dragon-ml-toolbox 6.1.1__tar.gz → 6.2.0__tar.gz

{dragon_ml_toolbox-6.1.1/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-6.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 6.1.1
+Version: 6.2.0
 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-6.1.1 → dragon_ml_toolbox-6.2.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 6.1.1
+Version: 6.2.0
 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-6.1.1 → dragon_ml_toolbox-6.2.0}/ml_tools/ML_callbacks.py

@@ -201,7 +201,7 @@ class ModelCheckpoint(Callback):
         mode (str): One of {'auto', 'min', 'max'}.
         verbose (int): Verbosity mode.
     """
-    def __init__(self, save_dir: Union[str,Path], monitor: str = PyTorchLogKeys.VAL_LOSS,
+    def __init__(self, save_dir: Union[str,Path], checkpoint_name: Optional[str]=None, monitor: str = PyTorchLogKeys.VAL_LOSS,
                  save_best_only: bool = True, mode: Literal['auto', 'min', 'max']= 'auto', verbose: int = 0):
         super().__init__()
         self.save_dir = make_fullpath(save_dir, make=True, enforce="directory")
@@ -212,6 +212,7 @@ class ModelCheckpoint(Callback):
         self.monitor = monitor
         self.save_best_only = save_best_only
         self.verbose = verbose
+        self.checkpoint_name = checkpoint_name
 
         # State variables to be managed during training
         self.saved_checkpoints = []
@@ -254,7 +255,10 @@ class ModelCheckpoint(Callback):
             old_best_str = f"{self.best:.4f}" if self.best not in [np.inf, -np.inf] else "inf"
             
             # Create a descriptive filename
-            filename = f"epoch_{epoch}-{self.monitor}_{current:.4f}.pth"
+            if self.checkpoint_name is None:
+                filename = f"epoch_{epoch}-{self.monitor}_{current:.4f}.pth"
+            else:
+                filename = f"epoch{epoch}_{self.checkpoint_name}.pth"
             new_filepath = self.save_dir / filename
             
             if self.verbose > 0:
@@ -273,7 +277,11 @@ class ModelCheckpoint(Callback):
 
     def _save_rolling_checkpoints(self, epoch, logs):
         """Saves the latest model and keeps only the most recent ones."""
-        filename = f"epoch_{epoch}.pth"
+        current = logs.get(self.monitor)
+        if self.checkpoint_name is None:
+            filename = f"epoch_{epoch}-{self.monitor}_{current:.4f}.pth"
+        else:
+            filename = f"epoch{epoch}_{self.checkpoint_name}.pth"
         filepath = self.save_dir / filename
         
         if self.verbose > 0:

{dragon_ml_toolbox-6.1.1 → dragon_ml_toolbox-6.2.0}/ml_tools/ML_optimization.py

@@ -114,10 +114,10 @@ def create_pytorch_problem(
 
         operators = [
             SimulatedBinaryCrossOver(problem,
-                                    tournament_size=4,
-                                    eta=0.8),
+                                    tournament_size=3,
+                                    eta=0.6),
             GaussianMutation(problem,
-                            stdev=0.1)
+                            stdev=0.4)
         ]
         
         searcher_kwargs["operators"] = operators
@@ -240,7 +240,7 @@ def run_optimization(
         
         # Process logger
         if verbose:
-            _handle_pandas_log(pandas_logger, save_path=save_path)
+            _handle_pandas_log(pandas_logger, save_path=save_path, target_name=target_name)
         
         _LOGGER.info(f"✅ Optimization complete. Best solution saved to '{csv_path.name}'")
         return result_dict
@@ -293,15 +293,15 @@ def run_optimization(
             
         # Process logger
         if pandas_logger is not None:
-            _handle_pandas_log(pandas_logger, save_path=save_path)      
+            _handle_pandas_log(pandas_logger, save_path=save_path, target_name=target_name)      
         
         _LOGGER.info(f"✅ Optimal solution space complete. Results saved to '{save_path}'")
         return None
 
 
-def _handle_pandas_log(logger: PandasLogger, save_path: Path):
+def _handle_pandas_log(logger: PandasLogger, save_path: Path, target_name: str):
     log_dataframe = logger.to_dataframe()
-    save_dataframe(df=log_dataframe, save_dir=save_path / "EvolutionLog", filename="evolution")
+    save_dataframe(df=log_dataframe, save_dir=save_path / "EvolutionLogs", filename=target_name)
 
 
 def info():

