dragon-ml-toolbox 13.7.0__py3-none-any.whl → 14.0.0__py3-none-any.whl

{dragon_ml_toolbox-13.7.0.dist-info → dragon_ml_toolbox-14.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 13.7.0
+Version: 14.0.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: "Karl L. Loza Vidaurre" <luigiloza@gmail.com>
 License-Expression: MIT
@@ -34,6 +34,7 @@ Requires-Dist: Pillow; extra == "ml"
 Requires-Dist: evotorch; extra == "ml"
 Requires-Dist: pyarrow; extra == "ml"
 Requires-Dist: colorlog; extra == "ml"
+Requires-Dist: torchmetrics; extra == "ml"
 Provides-Extra: mice
 Requires-Dist: numpy<2.0; extra == "mice"
 Requires-Dist: pandas; extra == "mice"

{dragon_ml_toolbox-13.7.0.dist-info → dragon_ml_toolbox-14.0.0.dist-info}/RECORD

@@ -1,41 +1,48 @@
-dragon_ml_toolbox-13.7.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-13.7.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
+dragon_ml_toolbox-14.0.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-14.0.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
 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=6caWbq6eu1RE9V51gmceD71PtMctJRjFuLvkkK5ChiY,36271
-ml_tools/ML_evaluation.py,sha256=li77AuP53pCzgrj6p-jTCNtPFgS9Y9XnMWIZn1ulTBM,18946
+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=yq2gdN6s_OUYC5ZLQrIJC5BA5H33q8UKODXwb-_0M2c,23549
-ml_tools/ML_models.py,sha256=UVWJHPLVIvFno_csCHH1FwBfTwQ5nX0V8F1TbOByZ4I,31388
+ml_tools/ML_inference.py,sha256=YJ953bhNWsdlPRtJQh3h2ACfMIgp8dQ9KtL9Azar-5s,23489
+ml_tools/ML_models.py,sha256=B_6cUMI0-CnVKcd9BoabvMOG-xIZz-eqP9G9sfOceHc,31434
 ml_tools/ML_optimization.py,sha256=P0zkhKAwTpkorIBtR0AOIDcyexo5ngmvFUzo3DfNO-E,22692
 ml_tools/ML_scaler.py,sha256=tw6onj9o8_kk3FQYb930HUzvv1zsFZe2YZJdF3LtHkU,7538
-ml_tools/ML_trainer.py,sha256=ZxeOagXW5adFhYIH-oMTlcrLU6VHe4R1EROI7yypNwQ,29665
-ml_tools/ML_utilities.py,sha256=EnKpPTnJ2qjZmz7kvows4Uu5CfSA7ByRmI1v2-KarKw,9337
+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=tOrdatuq_AP8-GDiTrtARvSJdpc8h7dT-OhDJtRQnsk,54433
+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_pytorch_tabular.py,sha256=G9ZkqtjfYe1KAZmkmlL2bCg5s4EIK_wPBBbDmgeEI8k,21753
+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=7tSAgRL7e-Ekm7rS1FLDocaPLCnaoKc7VSrtfwCtCEg,10067
+ml_tools/custom_logger.py,sha256=TGc0Ww2Xlqj2XE3q4bP43hV7T3qnb5ci9f0pYHXF5TY,11226
 ml_tools/data_exploration.py,sha256=-BbWO7BBFapPi_7ZuWo65VqguJXaBfgFSptrXyoWrDk,51902
 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=oykUVLB4Wos3AZomowjtI8AFFC5xnMUH-icNHydRpOk,2275
+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-13.7.0.dist-info/METADATA,sha256=Rk5n5BbicDim5Qg6AzpyG8MwJAqlu5MSclAiLP_V-Vc,6166
-dragon_ml_toolbox-13.7.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-13.7.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-13.7.0.dist-info/RECORD,,
+dragon_ml_toolbox-14.0.0.dist-info/METADATA,sha256=2efDLOcX7Wx5p_9LfMVX78CK_CP63GT93vH9rX2fa4Y,6209
+dragon_ml_toolbox-14.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-14.0.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-14.0.0.dist-info/RECORD,,

ml_tools/ML_datasetmaster.py

@@ -1,13 +1,10 @@
 import torch
-from torch.utils.data import Dataset, Subset
+from torch.utils.data import Dataset
 import pandas
 import numpy
 from sklearn.model_selection import train_test_split
 from typing import Literal, Union, Tuple, List, Optional
 from abc import ABC, abstractmethod
-from PIL import Image, ImageOps
-from torchvision.datasets import ImageFolder
-from torchvision import transforms
 import matplotlib.pyplot as plt
 from pathlib import Path
 
@@ -23,9 +20,7 @@ from ._schema import FeatureSchema
 __all__ = [
     "DatasetMaker",
     "DatasetMakerMulti",
-    "VisionDatasetMaker",
-    "SequenceMaker",
-    "ResizeAspectFill",
+    "SequenceMaker"
 ]
 
