dragon-ml-toolbox 12.0.0__py3-none-any.whl → 12.1.0__py3-none-any.whl

{dragon_ml_toolbox-12.0.0.dist-info → dragon_ml_toolbox-12.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 12.0.0
+Version: 12.1.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: "Karl L. Loza Vidaurre" <luigiloza@gmail.com>
 License-Expression: MIT
@@ -8,7 +8,7 @@ Project-URL: Homepage, https://github.com/DrAg0n-BoRn/ML_tools
 Project-URL: Changelog, https://github.com/DrAg0n-BoRn/ML_tools/blob/master/CHANGELOG.md
 Classifier: Programming Language :: Python :: 3
 Classifier: Operating System :: OS Independent
-Requires-Python: ==3.12
+Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
 License-File: LICENSE-THIRD-PARTY.md

{dragon_ml_toolbox-12.0.0.dist-info → dragon_ml_toolbox-12.1.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-12.0.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-12.0.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
+dragon_ml_toolbox-12.1.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-12.1.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
 ml_tools/ETL_cleaning.py,sha256=PLRSR-VYnt1nNT9XrcWq40SE0VzHCw7DQ8v9czfSQsU,20366
 ml_tools/ETL_engineering.py,sha256=l0I6Og9o4s6EODdk0kZXjbbC-a3vVPYy1FopP2BkQSQ,54909
 ml_tools/GUI_tools.py,sha256=Va6ig-dHULPVRwQYYtH3fvY5XPIoqRcJpRW8oXC55Hw,45413
@@ -10,8 +10,9 @@ ml_tools/ML_evaluation.py,sha256=tLswOPgH4G1KExSMn0876YtNkbxPh-W3J4MYOjomMWA,162
 ml_tools/ML_evaluation_multi.py,sha256=6OZyQ4SM9ALh38mOABmiHgIQDWcovsD_iOo7Bg9YZCE,12516
 ml_tools/ML_inference.py,sha256=ymFvncFsU10PExq87xnEj541DKV5ck0nMuK8ToJHzVQ,23067
 ml_tools/ML_models.py,sha256=pSCV6KbmVnPZr49Kbyg7g25CYaWBWJr6IinBHKgVKGw,28042
-ml_tools/ML_optimization.py,sha256=r1lAQiztTtRuh13rWj1iqbXvWO0LCqbzlkRdy3gEWo4,18124
+ml_tools/ML_optimization.py,sha256=TfVccKfZ_W6BgraZZ01-SNcNgGuViPozWLezBY8mBIg,20466
 ml_tools/ML_scaler.py,sha256=tw6onj9o8_kk3FQYb930HUzvv1zsFZe2YZJdF3LtHkU,7538
+ml_tools/ML_simple_optimization.py,sha256=X96zX6XPu3ggrcOapuG69jsiZJczJNihS1rcwi9OsBI,18159
 ml_tools/ML_trainer.py,sha256=_g48w5Ak-wQr5fGHdJqlcpnzv3gWyL1ghkOhy9VOZbo,23930
 ml_tools/ML_utilities.py,sha256=35DfZzAwfDwVwfRECD8X_2ynsU2NCpTdNJSmza6oAzQ,8712