{dragon_ml_toolbox-6.1.1 → dragon_ml_toolbox-6.2.0}/ml_tools/SQL.py

@@ -59,7 +59,7 @@ class DatabaseManager:
         try:
             self.conn = sqlite3.connect(self.db_path)
             self.cursor = self.conn.cursor()
-            _LOGGER.info(f"✅ Successfully connected to database: {self.db_path}")
+            _LOGGER.info(f"❇️ Successfully connected to database: {self.db_path}")
             return self
         except sqlite3.Error as e:
             _LOGGER.error(f"❌ Database connection failed: {e}")
@@ -99,7 +99,7 @@ class DatabaseManager:
         
         query = f"CREATE TABLE {exists_clause} {table_name} ({columns_def})"
         
-        _LOGGER.info(f"🗂️ Executing: {query}")
+        _LOGGER.info(f"➡️ Executing: {query}")
         self.cursor.execute(query)
 
     def insert_row(self, table_name: str, data: Dict[str, Any]):
@@ -192,7 +192,7 @@ class DatabaseManager:
         query = f"INSERT INTO {table_name} ({columns}) VALUES ({placeholders})"
         
         self.cursor.executemany(query, values_to_insert)
-        _LOGGER.info(f"✅ Bulk inserted {len(values_to_insert)} rows into '{table_name}'.")
+        _LOGGER.info(f"➡️ Bulk inserted {len(values_to_insert)} rows into '{table_name}'.")
         
     def insert_from_dataframe(self, table_name: str, df: pd.DataFrame, if_exists: Literal['fail', 'replace', 'append'] = 'append'):
         """
@@ -219,7 +219,7 @@ class DatabaseManager:
             if_exists=if_exists,
             index=False  # Typically, we don't want to save the DataFrame index
         )
-        _LOGGER.info(f"✅ Wrote {len(df)} rows from DataFrame to table '{table_name}' using mode '{if_exists}'.")
+        _LOGGER.info(f"➡️ Wrote {len(df)} rows from DataFrame to table '{table_name}' using mode '{if_exists}'.")
         
     def list_tables(self) -> List[str]:
         """Returns a list of all table names in the database."""
@@ -264,7 +264,7 @@ class DatabaseManager:
         
         query = f"CREATE {unique_clause} INDEX IF NOT EXISTS {index_name} ON {table_name} ({column_name})"
         
-        _LOGGER.info(f"🗂️ Executing: {query}")
+        _LOGGER.info(f"➡️ Executing: {query}")
         self.cursor.execute(query)
 
 

{dragon_ml_toolbox-6.1.1 → dragon_ml_toolbox-6.2.0}/ml_tools/optimization_tools.py

@@ -29,24 +29,24 @@ def parse_lower_upper_bounds(source: dict[str,tuple[Any,Any]]):
     return lower, upper
 
 
-def plot_optimal_feature_distributions(results_dir: Union[str, Path], save_dir: Union[str, Path]):
+def plot_optimal_feature_distributions(results_dir: Union[str, Path]):
     """
     Analyzes optimization results and plots the distribution of optimal values for each feature.
 
     For features with more than two unique values, this function generates a color-coded 
     Kernel Density Estimate (KDE) plot. For binary or constant features, it generates a bar plot
     showing relative frequency.
+    
+    Plots are saved in a subdirectory inside the source directory.
 
     Parameters
     ----------
     results_dir : str or Path
         The path to the directory containing the optimization result CSV files.
-    save_dir : str or Path
-        The directory where the output plots will be saved.
     """
     # Check results_dir and create output path
-    results_path = make_fullpath(results_dir)
-    output_path = make_fullpath(save_dir, make=True)
+    results_path = make_fullpath(results_dir, enforce="directory")
+    output_path = make_fullpath(results_path / "DistributionPlots", make=True)
     
     # Check that the directory contains csv files
     list_csv_paths(results_path, verbose=False)

{dragon_ml_toolbox-6.1.1 → dragon_ml_toolbox-6.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "6.1.1"
+version = "6.2.0"
 description = "A collection of tools for data science and machine learning projects."
 authors = [
     { name = "Karl Loza", email = "luigiloza@gmail.com" }