dragon-ml-toolbox 14.3.1__py3-none-any.whl → 16.0.0__py3-none-any.whl

ml_tools/path_manager.py

@@ -9,7 +9,7 @@ from ._logger import _LOGGER
 
 
 __all__ = [
-    "PathManager",
+    "DragonPathManager",
     "make_fullpath",
     "sanitize_filename",
     "list_csv_paths",
@@ -18,7 +18,7 @@ __all__ = [
 ]
 
 
-class PathManager:
+class DragonPathManager:
     """
     Manages and stores a project's file paths, acting as a centralized
     "path database". It supports both development mode and applications
@@ -43,7 +43,7 @@ class PathManager:
 
         Args:
             anchor_file (str): The path to a file within your package, typically
-                            the `__file__` of the script where PathManager
+                            the `__file__` of the script where DragonPathManager
                             is instantiated. This is used to locate the
                             package root directory.
             base_directories (List[str] | None): An optional list of strings,
@@ -149,7 +149,7 @@ class PathManager:
                 if key in self._paths:
                     path_items.append((key, self._paths[key]))
                 elif verbose:
-                    _LOGGER.warning(f"Key '{key}' not found in PathManager, skipping.")
+                    _LOGGER.warning(f"Key '{key}' not found in DragonPathManager, skipping.")
         else:
             path_items = self._paths.items()
 
@@ -194,7 +194,7 @@ class PathManager:
     def __repr__(self) -> str:
         """Provides a string representation of the stored paths."""
         path_list = "\n".join(f"  '{k}': '{v}'" for k, v in self._paths.items())
-        return f"PathManager(\n{path_list}\n)"
+        return f"DragonPathManager(\n{path_list}\n)"
     
     # --- Dictionary-Style Methods ---
     def __getitem__(self, key: str) -> Path:

ml_tools/utilities.py

@@ -10,7 +10,6 @@ from ._logger import _LOGGER
 from ._schema import FeatureSchema
 
 
-# Keep track of available tools
 __all__ = [
     "load_dataframe",
     "load_dataframe_greedy",
@@ -361,7 +360,7 @@ def save_dataframe_filename(df: Union[pd.DataFrame, pl.DataFrame], save_dir: Uni
     elif isinstance(df, pl.DataFrame):
         # Transform empty strings to Null
         df_to_save = df.with_columns(
-            pl.when(pl.col(pl.Utf8).str.strip() == "")
+            pl.when(pl.col(pl.Utf8).str.strip() == "") # type: ignore
             .then(None)
             .otherwise(pl.col(pl.Utf8))
         )

