dragon-ml-toolbox 13.3.0__py3-none-any.whl → 14.7.0__py3-none-any.whl

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)
@@ -310,14 +321,32 @@ 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)
         self._test_ds = _PytorchDataset(X_test_final, y_test, labels_dtype=label_dtype, feature_names=self._feature_names, target_names=self._target_names)
-        
+    
+    def __repr__(self) -> str:
+        s = f"<{self.__class__.__name__} (ID: '{self.id}')>\n"
+        s += f"  Target: {self.target_names[0]}\n"
+        s += f"  Features: {self.number_of_features}\n"
+        s += f"  Scaler: {'Fitted' if self.scaler else 'None'}\n"
+        
+        if self._train_ds:
+            s += f"  Train Samples: {len(self._train_ds)}\n" # type: ignore
+        if self._test_ds:
+            s += f"  Test Samples: {len(self._test_ds)}\n" # type: ignore
+            
+        return s
+
 
 # --- Multi-Target Class ---
 class DatasetMakerMulti(_BaseDatasetMaker):
@@ -336,9 +365,9 @@ 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 +377,35 @@ 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
@@ -403,15 +447,33 @@ 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)
         self._train_ds = _PytorchDataset(X_train_final, y_train, labels_dtype=label_dtype, feature_names=self._feature_names, target_names=self._target_names)
         self._test_ds = _PytorchDataset(X_test_final, y_test, labels_dtype=label_dtype, feature_names=self._feature_names, target_names=self._target_names)
 
+    def __repr__(self) -> str:
+        s = f"<{self.__class__.__name__} (ID: '{self.id}')>\n"
+        s += f"  Targets: {self.number_of_targets}\n"
+        s += f"  Features: {self.number_of_features}\n"
+        s += f"  Scaler: {'Fitted' if self.scaler else 'None'}\n"
+        
+        if self._train_ds:
+            s += f"  Train Samples: {len(self._train_ds)}\n" # type: ignore
+        if self._test_ds:
+            s += f"  Test Samples: {len(self._test_ds)}\n" # type: ignore
+            
+        return s
+
 
 # --- Private Base Class ---
 class _BaseMaker(ABC):
@@ -432,149 +494,6 @@ 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):
     """
@@ -761,41 +680,22 @@ class SequenceMaker(_BaseMaker):
             _LOGGER.error("Windows have not been generated. Call .generate_windows() first.")
             raise RuntimeError()
         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 __repr__(self) -> str:
+        s = f"<{self.__class__.__name__}>:\n"
+        s += f"  Sequence Length (Window): {self.sequence_length}\n"
+        s += f"  Total Data Points: {len(self.sequence)}\n"
+        s += "  --- Status ---\n"
+        s += f"  Split: {self._is_split}\n"
+        s += f"  Normalized: {self._is_normalized}\n"
+        s += f"  Windows Generated: {self._are_windows_generated}\n"
+        
+        if self._are_windows_generated:
+            train_len = len(self._train_dataset) if self._train_dataset else 0 # type: ignore
+            test_len = len(self._test_dataset) if self._test_dataset else 0 # type: ignore
+            s += f"  Datasets (Train/Test): {train_len} / {test_len} windows\n"
+            
+        return s
 
 
 def info():