dataeval 0.86.0__py3-none-any.whl → 0.86.2__py3-none-any.whl

dataeval/utils/datasets/_ships.py

@@ -30,7 +30,7 @@ class Ships(BaseICDataset[NDArray[Any]], BaseDatasetNumpyMixin):
     Parameters
     ----------
     root : str or pathlib.Path
-        Root directory of dataset where the ``shipdataset`` folder exists.
+        Root directory where the data should be downloaded to or the ``ships`` folder of the already downloaded data.
     transforms : Transform, Sequence[Transform] or None, default None
         Transform(s) to apply to the data.
     download : bool, default False
@@ -90,14 +90,23 @@ class Ships(BaseICDataset[NDArray[Any]], BaseDatasetNumpyMixin):
             verbose,
         )
         self._scenes: list[str] = self._load_scenes()
+        self._remove_extraneous_json_file()
+
+    def _remove_extraneous_json_file(self) -> None:
+        json_path = self.path / "shipsnet.json"
+        if json_path.exists():
+            json_path.unlink()
 
     def _load_data_inner(self) -> tuple[list[str], list[int], dict[str, Any]]:
         """Function to load in the file paths for the data and labels"""
         file_data = {"label": [], "scene_id": [], "longitude": [], "latitude": [], "path": []}
-        data_folder = self.path / "shipsnet"
-        for entry in data_folder.iterdir():
+        data_folder = sorted((self.path / "shipsnet").glob("*.png"))
+        if not data_folder:
+            raise FileNotFoundError
+
+        for entry in data_folder:
             # Remove file extension and split by "_"
-            parts = entry.stem.split("__")  # Removes ".png" and splits the string
+            parts = entry.stem.split("__")
             file_data["label"].append(int(parts[0]))
             file_data["scene_id"].append(parts[1])
             lat_lon = parts[2].split("_")
@@ -110,9 +119,7 @@ class Ships(BaseICDataset[NDArray[Any]], BaseDatasetNumpyMixin):
 
     def _load_scenes(self) -> list[str]:
         """Function to load in the file paths for the scene images"""
-        data_folder = self.path / "scenes"
-        scene = [str(entry) for entry in data_folder.iterdir()]
-        return scene
+        return sorted(str(entry) for entry in (self.path / "scenes").glob("*.png"))
 
     def get_scene(self, index: int) -> NDArray[np.uintp]:
         """

dataeval/utils/datasets/_voc.py

@@ -2,6 +2,8 @@ from __future__ import annotations
 
 __all__ = []
 
+import os
+import shutil
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Literal, Sequence, TypeVar
 
