dragon-ml-toolbox 6.1.2__py3-none-any.whl → 6.2.1__py3-none-any.whl

{dragon_ml_toolbox-6.1.2.dist-info → dragon_ml_toolbox-6.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 6.1.2
+Version: 6.2.1
 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-6.1.2.dist-info → dragon_ml_toolbox-6.2.1.dist-info}/RECORD

@@ -1,18 +1,18 @@
-dragon_ml_toolbox-6.1.2.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-6.1.2.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
+dragon_ml_toolbox-6.2.1.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-6.2.1.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
 ml_tools/ETL_engineering.py,sha256=4wwZXi9_U7xfCY70jGBaKniOeZ0m75ppxWpQBd_DmLc,39369
 ml_tools/GUI_tools.py,sha256=n4ZZ5kEjwK5rkOCFJE41HeLFfjhpJVLUSzk9Kd9Kr_0,45410
 ml_tools/MICE_imputation.py,sha256=oFHg-OytOzPYTzBR_wIRHhP71cMn3aupDeT59ABsXlQ,11576
-ml_tools/ML_callbacks.py,sha256=FEJ80TSEtY0-hdnOsAWeVApQt1mdzTdOntqtoWmMAzE,13310
+ml_tools/ML_callbacks.py,sha256=noedVMmHZ72Odbg28zqx5wkhhvX2v-jXicKE_NCAiqU,13838
 ml_tools/ML_datasetmaster.py,sha256=bbKCNA_b_uDIfxP9YIYKZm-VSfUSD15LvegFxpE9DIQ,34315
 ml_tools/ML_evaluation.py,sha256=-Z5fXQi2ou6l5Oyir06bO90SZIZVrjQfgoVAqKgSjks,13800
 ml_tools/ML_inference.py,sha256=blEDgzvDqatxbfloBKsyNPacRwoq9g6WTpIKQ3zoTak,5758
 ml_tools/ML_models.py,sha256=SJhKHGAN2VTBqzcHUOpFWuVZ2Y7U1M4P_axG_LNYWcI,6460
-ml_tools/ML_optimization.py,sha256=BWwaco2IiYgvQbD-WoTMKtlHGh94zHBpeGHKtN51pFs,13475
+ml_tools/ML_optimization.py,sha256=GX-qZ2mCI3gWRCTP5w7lXrZpfGle3J_mE0O68seIoio,13475
 ml_tools/ML_trainer.py,sha256=1q_CDXuMfndRsPuNofUn2mg2TlhG6MYuGqjWxTDgN9c,15112
 ml_tools/PSO_optimization.py,sha256=9Y074d-B5h4Wvp9YPiy6KAeXM-Yv6Il3gWalKvOLVgo,22705
 ml_tools/RNN_forecast.py,sha256=2CyjBLSYYc3xLHxwLXUmP5Qv8AmV1OB_EndETNX1IBk,1956
-ml_tools/SQL.py,sha256=9zzS6AFEJM9aj6nE31hDe8S9TqLonk-J1amwZoiHNbk,10468
+ml_tools/SQL.py,sha256=bkSTmMV4CtEqa67hApYWaRxTqwAlKIc5_b28P1bnDwg,10475
 ml_tools/VIF_factor.py,sha256=2nUMupfUoogf8o6ghoFZk_OwWhFXU0R3C9Gj0HOlI14,10415
 ml_tools/__init__.py,sha256=q0y9faQ6e17XCQ7eUiCZ1FJ4Bg5EQqLjZ9f_l5REUUY,41
 ml_tools/_logger.py,sha256=TpgYguxO-CWYqqgLW0tqFjtwZ58PE_W2OCfWNGZr0n0,1175
@@ -24,10 +24,10 @@ ml_tools/ensemble_inference.py,sha256=rtU7eUaQne615n2g7IHZCJI-OvrBCcjxbTkEIvtCGF
 ml_tools/ensemble_learning.py,sha256=dAyFgSTyvxJWjc_enJ_8EUoWwiekBeoNyJNxVY-kcUU,21868
 ml_tools/handle_excel.py,sha256=J9iwIqMZemoxK49J5osSwp9Ge0h9YTKyYGbOm53hcno,13007
 ml_tools/keys.py,sha256=HtPG8-MWh89C32A7eIlfuuA-DLwkxGkoDfwR2TGN9CQ,1074
-ml_tools/optimization_tools.py,sha256=MuT4OG7_r1QqLUti-yYix7QeCpglezD0oe9BDCq0QXk,5086
+ml_tools/optimization_tools.py,sha256=EL5tgNFwRo-82pbRE1CFVy9noNhULD7wprWuKadPheg,5090
 ml_tools/path_manager.py,sha256=Z8e7w3MPqQaN8xmTnKuXZS6CIW59BFwwqGhGc00sdp4,13692
 ml_tools/utilities.py,sha256=LqXXTovaHbA5AOKRk6Ru6DgAPAM0wPfYU70kUjYBryo,19231
-dragon_ml_toolbox-6.1.2.dist-info/METADATA,sha256=97hB43rYNc9a-iCnyxzfRvXfo6jdpgDmnBEvthYqv1M,6698
-dragon_ml_toolbox-6.1.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-6.1.2.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-6.1.2.dist-info/RECORD,,
+dragon_ml_toolbox-6.2.1.dist-info/METADATA,sha256=acX_886jWy_IUIO9-HsSalgpD9HAh8a5Q22rbUlBzbU,6698
+dragon_ml_toolbox-6.2.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-6.2.1.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-6.2.1.dist-info/RECORD,,

ml_tools/ML_callbacks.py

@@ -1,7 +1,7 @@
 import numpy as np
 import torch
 from tqdm.auto import tqdm
-from .path_manager import make_fullpath
+from .path_manager import make_fullpath, sanitize_filename
 from .keys import PyTorchLogKeys
 from ._logger import _LOGGER
 from typing import Optional
@@ -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 +212,9 @@ class ModelCheckpoint(Callback):
         self.monitor = monitor
         self.save_best_only = save_best_only
         self.verbose = verbose
+        if checkpoint_name:
+            checkpoint_name = sanitize_filename(checkpoint_name)
+        self.checkpoint_name = checkpoint_name
 
         # State variables to be managed during training
         self.saved_checkpoints = []
@@ -254,7 +257,10 @@ 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 +279,11 @@ 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:

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

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)
 
 

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)