 ml_tools/PSO_optimization.py,sha256=fVHeemqilBS0zrGV25E5yKwDlGdd2ZKa18d8CZ6Q6Fk,22961
@@ -23,18 +24,18 @@ ml_tools/_logger.py,sha256=dlp5cGbzooK9YSNSZYB4yjZrOaQUGW8PTrM411AOvL8,4717
 ml_tools/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
 ml_tools/constants.py,sha256=3br5Rk9cL2IUo638eJuMOGdbGQaWssaUecYEvSeRBLM,3322
 ml_tools/custom_logger.py,sha256=OZqG7FR_UE6byzY3RDmlj08a336ZU-4DzNBMPLr_d5c,5881
-ml_tools/data_exploration.py,sha256=qpRUCQEVUmkxjx7DAztT6yIdI___xNV5NVPMBqCp3Mk,38870
+ml_tools/data_exploration.py,sha256=is9P4c4orIKW6gRhTeScZlCGYH9ODguxMtVlrVubb4E,42515
 ml_tools/ensemble_evaluation.py,sha256=FGHSe8LBI8_w8LjNeJWOcYQ1UK_mc6fVah8gmSvNVGg,26853
 ml_tools/ensemble_inference.py,sha256=0yLmLNj45RVVoSCLH1ZYJG9IoAhTkWUqEZmLOQTFGTY,9348
 ml_tools/ensemble_learning.py,sha256=aTPeKthO4zRWBEaQJOUj8jEqVHiHjjOMXuiEWjI9NxM,21946
 ml_tools/handle_excel.py,sha256=pfdAPb9ywegFkM9T54bRssDOsX-K7rSeV0RaMz7lEAo,14006
 ml_tools/keys.py,sha256=FDpbS3Jb0pjrVvvp2_8nZi919mbob_-xwuy5OOtKM_A,1848
-ml_tools/math_utilities.py,sha256=CUkyBuExFOnEHp9J1Xsh6H4xILwYOBilwFccM9J_Dxo,7870
-ml_tools/optimization_tools.py,sha256=P3I6lIpvZ8Xf2kX5FvvBKBmrK2pB6idBpkTzfUJxTeE,5073
+ml_tools/math_utilities.py,sha256=PxoOrnuj6Ntp7_TJqyDWi0JX03WpAO5iaFNK2Oeq5I4,8800
+ml_tools/optimization_tools.py,sha256=bkKrTjukNOpxgVDMW5mUX5vQ72ckBcS5VA4eG8uZsOI,13515
 ml_tools/path_manager.py,sha256=CyDU16pOKmC82jPubqJPT6EBt-u-3rGVbxyPIZCvDDY,18432
 ml_tools/serde.py,sha256=k0qAwfMf13lVBQSgq5u9MSXEoo31iOA2-Ncm8XgMCMI,3974
 ml_tools/utilities.py,sha256=gef62GLK7ev5BWkkQekeJoVZqwf2mIuOlOfyCw6WdtE,13882
-dragon_ml_toolbox-12.0.0.dist-info/METADATA,sha256=piCOJTB5V7QKGXqbYiu3GjdNLeyrpzV-42tIxVxBRBU,6166
-dragon_ml_toolbox-12.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-12.0.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-12.0.0.dist-info/RECORD,,
+dragon_ml_toolbox-12.1.0.dist-info/METADATA,sha256=PJbBSG9h6juu_srL07VVhgOIGqebQwn_rlI1RgZdTwo,6166
+dragon_ml_toolbox-12.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-12.1.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-12.1.0.dist-info/RECORD,,