dragon_ml_toolbox-14.3.1.dist-info/RECORD

@@ -1,48 +0,0 @@
-dragon_ml_toolbox-14.3.1.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-14.3.1.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=gkOdNDbKYpIJezwSo2CEnISkLeYfYHv9t8b5K2-P69A,2687
-ml_tools/ETL_cleaning.py,sha256=2VBRllV8F-ZiPylPp8Az2gwn5ztgazN0BH5OKnRUhV0,20402
-ml_tools/ETL_engineering.py,sha256=KfYqgsxupAx6e_TxwO1LZXeu5mFkIhVXJrNjP3CzIZc,54927
-ml_tools/GUI_tools.py,sha256=Va6ig-dHULPVRwQYYtH3fvY5XPIoqRcJpRW8oXC55Hw,45413
-ml_tools/MICE_imputation.py,sha256=KLJXGQLKJ6AuWWttAG-LCCaxpS-ygM4dXPiguHDaL6Y,20815
-ml_tools/ML_callbacks.py,sha256=elD2Yr030sv_6gX_m9GVd6HTyrbmt34nFS8lrgS4HtM,15808
-ml_tools/ML_datasetmaster.py,sha256=rsJgZEGBJmfeKF6cR8CQZzfEx4T7Y-p1wUnR15_nNw0,28400
-ml_tools/ML_evaluation.py,sha256=4GU86rUWMIGbkXrvN6PyjfGwKtWvXKE7pMlWpWeBq14,18988
-ml_tools/ML_evaluation_multi.py,sha256=rJKdgtq-9I7oaI7PRzq7aIZ84XdNV0xzlVePZW4nj0k,16095
-ml_tools/ML_inference.py,sha256=YJ953bhNWsdlPRtJQh3h2ACfMIgp8dQ9KtL9Azar-5s,23489
-ml_tools/ML_models.py,sha256=PqOcNlws7vCJMbiVCKqlPuktxvskZVUHG3VfU-Yshf8,31415
-ml_tools/ML_models_advanced.py,sha256=vk3PZBSu3DVso2S1rKTxxdS43XG8Q5FnasIL3-rMajc,12410
-ml_tools/ML_optimization.py,sha256=P0zkhKAwTpkorIBtR0AOIDcyexo5ngmvFUzo3DfNO-E,22692
-ml_tools/ML_scaler.py,sha256=tw6onj9o8_kk3FQYb930HUzvv1zsFZe2YZJdF3LtHkU,7538
-ml_tools/ML_trainer.py,sha256=ZWI4MbUcLeBxyfoUTL96l5tjHHMp9I64h4SdXnjYmBE,49795
-ml_tools/ML_utilities.py,sha256=z6LbpbZwhn8F__fWlKi-g-cAJQXSxwg1NHfC5FBoAyc,21139
-ml_tools/ML_vision_datasetmaster.py,sha256=2S7stCgGQX39Y38gfMQccwAx_QTKEmmRIqh4XJ2K_YE,58041
-ml_tools/ML_vision_evaluation.py,sha256=t12R7i1RkOCt9zu1_lxSBr8OH6A6Get0k8ftDLctn6I,10486
-ml_tools/ML_vision_inference.py,sha256=He3KV3VJAm8PwO-fOq4b9VO8UXFr-GmpuCnoHXf4VZI,20588
-ml_tools/ML_vision_models.py,sha256=G3S4jB9AE9wMpU9ZygOgOx9q1K6t6LAXBYcJ-U2XQ1M,25600
-ml_tools/ML_vision_transformers.py,sha256=95e0aBkHY5VDGE8i5xy57COU7NvSNIgFknnhBubwE40,1832
-ml_tools/PSO_optimization.py,sha256=T-HWHMRJUnPvPwixdU5jif3_rnnI36TzcL8u3oSCwuA,22960
-ml_tools/RNN_forecast.py,sha256=Qa2KoZfdAvSjZ4yE78N4BFXtr3tTr0Gx7tQJZPotsh0,1967
-ml_tools/SQL.py,sha256=vXLPGfVVg8bfkbBE3HVfyEclVbdJy0TBhuQONtMwSCQ,11234
-ml_tools/VIF_factor.py,sha256=at5IVqPvicja2-DNSTSIIy3SkzDWCmLzo3qTG_qr5n8,10422
-ml_tools/_ML_vision_recipe.py,sha256=zrgxFUvTJqQVuwR7jWlbIC2FD29u6eNFPkTRoJ7yEZI,3178
-ml_tools/__init__.py,sha256=kJiankjz9_qXu7gU92mYqYg_anLvt-B6RtW0mMH8uGo,76
-ml_tools/_logger.py,sha256=dlp5cGbzooK9YSNSZYB4yjZrOaQUGW8PTrM411AOvL8,4717
-ml_tools/_schema.py,sha256=yu6aWmn_2Z4_AxAtJGDDCIa96y6JcUp-vgnCS013Qmw,3908
-ml_tools/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
-ml_tools/constants.py,sha256=3br5Rk9cL2IUo638eJuMOGdbGQaWssaUecYEvSeRBLM,3322
-ml_tools/custom_logger.py,sha256=TGc0Ww2Xlqj2XE3q4bP43hV7T3qnb5ci9f0pYHXF5TY,11226
-ml_tools/data_exploration.py,sha256=bwHzFJ-IAo5GN3T53F-1J_pXUg8VHS91sG_90utAsfg,69911
-ml_tools/ensemble_evaluation.py,sha256=FGHSe8LBI8_w8LjNeJWOcYQ1UK_mc6fVah8gmSvNVGg,26853
-ml_tools/ensemble_inference.py,sha256=0yLmLNj45RVVoSCLH1ZYJG9IoAhTkWUqEZmLOQTFGTY,9348
-ml_tools/ensemble_learning.py,sha256=vsIED7nlheYI4w2SBzP6SC1AnNeMfn-2A1Gqw5EfxsM,21964
-ml_tools/handle_excel.py,sha256=pfdAPb9ywegFkM9T54bRssDOsX-K7rSeV0RaMz7lEAo,14006
-ml_tools/keys.py,sha256=wZOBuEnnHc54vlOZiimnrxfk-sZh6f6suPppJW8rbPQ,3326
-ml_tools/math_utilities.py,sha256=xeKq1quR_3DYLgowcp4Uam_4s3JltUyOnqMOGuAiYWU,8802
-ml_tools/optimization_tools.py,sha256=TYFQ2nSnp7xxs-VyoZISWgnGJghFbsWasHjruegyJRs,12763
-ml_tools/path_manager.py,sha256=CyDU16pOKmC82jPubqJPT6EBt-u-3rGVbxyPIZCvDDY,18432
-ml_tools/serde.py,sha256=c8uDYjYry_VrLvoG4ixqDj5pij88lVn6Tu4NHcPkwDU,6943
-ml_tools/utilities.py,sha256=aWqvYzmxlD74PD5Yqu1VuTekDJeYLQrmPIU_VeVyRp0,22526
-dragon_ml_toolbox-14.3.1.dist-info/METADATA,sha256=dNN-vygEF2WikswJ-6XCShUDf3rD2-XRNtz0vvRg2-4,6475
-dragon_ml_toolbox-14.3.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-14.3.1.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-14.3.1.dist-info/RECORD,,

