dragon-ml-toolbox 1.4.5__py3-none-any.whl → 1.4.7__py3-none-any.whl

{dragon_ml_toolbox-1.4.5.dist-info → dragon_ml_toolbox-1.4.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 1.4.5
+Version: 1.4.7
 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-1.4.5.dist-info → dragon_ml_toolbox-1.4.7.dist-info}/RECORD

@@ -1,19 +1,19 @@
-dragon_ml_toolbox-1.4.5.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-1.4.5.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=jDnniT0tgD0uw1NpjibsPF-qK3wmOKgTykLG2iNQU7E,1840
+dragon_ml_toolbox-1.4.7.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-1.4.7.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=jDnniT0tgD0uw1NpjibsPF-qK3wmOKgTykLG2iNQU7E,1840
 ml_tools/MICE_imputation.py,sha256=JMe9hyidJadFTHW7AHkNQ_fduTxH6CEh7_Ouy2LhCOQ,11096
 ml_tools/VIF_factor.py,sha256=HEBsLJy_qSDaPw1Btha5B7omxN4wjJXg-sqoetCjCJw,10016
 ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ml_tools/data_exploration.py,sha256=vSjqKwtmPm1RHhHdC5AWH8Edg78nTM5SowUzWG2AxdY,18951
+ml_tools/data_exploration.py,sha256=X9mYZdynRGghT06GeOdVsfGBTFa342Ko-MkMImDll-M,20123
 ml_tools/datasetmaster.py,sha256=EFUEX-tqq94Ak1rXXYR-XaX85olrxvF2EuytdzUK7y0,29131
 ml_tools/ensemble_learning.py,sha256=xJyEbkFObm5YX6DmDW10FOUjSeYeBRhHLvncWZv_uTo,37319
 ml_tools/handle_excel.py,sha256=ZJui5__0rc2T8UGHTheqZGhKmdVZ7Q2I54IoYCjAqJw,12612
 ml_tools/logger.py,sha256=ZTtUB9HTkNs5zHTdYRKNbKADjUkuObsF7s8U5pNnVRA,4716
-ml_tools/particle_swarm_optimization.py,sha256=c5TG_MnCgxzkcREkqbJHqi6x_fovikUv2ePtKFL4HL8,20193
+ml_tools/particle_swarm_optimization.py,sha256=wRk5ni6pPnh-tqS5t9M5TAjg8GUSGFxp-u09FSIviOM,22213
 ml_tools/pytorch_models.py,sha256=bpWZsrSwCvHJQkR6UfoPpElsMv9AvmiNErNHC8NYB_I,10132
 ml_tools/trainer.py,sha256=WAZ4EdrZuTOAnGXRWV3XcLNce4s7EKGf2-qchLC08Ik,15702
-ml_tools/utilities.py,sha256=6369V_8VcDBPqUBOYS6VI6JKt0-wq_xVq9voTOU6VsQ,14515
+ml_tools/utilities.py,sha256=Ir3Yw4SuWMLKnbnl4Qzudn5U8CgcQ7zMtNqcllZMHeM,15682
 ml_tools/vision_helpers.py,sha256=idQ-Ugp1IdsvwXiYyhYa9G3rTRTm37YRpkQDLEpANHM,7701
-dragon_ml_toolbox-1.4.5.dist-info/METADATA,sha256=BDFkLly4Ylq2yPdQC3T4UVFr21fWjYlNgudq_bVWk-g,2516
-dragon_ml_toolbox-1.4.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-1.4.5.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-1.4.5.dist-info/RECORD,,
+dragon_ml_toolbox-1.4.7.dist-info/METADATA,sha256=Z_ai6XNFd8a_sf9CD73kh3mgVJlgVhcajXiJhkEivsM,2516
+dragon_ml_toolbox-1.4.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-1.4.7.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-1.4.7.dist-info/RECORD,,

ml_tools/data_exploration.py

@@ -5,9 +5,10 @@ import seaborn as sns
 from IPython import get_ipython
 from IPython.display import clear_output
 import time
-from typing import Union, Literal, Dict, Tuple, Iterator
+from typing import Union, Literal, Dict, Tuple, List
 import os
 from ml_tools.utilities import sanitize_filename, _script_info
+import re
 
 
 # Keep track of all available tools, show using `info()`
@@ -22,7 +23,8 @@ __all__ = [
     "check_value_distributions", 
     "plot_value_distributions", 
     "clip_outliers_single", 
-    "clip_outliers_multi"
+    "clip_outliers_multi",
+    "match_and_filter_columns_by_regex"
 ]
 
 
@@ -245,9 +247,6 @@ def plot_correlation_heatmap(df: pd.DataFrame, save_dir: Union[str, None] = None
         cbar_kws={"shrink": 0.8}
     )
     