ml_tools/ML_optimization.py

@@ -5,7 +5,7 @@ import evotorch
 from evotorch.algorithms import SNES, CEM, GeneticAlgorithm
 from evotorch.logging import PandasLogger
 from evotorch.operators import SimulatedBinaryCrossOver, GaussianMutation
-from typing import Literal, Union, Tuple, List, Optional, Any, Callable
+from typing import Literal, Union, Tuple, List, Optional, Any, Callable, Dict
 from pathlib import Path
 from tqdm.auto import trange
 from contextlib import nullcontext
@@ -19,7 +19,7 @@ from .keys import PyTorchInferenceKeys
 from .SQL import DatabaseManager
 from .optimization_tools import _save_result
 from .utilities import save_dataframe
-from .math_utilities import threshold_binary_values
+from .math_utilities import discretize_categorical_values
 
 
 __all__ = [
@@ -39,15 +39,23 @@ class MLOptimizer:
     SNES and CEM algorithms do not accept bounds, the given bounds will be used as an initial starting point.
 
     Example:
-        >>> # 1. Initialize the optimizer with model and search parameters
+        >>> # 1. Get categorical info from preprocessing steps
+        >>> # e.g., from data_exploration.encode_categorical_features
+        >>> cat_mappings = {'feature_C': {'A': 0, 'B': 1}, 'feature_D': {'X': 0, 'Y': 1}}
+        >>> # e.g., from data_exploration.create_transformer_categorical_map
+        >>> # Assumes feature_C is at index 2 (cardinality 2) and feature_D is at index 3 (cardinality 2)
+        >>> cat_index_map = {2: 2, 3: 2}
+        >>>
+        >>> # 2. Initialize the optimizer
         >>> optimizer = MLOptimizer(
         ...     inference_handler=my_handler,
-        ...     bounds=(lower_bounds, upper_bounds),
-        ...     number_binary_features=2,
+        ...     bounds=(lower_bounds, upper_bounds), # Bounds for ALL features
         ...     task="max",
-        ...     algorithm="Genetic"
+        ...     algorithm="Genetic",
+        ...     categorical_index_map=cat_index_map,
+        ...     categorical_mappings=cat_mappings,
         ... )
-        >>> # 2. Run the optimization and save the results
+        >>> # 3. Run the optimization
         >>> best_result = optimizer.run(
         ...     num_generations=100,
         ...     target_name="my_target",
@@ -59,35 +67,43 @@ class MLOptimizer:
     def __init__(self,
                  inference_handler: PyTorchInferenceHandler,
                  bounds: Tuple[List[float], List[float]],
-                 number_binary_features: int,
                  task: Literal["min", "max"],
                  algorithm: Literal["SNES", "CEM", "Genetic"] = "Genetic",
                  population_size: int = 200,
+                 categorical_index_map: Optional[Dict[int, int]] = None,
+                 categorical_mappings: Optional[Dict[str, Dict[str, int]]] = None,
+                 discretize_start_at_zero: bool = True,
                  **searcher_kwargs):
         """
         Initializes the optimizer by creating the EvoTorch problem and searcher.
 
         Args:
             inference_handler (PyTorchInferenceHandler): An initialized inference handler containing the model and weights.
-            bounds (tuple[list[float], list[float]]): A tuple containing the lower and upper bounds for the solution features.
-            number_binary_features (int): Number of binary features located at the END of the feature vector.
+            bounds (tuple[list[float], list[float]]): A tuple containing the lower and upper bounds for ALL solution features. 
+                Use the `optimization_tools.create_optimization_bounds()` helper to easily generate this and ensure unbiased categorical bounds.
             task (str): The optimization goal, either "min" or "max".
             algorithm (str): The search algorithm to use ("SNES", "CEM", "Genetic").
             population_size (int): Population size for CEM and GeneticAlgorithm.
+            categorical_index_map (Dict[int, int] | None): Used to discretize values after optimization. Maps {column_index: cardinality}.
+            categorical_mappings (Dict[str, Dict[str, int]] | None): Used to map discrete integer values back to strings (e.g., {0: 'Category_A'}) before saving.
+            discretize_start_at_zero (bool): 
+                True if the discrete encoding starts at 0 (e.g., [0, 1, 2]).
+                False if it starts at 1 (e.g., [1, 2, 3]).
             **searcher_kwargs: Additional keyword arguments for the selected search algorithm's constructor.
         """
         # Call the existing factory function to get the problem and searcher factory
         self.problem, self.searcher_factory = create_pytorch_problem(
             inference_handler=inference_handler,
             bounds=bounds,
-            binary_features=number_binary_features,
             task=task,
             algorithm=algorithm,
             population_size=population_size,
             **searcher_kwargs
         )
-        # Store binary_features count to pass it to the run function later
-        self._binary_features = number_binary_features
+        # Store categorical info to pass to the run function
+        self.categorical_map = categorical_index_map
+        self.categorical_mappings = categorical_mappings
+        self.discretize_start_at_zero = discretize_start_at_zero
 
     def run(self,
             num_generations: int,
@@ -104,7 +120,8 @@ class MLOptimizer:
             num_generations (int): The total number of generations for each repetition.
             target_name (str): Target name used for the CSV filename and/or SQL table.
             save_dir (str | Path): The directory where result files will be saved.
-            feature_names (List[str] | None): Names of the solution features for labeling output. If None, generic names like 'feature_0', 'feature_1', ... , will be created.
+            feature_names (List[str] | None): Names of the solution features for labeling output.
+                If None, generic names like 'feature_0', 'feature_1', ... , will be created.
             save_format (Literal['csv', 'sqlite', 'both']): The format for saving results.
             repetitions (int): The number of independent times to run the optimization.
             verbose (bool): If True, enables detailed logging.
@@ -112,25 +129,26 @@ class MLOptimizer:
         Returns:
             Optional[dict]: A dictionary with the best result if repetitions is 1, otherwise None.
         """
-        # Call the existing run function with the stored problem, searcher, and binary feature count
+        # Call the existing run function with the stored problem, searcher, and categorical info
         return run_optimization(
             problem=self.problem,
             searcher_factory=self.searcher_factory,
             num_generations=num_generations,
             target_name=target_name,
-            binary_features=self._binary_features,
             save_dir=save_dir,
             save_format=save_format,
             feature_names=feature_names,
             repetitions=repetitions,
-            verbose=verbose
+            verbose=verbose,
+            categorical_map=self.categorical_map,
+            categorical_mappings=self.categorical_mappings,
+            discretize_start_at_zero=self.discretize_start_at_zero
         )
 