@@ -14,6 +16,7 @@ from dataeval.utils.datasets._base import (
     BaseODDataset,
     BaseSegDataset,
     DataLocation,
+    _ensure_exists,
     _TArray,
     _TTarget,
 )
@@ -51,48 +54,56 @@ TVOCClassMap = TypeVar("TVOCClassMap", VOCClassStringMap, int, list[VOCClassStri
 class BaseVOCDataset(BaseDataset[_TArray, _TTarget, list[str]]):
     _resources = [
         DataLocation(
-            url="http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar",
+            url="https://data.brainchip.com/dataset-mirror/voc/VOCtrainval_11-May-2012.tar",
             filename="VOCtrainval_11-May-2012.tar",
-            md5=True,
-            checksum="6cd6e144f989b92b3379bac3b3de84fd",
+            md5=False,
+            checksum="e14f763270cf193d0b5f74b169f44157a4b0c6efa708f4dd0ff78ee691763bcb",
         ),
         DataLocation(
             url="http://host.robots.ox.ac.uk/pascal/VOC/voc2011/VOCtrainval_25-May-2011.tar",
             filename="VOCtrainval_25-May-2011.tar",
-            md5=True,
-            checksum="6c3384ef61512963050cb5d687e5bf1e",
+            md5=False,
+            checksum="0a7f5f5d154f7290ec65ec3f78b72ef72c6d93ff6d79acd40dc222a9ee5248ba",
         ),
         DataLocation(
             url="http://host.robots.ox.ac.uk/pascal/VOC/voc2010/VOCtrainval_03-May-2010.tar",
             filename="VOCtrainval_03-May-2010.tar",
-            md5=True,
-            checksum="da459979d0c395079b5c75ee67908abb",
+            md5=False,
+            checksum="1af4189cbe44323ab212bff7afbc7d0f55a267cc191eb3aac911037887e5c7d4",
         ),
         DataLocation(
             url="http://host.robots.ox.ac.uk/pascal/VOC/voc2009/VOCtrainval_11-May-2009.tar",
             filename="VOCtrainval_11-May-2009.tar",
-            md5=True,
-            checksum="da459979d0c395079b5c75ee67908abb",
+            md5=False,
+            checksum="11cbe1741fb5bdadbbca3c08e9ec62cd95c14884845527d50847bc2cf57e7fd6",
         ),
         DataLocation(
             url="http://host.robots.ox.ac.uk/pascal/VOC/voc2008/VOCtrainval_14-Jul-2008.tar",
             filename="VOCtrainval_14-Jul-2008.tar",
-            md5=True,
-            checksum="2629fa636546599198acfcfbfcf1904a",
+            md5=False,
+            checksum="7f0ca53c1b5a838fbe946965fc106c6e86832183240af5c88e3f6c306318d42e",
         ),
         DataLocation(
-            url="http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar",
+            url="https://data.brainchip.com/dataset-mirror/voc/VOCtrainval_06-Nov-2007.tar",
             filename="VOCtrainval_06-Nov-2007.tar",
-            md5=True,
-            checksum="c52e279531787c972589f7e41ab4ae64",
+            md5=False,
+            checksum="7d8cd951101b0957ddfd7a530bdc8a94f06121cfc1e511bb5937e973020c7508",
         ),
         DataLocation(
-            url="http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar",
+            url="https://data.brainchip.com/dataset-mirror/voc/VOC2012test.tar",
+            filename="VOC2012test.tar",
+            md5=False,
+            checksum="f08582b1935816c5eab3bbb1eb6d06201a789eaa173cdf1cf400c26f0cac2fb3",
+        ),
+        DataLocation(
+            url="https://data.brainchip.com/dataset-mirror/voc/VOCtest_06-Nov-2007.tar",
             filename="VOCtest_06-Nov-2007.tar",
-            md5=True,
-            checksum="b6e924de25625d8de591ea690078ad9f",
+            md5=False,
+            checksum="6836888e2e01dca84577a849d339fa4f73e1e4f135d312430c4856b5609b4892",
         ),
     ]
+    _base2007: tuple[int, int] = (5, 7)
+    _base2012: tuple[int, int] = (0, 6)
 
     index2label: dict[int, str] = {
         0: "aeroplane",
@@ -137,26 +148,183 @@ class BaseVOCDataset(BaseDataset[_TArray, _TTarget, list[str]]):
         )
 
     def _get_dataset_dir(self) -> Path:
-        """Function to reassign the dataset directory for common use with the VOC detection and segmentation classes"""
-        if self._root.stem == f"VOC{self.year}":
-            dataset_dir: Path = self._root
-        else:
-            dataset_dir: Path = self._root / f"VOC{self.year}"
+        """Overrides the base function to determine correct dataset directory for VOC class"""
+        return self._find_main_VOC_dir(self._root)
+
+    def _find_main_VOC_dir(self, base: Path) -> Path:
+        """
+        Determine the correct dataset directory for VOC detection and segmentation classes.
+        Handles various directory structure possibilities and validates existence.
+        """
+
+        # VOCdataset directory possibilities
+        dataset_dir = base if base.stem.lower() == "vocdataset" else base / "vocdataset"
+
+        # Define possible directory structures based on patterns
+        # 1. Root is already the specific VOC year directory
+        # 2. Root is the VOCdevkit directory
+        # 3. Standard structure
+        # 4. Special case for year 2011
+        # 5. Within VOCdataset directory
+        # 6. Special case for year 2011 within VOCdataset
+        possible_paths = [
+            base if base.stem == f"VOC{self.year}" else None,
+            base / f"VOC{self.year}" if base.stem == "VOCdevkit" else None,
+            base / "VOCdevkit" / f"VOC{self.year}",
+            base / "TrainVal" / "VOCdevkit" / f"VOC{self.year}" if self.year == "2011" else None,
+            dataset_dir / "VOCdevkit" / f"VOC{self.year}",
+            dataset_dir / "TrainVal" / "VOCdevkit" / f"VOC{self.year}" if self.year == "2011" else None,
+        ]
+
+        # Filter out None values and check each path
+        for path in filter(None, possible_paths):
+            if path.exists():
+                return path
+
+        # If no existing path is found, create and return the dataset directory
         if not dataset_dir.exists():
             dataset_dir.mkdir(parents=True, exist_ok=True)
+
         return dataset_dir
 