-    # sanitize the plot title
-    plot_title = sanitize_filename(plot_title)
-
     plt.title(plot_title)
     plt.xticks(rotation=45, ha='right')
     plt.yticks(rotation=0)
@@ -255,6 +254,8 @@ def plot_correlation_heatmap(df: pd.DataFrame, save_dir: Union[str, None] = None
     plt.tight_layout()
     
     if save_dir:
+        # sanitize the plot title to save the file
+        plot_title = sanitize_filename(plot_title)
         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')
@@ -518,6 +519,36 @@ def clip_outliers_multi(
     return new_df
 
 
+def match_and_filter_columns_by_regex(
+    df: pd.DataFrame,
+    pattern: str,
+    case_sensitive: bool = False,
+    escape_pattern: bool = False
+) -> Tuple[pd.DataFrame, List[str]]:
+    """
+    Return a tuple of (filtered DataFrame, matched column names) based on a regex pattern.
+
+    Parameters:
+        df (pd.DataFrame): The DataFrame to search.
+        pattern (str): The regex pattern to match column names (use a raw string).
+        case_sensitive (bool): Whether matching is case-sensitive.
+        escape_pattern (bool): If True, the pattern is escaped with `re.escape()` to treat it literally.
+
+    Returns:
+        (Tuple[pd.DataFrame, list[str]]): A DataFrame filtered to matched columns, and a list of matching column names.
+    """
+    if escape_pattern:
+        pattern = re.escape(pattern)
+
+    mask = df.columns.str.contains(pattern, case=case_sensitive, regex=True)
+    matched_columns = df.columns[mask].to_list()
+    filtered_df = df.loc[:, mask]
+    
+    print(f"{len(matched_columns)} column(s) match the regex pattern '{pattern}'.")
+
+    return filtered_df, matched_columns
+
+
 def _is_notebook():
     return get_ipython() is not None
 

ml_tools/particle_swarm_optimization.py

@@ -8,11 +8,13 @@ from sklearn.base import ClassifierMixin
 from typing import Literal, Union, Tuple, Dict, Optional
 import polars as pl
 from functools import partial
-from .utilities import sanitize_filename, _script_info, threshold_binary_values, deserialize_object
+from copy import deepcopy
+from .utilities import sanitize_filename, _script_info, threshold_binary_values, deserialize_object, list_files_by_extension
 
 
 __all__ = [
     "ObjectiveFunction",
+    "multiple_objective_functions_from_dir",
     "run_pso"
 ]
 
@@ -29,12 +31,12 @@ class ObjectiveFunction():
         Path to a serialized model (joblib) compatible with scikit-learn-like `.predict`. 
     add_noise : bool
         Whether to apply multiplicative noise to the input features during evaluation.
-    binary_features : int, default=0
-        Number of binary features located at the END of the feature vector. Model should be trained with continuous features first, followed by binary.
-    task : Literal, default 'maximization'
+    task : (Literal["maximization", "minimization"])
         Whether to maximize or minimize the target.
+    binary_features : int
+        Number of binary features located at the END of the feature vector. Model should be trained with continuous features first, followed by binary.
     """
-    def __init__(self, trained_model_path: str, add_noise: bool, task: Literal["maximization", "minimization"], binary_features: int=0) -> None:
+    def __init__(self, trained_model_path: str, add_noise: bool, task: Literal["maximization", "minimization"], binary_features: int) -> None:
         self.binary_features = binary_features
         self.is_hybrid = False if binary_features <= 0 else True
         self.use_noise = add_noise
@@ -96,6 +98,35 @@ class ObjectiveFunction():
         return (f"<ObjectiveFunction(model={type(self.model).__name__}, use_noise={self.use_noise}, is_hybrid={self.is_hybrid}, task='{self.task}')>")
 
 
+def multiple_objective_functions_from_dir(directory: str, add_noise: bool, task: Literal["maximization", "minimization"], binary_features: int):
+    """
+    Loads multiple objective functions from serialized models in the given directory.
+
+    Each `.joblib` file which is loaded and wrapped as an `ObjectiveFunction` instance. Returns a list of such instances along with their corresponding names.
+
+    Parameters:
+        directory (str) : Path to the directory containing `.joblib` files (serialized models).
+        add_noise (bool) : Whether to apply multiplicative noise to the input features during evaluation.
+        task (Literal["maximization", "minimization"]) : Defines the nature of the optimization task.
+        binary_features (int) : Number of binary features expected by each objective function.
+
+    Returns:
+        (tuple[list[ObjectiveFunction], list[str]]) : A tuple containing:
+            - list of `ObjectiveFunction` instances.
+            - list of corresponding filenames.
+    """
+    objective_functions = list()
+    objective_function_names = list()
+    for file_name, file_path in list_files_by_extension(directory=directory, extension='joblib').items():
+        current_objective = ObjectiveFunction(trained_model_path=file_path,
+                                              add_noise=add_noise,
+                                              task=task,
+                                              binary_features=binary_features)
+        objective_functions.append(current_objective)
+        objective_function_names.append(file_name)
+    return objective_functions, objective_function_names
+
+
 def _set_boundaries(lower_boundaries: list[float], upper_boundaries: list[float]):
     assert len(lower_boundaries) == len(upper_boundaries), "Lower and upper boundaries must have the same length."
     assert len(lower_boundaries) >= 1, "At least one boundary pair is required."
@@ -131,9 +162,9 @@ 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=1500,
+            max_iterations: int=1000,
             inequality_constrain_function=None, 
-            post_hoc_analysis: Optional[int]=5,
+            post_hoc_analysis: Optional[int]=3,
             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.
@@ -180,18 +211,25 @@ def run_pso(lower_boundaries: list[float],
     -----
     - PSO minimizes the objective function by default; if maximization is desired, it should be handled inside the ObjectiveFunction.
     """
+    # set local deep copies to prevent in place list modification
+    local_lower_boundaries = deepcopy(lower_boundaries)
+    local_upper_boundaries = deepcopy(upper_boundaries)
+    
     # Append binary boundaries
     binary_number = objective_function.binary_features
     if auto_binary_boundaries and binary_number > 0:
-        lower_boundaries.extend([0] * binary_number)
-        upper_boundaries.extend([1] * binary_number)
+        local_lower_boundaries.extend([0] * binary_number)
+        local_upper_boundaries.extend([1] * binary_number)
+        
+    # Set the total length of features
+    size_of_features = len(local_lower_boundaries)
 
