     """
     Yields cleaned DataFrames for each target column, where rows with missing
@@ -533,6 +534,8 @@ def distribute_datasets_by_target(
         Preprocessed dataframe with all feature and target columns ready to train.
     target_columns : List[str]
         List of target column names to generate per-target DataFrames.
+    verbose: bool
+        Whether to print info for each yielded dataset.
 
     Yields
     ------
@@ -540,10 +543,13 @@ def distribute_datasets_by_target(
         * First element is the target column name.
         * Second element is the corresponding cleaned DataFrame.
     """
-    feature_columns = [col for col in df.columns if col not in target_columns]
+    valid_targets = [col for col in df.columns if col in target_columns]
+    feature_columns = [col for col in df.columns if col not in valid_targets]
 
-    for target in target_columns:
+    for target in valid_targets:
         subset = df[feature_columns + [target]].dropna(subset=[target])
+        if verbose:
+            print(f"Target: '{target}' - Dataframe shape: {subset.shape}")
         yield target, subset
 
 

{dragon_ml_toolbox-1.4.3 → dragon_ml_toolbox-1.4.4}/ml_tools/ensemble_learning.py

@@ -157,9 +157,7 @@ class RegressionTreeModels:
         self.gamma = gamma
 
         # LightGBM specific
-        if num_leaves >= (2**max_depth):
-            num_leaves = (2**max_depth) - 1
-            print(f"⚠️ Warning: 'num_leaves' should be set proportional to 'max_depth'. Value set as {num_leaves}.")
+        num_leaves = min(num_leaves, 2 ** (max_depth - 1))
         self.num_leaves = num_leaves
         self.min_data_in_leaf = min_data_in_leaf
 
@@ -202,7 +200,7 @@ class RegressionTreeModels:
             verbose=-1,
             reg_alpha=self.L1,
             reg_lambda=self.L2,
-            boosting_type='dart',
+            boosting_type='gbdt',
             num_leaves=self.num_leaves,
             min_data_in_leaf=self.min_data_in_leaf
         )
@@ -321,9 +319,7 @@ class ClassificationTreeModels:
         self.gamma = gamma
 
         # LightGBM specific
-        if num_leaves >= (2**max_depth):
-            num_leaves = (2**max_depth) - 1
-            print(f"⚠️ Warning: 'num_leaves' should be set proportional to 'max_depth'. Value set as {num_leaves}.")
+        num_leaves = min(num_leaves, 2 ** (max_depth - 1))
         self.num_leaves = num_leaves
         self.min_data_in_leaf = min_data_in_leaf
 
@@ -370,7 +366,7 @@ class ClassificationTreeModels:
             verbose=-1,
             reg_alpha=self.L1,
             reg_lambda=self.L2,
-            boosting_type='dart' if self.use_model_balance else 'goss',
+            boosting_type='gbdt' if self.use_model_balance else 'goss',
             num_leaves=self.num_leaves,
             min_data_in_leaf=self.min_data_in_leaf,
             class_weight='balanced' if self.use_model_balance else None

{dragon_ml_toolbox-1.4.3 → dragon_ml_toolbox-1.4.4}/ml_tools/logger.py

@@ -55,7 +55,7 @@ def custom_logger(
     """
     try:
         os.makedirs(save_directory, exist_ok=True)
-        timestamp = datetime.now().strftime(r"%Y%m%d_%H%M")
+        timestamp = datetime.now().strftime(r"%Y%m%d_%H%M%S")
         log_name = sanitize_filename(log_name)
         base_path = os.path.join(save_directory, f"{log_name}_{timestamp}")
 
@@ -80,7 +80,7 @@ def custom_logger(
         else:
             raise ValueError("Unsupported data type. Must be list, dict, DataFrame, str, or BaseException.")
 
-        print(f"Log saved to: {base_path}")
+        print(f"Log saved to: '{base_path}'")
 
     except Exception as e:
         print(f"Error in custom_logger: {e}")

{dragon_ml_toolbox-1.4.3 → dragon_ml_toolbox-1.4.4}/ml_tools/particle_swarm_optimization.py

@@ -129,10 +129,10 @@ def run_pso(lower_boundaries: list[float],
             target_name: Union[str, None]=None, 
             feature_names: Union[list[str], None]=None,
             swarm_size: int=200, 
-            max_iterations: int=1000,
+            max_iterations: int=1500,
             inequality_constrain_function=None, 
-            post_hoc_analysis: Optional[int]=3,
-            workers: int=3) -> Tuple[Dict[str, float | list[float]], Dict[str, float | list[float]]]:
+            post_hoc_analysis: Optional[int]=5,
+            workers: int=1) -> Tuple[Dict[str, float | list[float]], Dict[str, float | list[float]]]:
     """
     Executes Particle Swarm Optimization (PSO) to optimize a given objective function and saves the results as a CSV file.
 

{dragon_ml_toolbox-1.4.3 → dragon_ml_toolbox-1.4.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "1.4.3"
+version = "1.4.4"
 description = "A collection of tools for data science and machine learning projects"
 authors = [
     { name = "Karl Loza", email = "luigiloza@gmail.com" }