dragon-ml-toolbox 13.2.0__tar.gz → 14.1.0__tar.gz

{dragon_ml_toolbox-13.2.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-14.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 13.2.0
+Version: 14.1.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: "Karl L. Loza Vidaurre" <luigiloza@gmail.com>
 License-Expression: MIT
@@ -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-13.2.0 → dragon_ml_toolbox-14.1.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 13.2.0
+Version: 14.1.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: "Karl L. Loza Vidaurre" <luigiloza@gmail.com>
 License-Expression: MIT
@@ -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-13.2.0 → dragon_ml_toolbox-14.1.0}/dragon_ml_toolbox.egg-info/SOURCES.txt

@@ -21,10 +21,17 @@ ml_tools/ML_optimization.py
 ml_tools/ML_scaler.py
 ml_tools/ML_trainer.py
 ml_tools/ML_utilities.py
+ml_tools/ML_vision_datasetmaster.py
+ml_tools/ML_vision_evaluation.py
+ml_tools/ML_vision_inference.py
+ml_tools/ML_vision_models.py
+ml_tools/ML_vision_transformers.py
 ml_tools/PSO_optimization.py
 ml_tools/RNN_forecast.py
 ml_tools/SQL.py
 ml_tools/VIF_factor.py
+ml_tools/_ML_pytorch_tabular.py
+ml_tools/_ML_vision_recipe.py
 ml_tools/__init__.py
 ml_tools/_logger.py
 ml_tools/_schema.py

{dragon_ml_toolbox-13.2.0 → dragon_ml_toolbox-14.1.0}/dragon_ml_toolbox.egg-info/requires.txt

@@ -21,6 +21,7 @@ Pillow
 evotorch
 pyarrow
 colorlog
+torchmetrics
 
 [excel]
 pandas

{dragon_ml_toolbox-13.2.0 → dragon_ml_toolbox-14.1.0}/ml_tools/MICE_imputation.py

@@ -7,19 +7,20 @@ from plotnine import ggplot, labs, theme, element_blank # type: ignore
 from typing import Optional, Union
 
 from .utilities import load_dataframe, merge_dataframes, save_dataframe_filename
-from .math_utilities import threshold_binary_values
+from .math_utilities import threshold_binary_values, discretize_categorical_values
 from .path_manager import sanitize_filename, make_fullpath, list_csv_paths
 from ._logger import _LOGGER
 from ._script_info import _script_info
+from ._schema import FeatureSchema
 
 
 __all__ = [
+    "MiceImputer",
     "apply_mice",
     "save_imputed_datasets",
-    "get_na_column_names",
     "get_convergence_diagnostic",
     "get_imputed_distributions",
-    "run_mice_pipeline"
+    "run_mice_pipeline",
 ]
 
 
@@ -79,7 +80,7 @@ def save_imputed_datasets(save_dir: Union[str, Path], imputed_datasets: list, df
 
 
 #Get names of features that had missing values before imputation
-def get_na_column_names(df: pd.DataFrame):
+def _get_na_column_names(df: pd.DataFrame):
     return [col for col in df.columns if df[col].isna().any()]
 
 
@@ -264,7 +265,7 @@ def run_mice_pipeline(df_path_or_dir: Union[str,Path], target_columns: list[str]
         
         save_imputed_datasets(save_dir=save_datasets_path, imputed_datasets=imputed_datasets, df_targets=df_targets, imputed_dataset_names=imputed_dataset_names)
         
-        imputed_column_names = get_na_column_names(df=df)
+        imputed_column_names = _get_na_column_names(df=df)
         
         get_convergence_diagnostic(kernel=kernel, imputed_dataset_names=imputed_dataset_names, column_names=imputed_column_names, root_dir=save_metrics_path)
         
@@ -278,5 +279,206 @@ def _skip_targets(df: pd.DataFrame, target_cols: list[str]):
     return df_feats, df_targets
 