-    def _get_year_image_set_index(self, year, image_set) -> int:
+    def _get_year_image_set_index(self, year: str, image_set: str) -> int:
         """Function to ensure that the correct resource file is accessed"""
         if year == "2007" and image_set == "test":
             return -1
-        elif year != "2007" and image_set == "test":
+        if year == "2012" and image_set == "test":
+            return -2
+        if year != "2007" and image_set == "test":
             raise ValueError(
-                f"The only test set available is for the year 2007, not {year}. "
-                "Either select the year 2007 or use a different image_set."
+                f"The only test sets available are for the years 2007 and 2012, not {year}. "
+                "Either select the year 2007 or 2012, or use a different image_set."
             )
+        return 2012 - int(year)
+
+    def _update_path(self) -> None:
+        """Update the path to the new folder structure"""
+        if self.year == "2011" and self.path.stem.lower() == "vocdataset":
+            self.path: Path = self.path / "TrainVal" / "VOCdevkit" / f"VOC{self.year}"
+        elif self.path.stem.lower() == "vocdataset":
+            self.path: Path = self.path / "VOCdevkit" / f"VOC{self.year}"
+
+    def _load_data_exception(self) -> tuple[list[str], list[str], dict[str, Any]]:
+        """Adjust how the directory is created for the 2007 and 2012 test set"""
+        filepaths: list[str] = []
+        targets: list[str] = []
+        datum_metadata: dict[str, list[Any]] = {}
+        tmp_path: Path = self._root / "tmp_directory_for_download"
+        tmp_path.mkdir(exist_ok=True)
+        resource_idx = self._base2007 if self.year == "2007" else self._base2012
+
+        # Determine if text files exist
+        train_file = self.path / "ImageSets" / "Main" / "trainval.txt"
+        test_file = self.path / "ImageSets" / "Main" / "test.txt"
+        train_exists = train_file.exists()
+        test_exists = test_file.exists()
+
+        if self.image_set == "base":
+            if not train_exists and not test_exists:
+                _ensure_exists(*self._resources[resource_idx[0]], self.path, self._root, self._download, self._verbose)
+                self._update_path()
+                _ensure_exists(*self._resources[resource_idx[1]], tmp_path, self._root, self._download, self._verbose)
+                self._merge_voc_directories(tmp_path)
+
+            elif train_exists and not test_exists:
+                _ensure_exists(*self._resources[resource_idx[1]], tmp_path, self._root, self._download, self._verbose)
+                self._merge_voc_directories(tmp_path)
+
+            elif not train_exists and test_exists:
+                _ensure_exists(*self._resources[resource_idx[0]], tmp_path, self._root, self._download, self._verbose)
+                self._merge_voc_directories(tmp_path)
+
+            # Code to determine what is needed in each category
+            metadata_list: list[dict[str, Any]] = []
+
+            for img_set in ["test", "base"]:
+                self.image_set = img_set
+                resource_filepaths, resource_targets, resource_metadata = self._load_data_inner()
+                filepaths.extend(resource_filepaths)
+                targets.extend(resource_targets)
+                metadata_list.append(resource_metadata)
+
+            # Combine metadata from all resources
+            for data_dict in metadata_list:
+                for key, val in data_dict.items():
+                    str_key = str(key)  # Ensure key is string
+                    if str_key not in datum_metadata:
+                        datum_metadata[str_key] = []
+                    datum_metadata[str_key].extend(val)
+
         else:
-            return 2012 - int(year)
+            self._resource = self._resources[resource_idx[1]]
+
+            if train_exists and not test_exists:
+                _ensure_exists(*self._resource, tmp_path, self._root, self._download, self._verbose)
+                self._merge_voc_directories(tmp_path)
+
+            resource_filepaths, resource_targets, resource_metadata = self._load_try_and_update()
+            filepaths.extend(resource_filepaths)
+            targets.extend(resource_targets)
+            datum_metadata.update(resource_metadata)
+
+        return filepaths, targets, datum_metadata
+
+    def _merge_voc_directories(self, source_dir: Path) -> None:
+        """Merge two VOC directories, handling file conflicts intelligently."""
+        base: Path = self._find_main_VOC_dir(source_dir)
+        # Create all subdirectories in target if they don't exist
+        for dirpath, dirnames, filenames in os.walk(base):
+            # Convert to Path objects
+            source_path = Path(dirpath)
+
+            # Get the relative path from source_dir
+            rel_path = source_path.relative_to(base)
+
+            # Create the corresponding target path
+            target_path = self.path / rel_path
+            target_path.mkdir(parents=True, exist_ok=True)
+
+            # Copy all files
+            for filename in filenames:
+                source_file = source_path / filename
+                target_file = target_path / filename
+
+                # File doesn't exist in target, just move it
+                if not target_file.exists():
+                    shutil.move(source_file, target_file)
+                else:
+                    # File exists in both assume they're identical and skip
+                    pass
+
+        shutil.rmtree(source_dir)
+
+    def _load_try_and_update(self) -> tuple[list[str], list[str], dict[str, Any]]:
+        """Test if data needs to be downloaded and update path if it does"""
+        if self._verbose:
+            print(f"Determining if {self._resource.filename} needs to be downloaded.")
+
+        try:
+            result = self._load_data_inner()
+            if self._verbose:
+                print("No download needed, loaded data successfully.")
+        except FileNotFoundError:
+            _ensure_exists(*self._resource, self.path, self._root, self._download, self._verbose)
+            self._update_path()
+            result = self._load_data_inner()
+        return result
+
+    def _load_data(self) -> tuple[list[str], list[str], dict[str, Any]]:
+        """
+        Function to determine if data can be accessed or if it needs to be downloaded and/or extracted.
+        """
+        # Exception - test sets
+        year_set_bool = (self.image_set == "test" or self.image_set == "base") and (
+            self.year == "2012" or self.year == "2007"
+        )
+        if year_set_bool:
+            return self._load_data_exception()
+
+        return self._load_try_and_update()
 