 
 def create_pytorch_problem(
     inference_handler: PyTorchInferenceHandler,
     bounds: Tuple[List[float], List[float]],
-    binary_features: int,
     task: Literal["min", "max"],
     algorithm: Literal["SNES", "CEM", "Genetic"] = "Genetic",
     population_size: int = 200,
@@ -146,7 +164,7 @@ def create_pytorch_problem(
     Args:
         inference_handler (PyTorchInferenceHandler): An initialized inference handler containing the model and weights.
         bounds (tuple[list[float], list[float]]): A tuple containing the lower and upper bounds for the solution features.
-        binary_features (int): Number of binary features located at the END of the feature vector. Will be automatically added to the bounds.
+            Use the `optimization_tools.create_optimization_bounds()` helper to easily generate this and ensure unbiased categorical bounds.
         task (str): The optimization goal, either "minimize" or "maximize".
         algorithm (str): The search algorithm to use.
         population_size (int): Used for CEM and GeneticAlgorithm.
@@ -161,11 +179,6 @@ def create_pytorch_problem(
     lower_bounds = list(bounds[0])
     upper_bounds = list(bounds[1])
     
-    # add binary bounds
-    if binary_features > 0:
-        lower_bounds.extend([0.48] * binary_features)
-        upper_bounds.extend([0.52] * binary_features)
-    
     solution_length = len(lower_bounds)
     device = inference_handler.device
 
@@ -242,12 +255,14 @@ def run_optimization(
     searcher_factory: Callable[[],Any],
     num_generations: int,
     target_name: str,
-    binary_features: int,
     save_dir: Union[str, Path],
     save_format: Literal['csv', 'sqlite', 'both'],
     feature_names: Optional[List[str]],
     repetitions: int = 1,
-    verbose: bool = True
+    verbose: bool = True,
+    categorical_map: Optional[Dict[int, int]] = None,
+    categorical_mappings: Optional[Dict[str, Dict[str, int]]] = None,
+    discretize_start_at_zero: bool = True
 ) -> Optional[dict]:
     """
     Runs the evolutionary optimization process, with support for multiple repetitions.
@@ -270,7 +285,6 @@ def run_optimization(
         searcher_factory (Callable): The searcher factory to generate fresh evolutionary algorithms.
         num_generations (int): The total number of generations to run the search algorithm for in each repetition.
         target_name (str): Target name that will also be used for the CSV filename and SQL table.
-        binary_features (int): Number of binary features located at the END of the feature vector.
         save_dir (str | Path): The directory where the result file(s) will be saved.
         save_format (Literal['csv', 'sqlite', 'both'], optional): The format for
             saving results during iterative analysis.
@@ -280,13 +294,18 @@ def run_optimization(
         repetitions (int, optional): The number of independent times to run the
             entire optimization process.
         verbose (bool): Add an Evotorch Pandas logger saved as a csv. Only for the first repetition.
+        categorical_index_map (Dict[int, int] | None): Used to discretize values after optimization. Maps {column_index: cardinality}.
+        categorical_mappings (Dict[str, Dict[str, int]] | None): Used to map discrete integer values back to strings (e.g., {0: 'Category_A'}) before saving.
+        discretize_start_at_zero (bool): 
+            True if the discrete encoding starts at 0 (e.g., [0, 1, 2]).
+            False if it starts at 1 (e.g., [1, 2, 3]).
 