 
+# modern implementation
+class MiceImputer:
+    """
+    A modern MICE imputation pipeline that uses a FeatureSchema
+    to correctly discretize categorical features after imputation.
+    """
+    def __init__(self, 
+                 schema: FeatureSchema,
+                 iterations: int=20,
+                 resulting_datasets: int = 1,
+                 random_state: int = 101):
+        
+        self.schema = schema
+        self.random_state = random_state
+        self.iterations = iterations
+        self.resulting_datasets = resulting_datasets
+        
+        # --- Store schema info ---
+        
+        # 1. Categorical info
+        if not self.schema.categorical_index_map:
+            _LOGGER.warning("FeatureSchema has no 'categorical_index_map'. No discretization will be applied.")
+            self.cat_info = {}
+        else:
+            self.cat_info = self.schema.categorical_index_map
+            
+        # 2. Ordered feature names (critical for index mapping)
+        self.ordered_features = list(self.schema.feature_names)
+        
+        # 3. Names of categorical features
+        self.categorical_features = list(self.schema.categorical_feature_names)
+
+        _LOGGER.info(f"MiceImputer initialized. Found {len(self.cat_info)} categorical features to discretize.")
+        
+    def _post_process(self, imputed_df: pd.DataFrame) -> pd.DataFrame:
+        """
+        Applies schema-based discretization to a completed dataframe.
+        
+        This method works around the behavior of `discretize_categorical_values`
+        (which returns a full int32 array) by:
+        1. Calling it on the full, ordered feature array.
+        2. Extracting *only* the valid discretized categorical columns.
+        3. Updating the original float dataframe with these integer values.
+        """
+        # If no categorical features are defined, return the df as-is.
+        if not self.cat_info:
+            return imputed_df
+
+        try:
+            # 1. Ensure DataFrame columns match the schema order
+            # This is critical for the index-based categorical_info
+            df_ordered: pd.DataFrame = imputed_df[self.ordered_features] # type: ignore
+            
+            # 2. Convert to NumPy array
+            array_ordered = df_ordered.to_numpy()
+
+            # 3. Apply discretization utility (which returns a full int32 array)
+            # This array has *correct* categorical values but *truncated* continuous values.
+            discretized_array_int32 = discretize_categorical_values(
+                array_ordered,
+                self.cat_info,
+                start_at_zero=True  # Assuming 0-based indexing
+            )
+
+            # 4. Create a new DF from the int32 array, keeping the categorical columns.
+            df_discretized_cats = pd.DataFrame(
+                discretized_array_int32,
+                columns=self.ordered_features,
+                index=df_ordered.index  # <-- Critical: align index
+            )[self.categorical_features] # <-- Select only cat features
+
+            # 5. "Rejoin": Start with a fresh copy of the *original* imputed DF (which has correct continuous floats).
+            final_df = df_ordered.copy()
+            
+            # 6. Use .update() to "paste" the integer categorical values
+            # over the old float categorical values. Continuous floats are unaffected.
+            final_df.update(df_discretized_cats)
+            
+            return final_df
+
+        except Exception as e:
+            _LOGGER.error(f"Failed during post-processing discretization:\n\tInput DF shape: {imputed_df.shape}\n\tSchema features: {len(self.ordered_features)}\n\tCategorical info keys: {list(self.cat_info.keys())}\n{e}")
+            raise
+        
+    def _run_mice(self, 
+                  df: pd.DataFrame, 
+                  df_name: str) -> tuple[mf.ImputationKernel, list[pd.DataFrame], list[str]]:
+        """
+        Runs the MICE kernel and applies schema-based post-processing.
+        
+        Parameters:
+            df (pd.DataFrame): The input dataframe *with NaNs*. Should only contain feature columns.
+            df_name (str): The base name for the dataset.
+
+        Returns:
+            tuple[mf.ImputationKernel, list[pd.DataFrame], list[str]]:
+                - The trained MICE kernel
+                - A list of imputed and processed DataFrames
+                - A list of names for the new DataFrames
+        """
+        # Ensure input df only contains features from the schema and is in the correct order.
+        try:
+            df_feats = df[self.ordered_features]
+        except KeyError as e:
+            _LOGGER.error(f"Input DataFrame is missing required schema columns: {e}")
+            raise
+        
+        # 1. Initialize kernel
+        kernel = mf.ImputationKernel(
+            data=df_feats,
+            num_datasets=self.resulting_datasets,
+            random_state=self.random_state
+        )
+        
+        _LOGGER.info("➡️ Schema-based MICE imputation running...")
+        
+        # 2. Perform MICE
+        kernel.mice(self.iterations)
+        
+        # 3. Retrieve, process, and collect datasets
+        imputed_datasets = []
+        for i in range(self.resulting_datasets):
+            # complete_data returns a pd.DataFrame
+            completed_df = kernel.complete_data(dataset=i)
+            
+            # Apply our new discretization and ordering
+            processed_df = self._post_process(completed_df)
+            imputed_datasets.append(processed_df)
+
+        if not imputed_datasets:
+            _LOGGER.error("No imputed datasets were generated.")
+            raise ValueError()
+
+        # 4. Generate names
+        if self.resulting_datasets == 1:
+            imputed_dataset_names = [f"{df_name}_MICE"]
+        else:
+            imputed_dataset_names = [f"{df_name}_MICE_{i+1}" for i in range(self.resulting_datasets)]
+        
+        # 5. Validate indexes 
+        for imputed_df, subname in zip(imputed_datasets, imputed_dataset_names):
+            assert imputed_df.shape[0] == df.shape[0], f"❌ Row count mismatch in dataset {subname}"
+            assert all(imputed_df.index == df.index), f"❌ Index mismatch in dataset {subname}"
+        
+        _LOGGER.info("Schema-based MICE imputation complete.")
+        
+        return kernel, imputed_datasets, imputed_dataset_names
+        
+    def run_pipeline(self, 
+                     df_path_or_dir: Union[str,Path],
+                     save_datasets_dir: Union[str,Path], 
+                     save_metrics_dir: Union[str,Path],
+                     ):
+        """
+        Runs the complete MICE imputation pipeline.
+
+        This method automates the entire workflow:
+            1. Loads data from a CSV file path or a directory with CSV files.
+            2. Separates features and targets based on the `FeatureSchema`.
+            3. Runs the MICE algorithm on the feature set.
+            4. Applies schema-based post-processing to discretize categorical features.
+            5. Saves the final, processed, and imputed dataset(s) (re-joined with targets) to `save_datasets_dir`.
+            6. Generates and saves convergence and distribution plots for all imputed columns to `save_metrics_dir`.
+
+        Parameters
+        ----------
+        df_path_or_dir :[str,Path]
+            Path to a single CSV file or a directory containing multiple CSV files to impute.
+        save_datasets_dir : [str,Path]
+            Directory where the final imputed and processed dataset(s) will be saved as CSVs.
+        save_metrics_dir : [str,Path]
+            Directory where convergence and distribution plots will be saved.
+        """
+        # Check paths
+        save_datasets_path = make_fullpath(save_datasets_dir, make=True)
+        save_metrics_path = make_fullpath(save_metrics_dir, make=True)
+        
+        input_path = make_fullpath(df_path_or_dir)
+        if input_path.is_file():
+            all_file_paths = [input_path]
+        else:
+            all_file_paths = list(list_csv_paths(input_path).values())
+        
+        for df_path in all_file_paths:
+            
+            df, df_name = load_dataframe(df_path=df_path, kind="pandas")
+            
+            df_features: pd.DataFrame = df[self.schema.feature_names] # type: ignore
+            df_targets = df.drop(columns=self.schema.feature_names)
+            
+            imputed_column_names = _get_na_column_names(df=df_features)
+            
+            kernel, imputed_datasets, imputed_dataset_names = self._run_mice(df=df_features, df_name=df_name)
+            
+            save_imputed_datasets(save_dir=save_datasets_path, imputed_datasets=imputed_datasets, df_targets=df_targets, imputed_dataset_names=imputed_dataset_names)
+            
+            get_convergence_diagnostic(kernel=kernel, imputed_dataset_names=imputed_dataset_names, column_names=imputed_column_names, root_dir=save_metrics_path)
+            
+            get_imputed_distributions(kernel=kernel, df_name=df_name, root_dir=save_metrics_path, column_names=imputed_column_names)
+
+
 def info():
     _script_info(__all__)