     def _get_image_sets(self) -> dict[str, list[str]]:
         """Function to create the list of images in each image set"""
@@ -206,20 +374,21 @@ class BaseVOCDataset(BaseDataset[_TArray, _TTarget, list[str]]):
     def _read_annotations(self, annotation: str) -> tuple[list[list[float]], list[int], dict[str, Any]]:
         boxes: list[list[float]] = []
         label_str = []
+        if not Path(annotation).exists():
+            return boxes, label_str, {}
         root = parse(annotation).getroot()
         if root is None:
             raise ValueError(f"Unable to parse {annotation}")
-        num_objects = len(root.findall("object"))
         additional_meta: dict[str, Any] = {
-            "folder": [root.findtext("folder", default="") for _ in range(num_objects)],
-            "filename": [root.findtext("filename", default="") for _ in range(num_objects)],
-            "database": [root.findtext("source/database", default="") for _ in range(num_objects)],
-            "annotation_source": [root.findtext("source/annotation", default="") for _ in range(num_objects)],
-            "image_source": [root.findtext("source/image", default="") for _ in range(num_objects)],
-            "image_width": [int(root.findtext("size/width", default="-1")) for _ in range(num_objects)],
-            "image_height": [int(root.findtext("size/height", default="-1")) for _ in range(num_objects)],
-            "image_depth": [int(root.findtext("size/depth", default="-1")) for _ in range(num_objects)],
-            "segmented": [int(root.findtext("segmented", default="-1")) for _ in range(num_objects)],
+            "folder": root.findtext("folder", default=""),
+            "filename": root.findtext("filename", default=""),
+            "database": root.findtext("source/database", default=""),
+            "annotation_source": root.findtext("source/annotation", default=""),
+            "image_source": root.findtext("source/image", default=""),
+            "image_width": int(root.findtext("size/width", default="-1")),
+            "image_height": int(root.findtext("size/height", default="-1")),
+            "image_depth": int(root.findtext("size/depth", default="-1")),
+            "segmented": int(root.findtext("segmented", default="-1")),
             "pose": [],
             "truncated": [],
             "difficult": [],
@@ -252,9 +421,14 @@ class VOCDetection(
     Parameters
     ----------
     root : str or pathlib.Path
-        Root directory of dataset where the ``vocdataset`` folder exists.
+        Because of the structure of the PASCAL VOC datasets, the root needs to be one of 4 folders.
+        1) Directory containing the year of the **already downloaded** dataset (i.e. .../VOCdevkit/VOC2012 <-)
+        2) Directory to the VOCdevkit folder of the **already downloaded** dataset (i.e. .../VOCdevkit <- /VOC2012)
+        3) Directory to the folder one level up from the VOCdevkit folder,
+        data **may** or **may not** be already downloaded (i.e. ... <- /VOCdevkit/VOC2012)
+        4) Directory to where you would like the dataset to be downloaded
     image_set : "train", "val", "test", or "base", default "train"
-        If "test", then dataset year must be "2007".
+        If "test", then dataset year must be "2007" or "2012". Note that the 2012 test set does not contain annotations.
         If "base", then the combined dataset of "train" and "val" is returned.
     year : "2007", "2008", "2009", "2010", "2011" or "2012", default "2012"
         The dataset year.
@@ -302,9 +476,14 @@ class VOCDetectionTorch(
     Parameters
     ----------
     root : str or pathlib.Path
-        Root directory of dataset where the ``vocdataset`` folder exists.
+        Because of the structure of the PASCAL VOC datasets, the root needs to be one of 4 folders.
+        1) Directory containing the year of the **already downloaded** dataset (i.e. .../VOCdevkit/VOC2012 <-)
+        2) Directory to the VOCdevkit folder of the **already downloaded** dataset (i.e. .../VOCdevkit <- /VOC2012)
+        3) Directory to the folder one level up from the VOCdevkit folder,
+        data **may** or **may not** be already downloaded (i.e. ... <- /VOCdevkit/VOC2012)
+        4) Directory to where you would like the dataset to be downloaded
     image_set : "train", "val", "test", or "base", default "train"
-        If "test", then dataset year must be "2007".
+        If "test", then dataset year must be "2007" or "2012". Note that the 2012 test set does not contain annotations.
         If "base", then the combined dataset of "train" and "val" is returned.
     year : "2007", "2008", "2009", "2010", "2011" or "2012", default "2012"
         The dataset year.
@@ -391,6 +570,14 @@ class VOCSegmentation(
     """
 