     Returns:
         Optional[dict]: A dictionary containing the best feature values and the
         fitness score if `repetitions` is 1. Returns `None` if `repetitions`
         is greater than 1, as results are streamed to files instead.
     """
-    # preprocess paths
+    # --- 1. Setup Paths and Feature Names ---
     save_path = make_fullpath(save_dir, make=True, enforce="directory")
     
     sanitized_target_name = sanitize_filename(target_name)
@@ -294,54 +313,38 @@ def run_optimization(
         sanitized_target_name = sanitized_target_name + ".csv"
     
     csv_path = save_path / sanitized_target_name
-    
     db_path = save_path / "Optimization.db"
     db_table_name = target_name
     
-    # preprocess feature names
+    # Use problem's solution_length to create default names if none provided
     if feature_names is None:
-        feature_names = [f"feature_{i}" for i in range(problem.solution_length)] # type: ignore
+        feat_len = problem.solution_length
+        feature_names = [f"feature_{i}" for i in range(feat_len)] # type: ignore
     
+    # --- 2. Run Optimization ---
     # --- SINGLE RUN LOGIC ---
     if repetitions <= 1:
-        searcher = searcher_factory()
-        _LOGGER.info(f"🤖 Starting optimization with {searcher.__class__.__name__} Algorithm for {num_generations} generations...")
-        # for _ in trange(num_generations, desc="Optimizing"):
-        #     searcher.step()
-        
-        # Attach logger if requested
-        if verbose:
-            pandas_logger = PandasLogger(searcher)
-            
-        searcher.run(num_generations) # Use the built-in run method for simplicity
-            
-        # # DEBUG new searcher objects
-        # for status_key in searcher.iter_status_keys():
-        #     print("===", status_key, "===")
-        #     print(searcher.status[status_key])
-        #     print()
+        _LOGGER.info(f"🤖 Starting optimization for {num_generations} generations...")
         
-        # Get results from the .status dictionary 
-        # SNES and CEM use the key 'center' to get mean values if needed    best_solution_tensor = searcher.status["center"]
-        best_solution_container = searcher.status["pop_best"]
-        best_solution_tensor = best_solution_container.values
-        best_fitness = best_solution_container.evals
-
-        best_solution_np = best_solution_tensor.cpu().numpy()
-        
-        # threshold binary features
-        if binary_features > 0:
-            best_solution_thresholded = threshold_binary_values(input_array=best_solution_np, binary_values=binary_features)
-        else:
-            best_solution_thresholded = best_solution_np
-
-        result_dict = {name: value for name, value in zip(feature_names, best_solution_thresholded)}
-        result_dict[target_name] = best_fitness.item()
+        result_dict, pandas_logger = _run_single_optimization_rep(
+            searcher_factory=searcher_factory,
+            num_generations=num_generations,
+            feature_names=feature_names,
+            target_name=target_name,
+            categorical_map=categorical_map,
+            discretize_start_at_zero=discretize_start_at_zero,
+            attach_logger=verbose
+        )
         
-        _save_result(result_dict, 'csv', csv_path) # Single run defaults to CSV
+        # Single run defaults to CSV, pass mappings for reverse mapping
+        _save_result(
+            result_dict=result_dict, 
+            save_format='csv', 
+            csv_path=csv_path,
+            categorical_mappings=categorical_mappings
+        )
         
-        # Process logger
-        if verbose:
+        if pandas_logger:
             _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}'")
@@ -350,57 +353,106 @@ def run_optimization(
     # --- MULTIPLE REPETITIONS LOGIC ---
     else:
         _LOGGER.info(f"🏁 Starting optimal solution space analysis with {repetitions} repetitions...")
-
+        
+        first_run_logger = None # To store the logger from the first rep
         db_context = DatabaseManager(db_path) if save_format in ['sqlite', 'both'] else nullcontext()
         
         with db_context as db_manager:
+            # --- Setup Database Schema (if applicable) ---
             if db_manager:
-                schema = {name: "REAL" for name in feature_names}
+                schema = {}
+                categorical_cols = set(categorical_mappings.keys()) if categorical_mappings else set()
+                
+                for name in feature_names:
+                    schema[name] = "TEXT" if name in categorical_cols else "REAL"
                 schema[target_name] = "REAL"
+                
                 db_manager.create_table(db_table_name, schema)
             