 
@@ -473,149 +468,6 @@ class _BaseMaker(ABC):
         pass
 
 
-# --- VisionDatasetMaker ---
-class VisionDatasetMaker(_BaseMaker):
-    """
-    Creates processed PyTorch datasets for computer vision tasks from an
-    image folder directory.
-    
-    Uses online augmentations per epoch (image augmentation without creating new files).
-    """
-    def __init__(self, full_dataset: ImageFolder):
-        super().__init__()
-        self.full_dataset = full_dataset
-        self.labels = [s[1] for s in self.full_dataset.samples]
-        self.class_map = full_dataset.class_to_idx
-        
-        self._is_split = False
-        self._are_transforms_configured = False
-
-    @classmethod
-    def from_folder(cls, root_dir: str) -> 'VisionDatasetMaker':
-        """Creates a maker instance from a root directory of images."""
-        initial_transform = transforms.Compose([transforms.ToTensor()])
-        full_dataset = ImageFolder(root=root_dir, transform=initial_transform)
-        _LOGGER.info(f"Found {len(full_dataset)} images in {len(full_dataset.classes)} classes.")
-        return cls(full_dataset)
-        
-    @staticmethod
-    def inspect_folder(path: Union[str, Path]):
-        """
-        Logs a report of the types, sizes, and channels of image files
-        found in the directory and its subdirectories.
-        """
-        path_obj = make_fullpath(path)
-
-        non_image_files = set()
-        img_types = set()
-        img_sizes = set()
-        img_channels = set()
-        img_counter = 0
-
-        _LOGGER.info(f"Inspecting folder: {path_obj}...")
-        # Use rglob to recursively find all files
-        for filepath in path_obj.rglob('*'):
-            if filepath.is_file():
-                try:
-                    # Using PIL to open is a more reliable check
-                    with Image.open(filepath) as img:
-                        img_types.add(img.format)
-                        img_sizes.add(img.size)
-                        img_channels.update(img.getbands())
-                        img_counter += 1
-                except (IOError, SyntaxError):
-                    non_image_files.add(filepath.name)
-
-        if non_image_files:
-            _LOGGER.warning(f"Non-image or corrupted files found and ignored: {non_image_files}")
-
-        report = (
-            f"\n--- Inspection Report for '{path_obj.name}' ---\n"
-            f"Total images found: {img_counter}\n"
-            f"Image formats: {img_types or 'None'}\n"
-            f"Image sizes (WxH): {img_sizes or 'None'}\n"
-            f"Image channels (bands): {img_channels or 'None'}\n"
-            f"--------------------------------------"
-        )
-        print(report)
-
-    def split_data(self, val_size: float = 0.2, test_size: float = 0.0, 
-                   stratify: bool = True, random_state: Optional[int] = None) -> 'VisionDatasetMaker':
-        """Splits the dataset into training, validation, and optional test sets."""
-        if self._is_split:
-            _LOGGER.warning("Data has already been split.")
-            return self
-
-        if val_size + test_size >= 1.0:
-            _LOGGER.error("The sum of val_size and test_size must be less than 1.")
-            raise ValueError()
-
-        indices = list(range(len(self.full_dataset)))
-        labels_for_split = self.labels if stratify else None
-
-        train_indices, val_test_indices = train_test_split(
-            indices, test_size=(val_size + test_size), random_state=random_state, stratify=labels_for_split
-        )
-
-        if test_size > 0:
-            val_test_labels = [self.labels[i] for i in val_test_indices]
-            stratify_val_test = val_test_labels if stratify else None
-            val_indices, test_indices = train_test_split(
-                val_test_indices, test_size=(test_size / (val_size + test_size)), 
-                random_state=random_state, stratify=stratify_val_test
-            )
-            self._test_dataset = Subset(self.full_dataset, test_indices)
-            _LOGGER.info(f"Test set created with {len(self._test_dataset)} images.")
-        else:
-            val_indices = val_test_indices
-        
-        self._train_dataset = Subset(self.full_dataset, train_indices)
-        self._val_dataset = Subset(self.full_dataset, val_indices)
-        self._is_split = True
-        
-        _LOGGER.info(f"Data split into: \n- Training: {len(self._train_dataset)} images \n- Validation: {len(self._val_dataset)} images")
-        return self
-
-    def configure_transforms(self, resize_size: int = 256, crop_size: int = 224, 
-                             mean: List[float] = [0.485, 0.456, 0.406], 
-                             std: List[float] = [0.229, 0.224, 0.225],
-                             extra_train_transforms: Optional[List] = None) -> 'VisionDatasetMaker':
-        """Configures and applies the image transformations (augmentations)."""
-        if not self._is_split:
-            _LOGGER.error("Transforms must be configured AFTER splitting data. Call .split_data() first.")
-            raise RuntimeError()
-
-        base_train_transforms = [transforms.RandomResizedCrop(crop_size), transforms.RandomHorizontalFlip()]
-        if extra_train_transforms:
-            base_train_transforms.extend(extra_train_transforms)
-        
-        final_transforms = [transforms.ToTensor(), transforms.Normalize(mean=mean, std=std)]
-
-        val_transform = transforms.Compose([transforms.Resize(resize_size), transforms.CenterCrop(crop_size), *final_transforms])
-        train_transform = transforms.Compose([*base_train_transforms, *final_transforms])
-
-        self._train_dataset.dataset.transform = train_transform # type: ignore
-        self._val_dataset.dataset.transform = val_transform # type: ignore
-        if self._test_dataset:
-            self._test_dataset.dataset.transform = val_transform # type: ignore
-        
-        self._are_transforms_configured = True
-        _LOGGER.info("Image transforms configured and applied.")
-        return self
-
-    def get_datasets(self) -> Tuple[Dataset, ...]:
-        """Returns the final train, validation, and optional test datasets."""
-        if not self._is_split:
-            _LOGGER.error("Data has not been split. Call .split_data() first.")
-            raise RuntimeError()
-        if not self._are_transforms_configured:
-            _LOGGER.warning("Transforms have not been configured. Using default ToTensor only.")
-
-        if self._test_dataset:
-            return self._train_dataset, self._val_dataset, self._test_dataset
-        return self._train_dataset, self._val_dataset
-
-
 # --- SequenceMaker ---
 class SequenceMaker(_BaseMaker):
     """
@@ -804,40 +656,5 @@ class SequenceMaker(_BaseMaker):
         return self._train_dataset, self._test_dataset
 