     def _load_data(self) -> tuple[list[str], list[str], dict[str, list[Any]]]:
-        filepaths, targets, datum_metadata = super()._load_data()
+        """Overload base load data to split out masks for segmentation."""
+        # Exception - test sets
+        year_set_bool = (self.image_set == "test" or self.image_set == "base") and (
+            self.year == "2012" or self.year == "2007"
+        )
+        if year_set_bool:
+            filepaths, targets, datum_metadata = self._load_data_exception()
+        else:
+            filepaths, targets, datum_metadata = self._load_try_and_update()
         self._masks = datum_metadata.pop("mask_path")
         return filepaths, targets, datum_metadata

dataeval/utils/torch/models.py

@@ -47,8 +47,7 @@ class Autoencoder(nn.Module):
             The reconstructed output tensor.
         """
         x = self.encoder(x)
-        x = self.decoder(x)
-        return x
+        return self.decoder(x)
 
     def encode(self, x: Any) -> Any:
         """
@@ -188,8 +187,7 @@ class AE(nn.Module):
             The reconstructed output tensor.
         """
         x = self.encoder(x)
-        x = self.decoder(x)
-        return x
+        return self.decoder(x)
 
     def encode(self, x: torch.Tensor) -> torch.Tensor:
         """
@@ -278,9 +276,7 @@ class Encoder_AE(nn.Module):
         """
         x = self.encoding_ops(x)
 