ml_tools/RNN_forecast.py

@@ -1,56 +0,0 @@
-import torch
-from torch import nn
-import numpy as np
-
-from ._script_info import _script_info
-
-
-__all__ = [
-    "rnn_forecast"
-]
-
-def rnn_forecast(model: nn.Module, start_sequence: torch.Tensor, steps: int, device: str = 'cpu'):
-    """
-    Runs a sequential forecast for a trained RNN-based model.
-
-    This function iteratively predicts future time steps, where each new prediction
-    is generated by feeding the previous prediction back into the model.
-
-    Args:
-        model (nn.Module): The trained PyTorch RNN model (e.g., LSTM, GRU).
-        start_sequence (torch.Tensor): The initial sequence to start the forecast from.
-                                       Shape should be (sequence_length, num_features).
-        steps (int): The number of future time steps to predict.
-        device (str, optional): The device to run the forecast on ('cpu', 'cuda', 'mps'). 
-                                Defaults to 'cpu'.
-
-    Returns:
-        np.ndarray: A numpy array containing the forecasted values.
-    """
-    model.eval()
-    model.to(device)
-    
-    predictions = []
-    current_sequence = start_sequence.to(device)
-
-    with torch.no_grad():
-        for _ in range(steps):
-            # Get the model's prediction for the current sequence
-            output = model(current_sequence.unsqueeze(0)) # Add batch dimension
-            
-            # The prediction is the last element of the output sequence
-            next_pred = output[0, -1, :].view(1, -1)
-            
-            # Store the prediction
-            predictions.append(next_pred.cpu().numpy())
-            
-            # Update the sequence for the next iteration:
-            # Drop the first element and append the new prediction
-            current_sequence = torch.cat([current_sequence[1:], next_pred], dim=0)
-            
-    # Concatenate all predictions and flatten the array for easy use
-    return np.concatenate(predictions).flatten()
-
-
-def info():
-    _script_info(__all__)

ml_tools/_ML_vision_recipe.py

@@ -1,88 +0,0 @@
-import json
-import torch
-from torchvision import transforms
-from typing import Dict, Any, List, Callable, Union
-from pathlib import Path
-
-from .ML_vision_transformers import TRANSFORM_REGISTRY
-from ._logger import _LOGGER
-from .keys import VisionTransformRecipeKeys
-from .path_manager import make_fullpath
-
-
-def save_recipe(recipe: Dict[str, Any], filepath: Path) -> None:
-    """
-    Saves a transform recipe dictionary to a JSON file.
-
-    Args:
-        recipe (Dict[str, Any]): The recipe dictionary to save.
-        filepath (str): The path to the output .json file.
-    """
-    final_filepath = filepath.with_suffix(".json")
-    
-    try:
-        with open(final_filepath, 'w') as f:
-            json.dump(recipe, f, indent=4)
-        _LOGGER.info(f"Transform recipe saved as '{final_filepath.name}'.")
-    except Exception as e:
-        _LOGGER.error(f"Failed to save recipe to '{final_filepath}': {e}")
-        raise
-
-
-def load_recipe_and_build_transform(filepath: Union[str,Path]) -> transforms.Compose:
-    """
-    Loads a transform recipe from a .json file and reconstructs the
-    torchvision.transforms.Compose pipeline.
-
-    Args:
-        filepath (str): Path to the saved transform recipe .json file.
-
-    Returns:
-        transforms.Compose: The reconstructed transformation pipeline.
-        
-    Raises:
-        ValueError: If a transform name in the recipe is not found in
-                    torchvision.transforms or the custom TRANSFORM_REGISTRY.
-    """
-    # validate filepath
-    final_filepath = make_fullpath(filepath, enforce="file")
-    
-    try:
-        with open(final_filepath, 'r') as f:
-            recipe = json.load(f)
-    except Exception as e:
-        _LOGGER.error(f"Failed to load recipe from '{final_filepath}': {e}")
-        raise
-        
-    pipeline_steps: List[Callable] = []
-    
-    if VisionTransformRecipeKeys.PIPELINE not in recipe:
-        _LOGGER.error("Recipe file is invalid: missing 'pipeline' key.")
-        raise ValueError("Invalid recipe format.")
-
-    for step in recipe[VisionTransformRecipeKeys.PIPELINE]:
-        t_name = step[VisionTransformRecipeKeys.NAME]
-        t_kwargs = step[VisionTransformRecipeKeys.KWARGS]
-        
-        transform_class: Any = None
-
-        # 1. Check standard torchvision transforms
-        if hasattr(transforms, t_name):
-            transform_class = getattr(transforms, t_name)
-        # 2. Check custom transforms
-        elif t_name in TRANSFORM_REGISTRY:
-            transform_class = TRANSFORM_REGISTRY[t_name]
-        # 3. Not found
-        else:
-            _LOGGER.error(f"Unknown transform '{t_name}' in recipe. Not found in torchvision.transforms or TRANSFORM_REGISTRY.")
-            raise ValueError(f"Unknown transform name: {t_name}")
-            
-        # Instantiate the transform
-        try:
-            pipeline_steps.append(transform_class(**t_kwargs))
-        except Exception as e:
-            _LOGGER.error(f"Failed to instantiate transform '{t_name}' with kwargs {t_kwargs}: {e}")
-            raise
-            
-    _LOGGER.info(f"Successfully loaded and built transform pipeline from '{final_filepath.name}'.")
-    return transforms.Compose(pipeline_steps)