{dragon_ml_toolbox-13.2.0 → dragon_ml_toolbox-14.1.0}/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"
 ]
 
 
@@ -126,8 +121,8 @@ class _BaseDatasetMaker(ABC):
         else:
             _LOGGER.info("No continuous features listed in schema. Scaler will not be fitted.")
 
-        X_train_values = X_train.values
-        X_test_values = X_test.values
+        X_train_values = X_train.to_numpy()
+        X_test_values = X_test.to_numpy()
 
         # continuous_feature_indices is derived
         if self.scaler is None and continuous_feature_indices:
@@ -253,26 +248,42 @@ class DatasetMaker(_BaseDatasetMaker):
                  pandas_df: pandas.DataFrame,
                  schema: FeatureSchema,
                  kind: Literal["regression", "classification"],
+                 scaler: Union[Literal["fit"], Literal["none"], PytorchScaler],
                  test_size: float = 0.2,
-                 random_state: int = 42,
-                 scaler: Optional[PytorchScaler] = None):
+                 random_state: int = 42):
         """
         Args:
             pandas_df (pandas.DataFrame): 
                 The pre-processed input DataFrame containing all columns. (features and single target).
             schema (FeatureSchema): 
                 The definitive schema object from data_exploration.
-            kind (Literal["regression", "classification"]): 
+            kind ("regression" | "classification"): 
                 The type of ML task. This determines the data type of the labels.
+            scaler ("fit" | "none" | PytorchScaler): 
+                Strategy for data scaling:
+                - "fit": Fit a new PytorchScaler on continuous features.
+                - "none": Do not scale data (e.g., for TabularTransformer).
+                - PytorchScaler instance: Use a pre-fitted scaler to transform data.
             test_size (float): 
                 The proportion of the dataset to allocate to the test split.
             random_state (int): 
                 The seed for the random number of generator for reproducibility.
-            scaler (PytorchScaler | None): 
-                A pre-fitted PytorchScaler instance, if None a new scaler will be created.
+            
         """
         super().__init__()
-        self.scaler = scaler
+        
+        _apply_scaling: bool = False
+        if scaler == "fit":
+            self.scaler = None # To be created
+            _apply_scaling = True
+        elif scaler == "none":
+            self.scaler = None
+        elif isinstance(scaler, PytorchScaler):
+            self.scaler = scaler # Use the provided one
+            _apply_scaling = True
+        else:
+            _LOGGER.error(f"Invalid 'scaler' argument. Must be 'fit', 'none', or a PytorchScaler instance.")
+            raise ValueError()
         