-    lower, upper = _set_boundaries(lower_boundaries, upper_boundaries)
+    lower, upper = _set_boundaries(local_lower_boundaries, local_upper_boundaries)
 
     # feature names
     if feature_names is None and objective_function.feature_names is not None:
         feature_names = objective_function.feature_names
-    names = _set_feature_names(size=len(lower_boundaries), names=feature_names)
+    names = _set_feature_names(size=size_of_features, names=feature_names)
 
     # target name
     if target_name is None and objective_function.target_name is not None:
@@ -233,7 +271,7 @@ def run_pso(lower_boundaries: list[float],
         return best_features_named, best_target_named
     else:
         all_best_targets = list()
-        all_best_features = [[] for _ in range(len(lower_boundaries))]
+        all_best_features = [[] for _ in range(size_of_features)]
         for _ in range(post_hoc_analysis):
             best_features, best_target, *_ = _pso(**arguments)
             # best_features, best_target, _particle_positions, _target_values_per_position = _pso(**arguments)

ml_tools/utilities.py

@@ -13,6 +13,7 @@ from joblib.externals.loky.process_executor import TerminatedWorkerError
 # Keep track of available tools
 __all__ = [
     "list_csv_paths",
+    "list_files_by_extension",
     "load_dataframe",
     "yield_dataframes_from_dir",
     "merge_dataframes",
@@ -34,7 +35,7 @@ def list_csv_paths(directory: str) -> dict[str, str]:
         directory (str): Path to the directory containing `.csv` files.
 
     Returns:
-        (dict[str, str]): Mapping {name, path}.
+        (dict[str, str]): Dictionary mapping {filename: filepath}.
     """
     dir_path = Path(directory).expanduser().resolve()
 
@@ -48,13 +49,47 @@ def list_csv_paths(directory: str) -> dict[str, str]:
     # make a dictionary of paths and names
     name_path_dict = {p.stem: str(p) for p in csv_paths}
     
-    print("🗂️ CSV files found:")
+    print("\n🗂️ CSV files found:")
     for name in name_path_dict.keys():
         print(f"\t{name}")
 
     return name_path_dict
 
 
+def list_files_by_extension(directory: str, extension: str) -> dict[str, str]:
+    """
+    Lists all files with the specified extension in the given directory and returns a mapping: 
+    filenames (without extensions) to their absolute paths.
+
+    Parameters:
+        directory (str): Path to the directory to search in.
+        extension (str): File extension to search for (e.g., 'json', 'txt').
+
+    Returns:
+        (dict[str, str]): Dictionary mapping {filename: filepath}.
+    """
+    dir_path = Path(directory).expanduser().resolve()
+
+    if not dir_path.is_dir():
+        raise FileNotFoundError(f"Directory not found: {dir_path}")
+    
+    # Normalize the extension (remove leading dot if present)
+    normalized_ext = extension.lstrip(".").lower()
+    pattern = f"*.{normalized_ext}"
+    
+    matched_paths = list(dir_path.glob(pattern))
+    if not matched_paths:
+        raise IOError(f"No '.{normalized_ext}' files found in directory: {dir_path}")
+
+    name_path_dict = {p.stem: str(p) for p in matched_paths}
+    
+    print(f"\n📂 '{normalized_ext.upper()}' files found:")
+    for name in name_path_dict:
+        print(f"\t{name}")
+    
+    return name_path_dict
+
+
 def load_dataframe(df_path: str) -> tuple[pd.DataFrame, str]:
     """
     Load a CSV file into a pandas DataFrame and extract the base name (without extension) from the file path.
@@ -404,8 +439,8 @@ def distribute_datasets_by_target(
     Yields
     ------
     Tuple[str, pd.DataFrame]
-        * First element is the target column name.
-        * Second element is the corresponding cleaned DataFrame.
+        * Target name.
+        * Pandas DataFrame.
     """
     # Validate path
     if isinstance(df_or_path, str):