+            # --- Repetitions Loop ---
             print("")
-            # Repetitions loop
-            pandas_logger = None
             for i in trange(repetitions, desc="Repetitions"):
-                # CRITICAL: Create a fresh searcher for each run using the factory
-                searcher = searcher_factory()
-                
-                # Attach logger if requested
-                if verbose and i==0:
-                    pandas_logger = PandasLogger(searcher)
                 
-                searcher.run(num_generations) # Use the built-in run method for simplicity
+                # Only attach a logger for the first repetition if verbose
+                attach_logger = verbose and (i == 0)
                 
-                # Get results from the .status dictionary 
-                # SNES and CEM use the key 'center' to get mean values if needed    best_solution_tensor = searcher.status["center"]
-                best_solution_container = searcher.status["pop_best"]
-                best_solution_tensor = best_solution_container.values
-                best_fitness = best_solution_container.evals
-             
-                best_solution_np = best_solution_tensor.cpu().numpy()
+                result_dict, pandas_logger = _run_single_optimization_rep(
+                    searcher_factory=searcher_factory,
+                    num_generations=num_generations,
+                    feature_names=feature_names,
+                    target_name=target_name,
+                    categorical_map=categorical_map,
+                    discretize_start_at_zero=discretize_start_at_zero,
+                    attach_logger=attach_logger
+                )
                 
-                # threshold binary features
-                if binary_features > 0:
-                    best_solution_thresholded = threshold_binary_values(input_array=best_solution_np, binary_values=binary_features)
-                else:
-                    best_solution_thresholded = best_solution_np
-                
-                # make results dictionary
-                result_dict = {name: value for name, value in zip(feature_names, best_solution_thresholded)}
-                result_dict[target_name] = best_fitness.item()
+                if pandas_logger:
+                    first_run_logger = pandas_logger
                 
                 # Save each result incrementally
-                _save_result(result_dict, save_format, csv_path, db_manager, db_table_name)
+                _save_result(
+                    result_dict=result_dict, 
+                    save_format=save_format, 
+                    csv_path=csv_path, 
+                    db_manager=db_manager, 
+                    db_table_name=db_table_name, 
+                    categorical_mappings=categorical_mappings
+                )
             
-        # Process logger
-        if pandas_logger is not None:
-            _handle_pandas_log(pandas_logger, save_path=save_path, target_name=target_name)      
+        if first_run_logger:
+            _handle_pandas_log(first_run_logger, save_path=save_path, target_name=target_name)      
         
         _LOGGER.info(f"Optimal solution space complete. Results saved to '{save_path}'")
         return None
 
 
+def _run_single_optimization_rep(
+    searcher_factory: Callable[[],Any],
+    num_generations: int,
+    feature_names: List[str],
+    target_name: str,
+    categorical_map: Optional[Dict[int, int]],
+    discretize_start_at_zero: bool,
+    attach_logger: bool
+) -> Tuple[dict, Optional[PandasLogger]]:
+    """
+    Internal helper to run one full optimization repetition.
+    
+    Handles searcher creation, logging, running, and result post-processing.
+    """
+    # CRITICAL: Create a fresh searcher for each run using the factory
+    searcher = searcher_factory()
+    
+    # Attach logger if requested
+    pandas_logger = PandasLogger(searcher) if attach_logger else None
+    
+    # Run the optimization
+    searcher.run(num_generations)
+    
+    # Get the best result
+    best_solution_container = searcher.status["pop_best"]
+    best_solution_tensor = best_solution_container.values
+    best_fitness = best_solution_container.evals
+ 
+    best_solution_np = best_solution_tensor.cpu().numpy()
+    
+    # Discretize categorical/binary features
+    if categorical_map:
+        best_solution_thresholded = discretize_categorical_values(
+            input_array=best_solution_np,
+            categorical_info=categorical_map,
+            start_at_zero=discretize_start_at_zero
+        )
+    else:
+        best_solution_thresholded = best_solution_np
+    
+    # Format results into a dictionary
+    result_dict = {name: value for name, value in zip(feature_names, best_solution_thresholded)}
+    result_dict[target_name] = best_fitness.item()
+    
+    return result_dict, pandas_logger
+
+
 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 / "EvolutionLogs", filename=target_name)