 
-# --- Custom Vision Transform Class ---
-class ResizeAspectFill:
-    """
-    Custom transformation to make an image square by padding it to match the
-    longest side, preserving the aspect ratio. The image is finally centered.
-
-    Args:
-        pad_color (Union[str, int]): Color to use for the padding.
-                                     Defaults to "black".
-    """
-    def __init__(self, pad_color: Union[str, int] = "black") -> None:
-        self.pad_color = pad_color
-
-    def __call__(self, image: Image.Image) -> Image.Image:
-        if not isinstance(image, Image.Image):
-            _LOGGER.error(f"Expected PIL.Image.Image, got {type(image).__name__}")
-            raise TypeError()
-
-        w, h = image.size
-        if w == h:
-            return image
-
-        # Determine padding to center the image
-        if w > h:
-            top_padding = (w - h) // 2
-            bottom_padding = w - h - top_padding
-            padding = (0, top_padding, 0, bottom_padding)
-        else: # h > w
-            left_padding = (h - w) // 2
-            right_padding = h - w - left_padding
-            padding = (left_padding, 0, right_padding, 0)
-
-        return ImageOps.expand(image, padding, fill=self.pad_color)
-
-
 def info():
     _script_info(__all__)

ml_tools/ML_evaluation.py

@@ -24,7 +24,7 @@ import warnings
 from .path_manager import make_fullpath
 from ._logger import _LOGGER
 from ._script_info import _script_info
-from .keys import SHAPKeys
+from .keys import SHAPKeys, PyTorchLogKeys
 
 
 __all__ = [
@@ -44,8 +44,8 @@ def plot_losses(history: dict, save_dir: Union[str, Path]):
         history (dict): A dictionary containing 'train_loss' and 'val_loss'.
         save_dir (str | Path): Directory to save the plot image.
     """
-    train_loss = history.get('train_loss', [])
-    val_loss = history.get('val_loss', [])
+    train_loss = history.get(PyTorchLogKeys.TRAIN_LOSS, [])
+    val_loss = history.get(PyTorchLogKeys.VAL_LOSS, [])
     
     if not train_loss and not val_loss:
         print("Warning: Loss history is empty or incomplete. Cannot plot.")

ml_tools/ML_inference.py

@@ -82,7 +82,6 @@ class _BaseInferenceHandler(ABC):
             _LOGGER.warning("CUDA not available, switching to CPU.")
             device_lower = "cpu"
         elif device_lower == "mps" and not torch.backends.mps.is_available():
-            # Your M-series Mac will appreciate this check!
             _LOGGER.warning("Apple Metal Performance Shaders (MPS) not available, switching to CPU.")
             device_lower = "cpu"
         return torch.device(device_lower)

ml_tools/ML_models.py

@@ -1,6 +1,6 @@
 import torch
 from torch import nn
-from typing import List, Union, Tuple, Dict, Any
+from typing import List, Union, Tuple, Dict, Any, Literal, Optional
 from pathlib import Path
 import json
 
@@ -748,5 +748,7 @@ class SequencePredictorLSTM(nn.Module, _ArchitectureHandlerMixin):
         )
 
 
+# ---- PyTorch models ---
+
 def info():
     _script_info(__all__)