         # --- 1. Identify features (from schema) ---
         self._feature_names = list(schema.feature_names)
@@ -310,9 +321,14 @@ class DatasetMaker(_BaseDatasetMaker):
         label_dtype = torch.float32 if kind == "regression" else torch.int64
 
         # --- 4. Scale (using the schema) ---
-        X_train_final, X_test_final = self._prepare_scaler(
-            X_train, y_train, X_test, label_dtype, schema
-        )
+        if _apply_scaling:
+            X_train_final, X_test_final = self._prepare_scaler(
+                X_train, y_train, X_test, label_dtype, schema
+            )
+        else:
+            _LOGGER.info("Features have not been scaled as specified.")
+            X_train_final = X_train.to_numpy()
+            X_test_final = X_test.to_numpy()
         
         # --- 5. Create Datasets ---
         self._train_ds = _PytorchDataset(X_train_final, y_train, labels_dtype=label_dtype, feature_names=self._feature_names, target_names=self._target_names)
@@ -336,9 +352,9 @@ class DatasetMakerMulti(_BaseDatasetMaker):
                  pandas_df: pandas.DataFrame,
                  target_columns: List[str],
                  schema: FeatureSchema,
+                 scaler: Union[Literal["fit"], Literal["none"], PytorchScaler],
                  test_size: float = 0.2,
-                 random_state: int = 42,
-                 scaler: Optional[PytorchScaler] = None):
+                 random_state: int = 42):
         """
         Args:
             pandas_df (pandas.DataFrame): 
@@ -348,20 +364,35 @@ class DatasetMakerMulti(_BaseDatasetMaker):
                 List of target column names.
             schema (FeatureSchema): 
                 The definitive schema object from data_exploration.
+            scaler ("fit" | "none" | PytorchScaler): 
+                Strategy for data scaling:
+                - "fit": Fit a new PytorchScaler on continuous features.
+                - "none": Do not scale data (e.g., for TabularTransformer).
+                - PytorchScaler instance: Use a pre-fitted scaler to transform data.
             test_size (float): 
                 The proportion of the dataset to allocate to the test split.
             random_state (int): 
                 The seed for the random number generator for reproducibility.
-            scaler (PytorchScaler | None): 
-                A pre-fitted PytorchScaler instance.
                 
         ## Note:
         For multi-binary classification, the most common PyTorch loss function is nn.BCEWithLogitsLoss. 
         This loss function requires the labels to be torch.float32 which is the same type required for regression (multi-regression) tasks.
         """
         super().__init__()
-        self.scaler = scaler
-
+        
+        _apply_scaling: bool = False
+        if scaler == "fit":
+            self.scaler = None
+            _apply_scaling = True
+        elif scaler == "none":
+            self.scaler = None
+        elif isinstance(scaler, PytorchScaler):
+            self.scaler = scaler # Use the provided one
+            _apply_scaling = True
+        else:
+            _LOGGER.error(f"Invalid 'scaler' argument. Must be 'fit', 'none', or a PytorchScaler instance.")
+            raise ValueError()
+        
         # --- 1. Get features and targets from schema/args ---
         self._feature_names = list(schema.feature_names)
         self._target_names = target_columns
@@ -403,9 +434,14 @@ class DatasetMakerMulti(_BaseDatasetMaker):
         label_dtype = torch.float32 
 
         # --- 4. Scale (using the schema) ---
-        X_train_final, X_test_final = self._prepare_scaler(
-            X_train, y_train, X_test, label_dtype, schema
-        )
+        if _apply_scaling:
+            X_train_final, X_test_final = self._prepare_scaler(
+                X_train, y_train, X_test, label_dtype, schema
+            )
+        else:
+            _LOGGER.info("Features have not been scaled as specified.")
+            X_train_final = X_train.to_numpy()
+            X_test_final = X_test.to_numpy()
         
         # --- 5. Create Datasets ---
         # _PytorchDataset now correctly handles y_train (a DataFrame)
@@ -432,149 +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):
     """
@@ -763,40 +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__)