-        x = self.flatten(x)
-
-        return x
+        return self.flatten(x)
 
 
 class Decoder_AE(nn.Module):
@@ -334,8 +330,7 @@ class Decoder_AE(nn.Module):
         x = self.input(x)
         x = x.reshape((-1, *self.post_op_shape))
         x = self.decoder(x)
-        x = x.reshape((-1, *self.input_shape))
-        return x
+        return x.reshape((-1, *self.input_shape))
 
 
 class ResNet18(nn.Module):
@@ -355,7 +350,7 @@ class ResNet18(nn.Module):
     Please use with caution if deploying this class or subclasses.
     """
 
-    def __init__(self, embedding_size: int = 128):
+    def __init__(self, embedding_size: int = 128) -> None:
         super().__init__()
         self.model: nn.Module = resnet18(weights=ResNet18_Weights.DEFAULT, progress=False)
         self.model.fc = nn.Linear(self.model.fc.in_features, embedding_size)

dataeval/utils/torch/trainer.py

@@ -2,8 +2,6 @@
 
 from __future__ import annotations
 
-from dataeval.config import DeviceLike, get_device
-
 __all__ = ["AETrainer"]
 
 from typing import Any
@@ -13,6 +11,8 @@ import torch.nn as nn
 from torch.optim import Adam
 from torch.utils.data import DataLoader, Dataset
 
+from dataeval.config import DeviceLike, get_device
+
 
 def get_images_from_batch(batch: Any) -> Any:
     """Extracts images from a batch of collated data by DataLoader"""
@@ -39,7 +39,7 @@ class AETrainer:
         model: nn.Module,
         device: DeviceLike | None = None,
         batch_size: int = 8,
-    ):
+    ) -> None:
         self.device: torch.device = get_device(device)
         self.model: nn.Module = model.to(self.device)
         self.batch_size = batch_size

dataeval/workflows/sufficiency.py

@@ -21,7 +21,7 @@ def reset_parameters(model: nn.Module) -> nn.Module:
     """
 
     @torch.no_grad()
-    def weight_reset(m: nn.Module):
+    def weight_reset(m: nn.Module) -> None:
         # Check if the current module has reset_parameters
         reset_parameters = getattr(m, "reset_parameters", None)
         if callable(reset_parameters):
@@ -86,7 +86,7 @@ class Sufficiency(Generic[T]):
         substeps: int = 5,
         train_kwargs: Mapping[str, Any] | None = None,
         eval_kwargs: Mapping[str, Any] | None = None,
-    ):
+    ) -> None:
         self.model = model
         self.train_ds = train_ds
         self.test_ds = test_ds

{dataeval-0.86.0.dist-info → dataeval-0.86.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dataeval
-Version: 0.86.0
+Version: 0.86.2
 Summary: DataEval provides a simple interface to characterize image data and its impact on model performance across classification and object-detection tasks
 Home-page: https://dataeval.ai/
 License: MIT
@@ -29,6 +29,7 @@ Requires-Dist: numba (>=0.59.1)
 Requires-Dist: numpy (>=1.24.2)
 Requires-Dist: pandas (>=2.0)
 Requires-Dist: pillow (>=10.3.0)
+Requires-Dist: polars (>=1.0.0)
 Requires-Dist: requests
 Requires-Dist: scikit-learn (>=1.5.0)
 Requires-Dist: scipy (>=1.10)

dataeval-0.86.2.dist-info/RECORD

@@ -0,0 +1,114 @@
+dataeval/__init__.py,sha256=7Q_nGiQN6g8Le7VtOsemNgn5mC_6gR3NhazolD_arSQ,1636
+dataeval/_log.py,sha256=C7AGkIRzymvYJ0LQXtnShiy3i5Xrp8T58JzIHHguk_Q,365
+dataeval/config.py,sha256=hjad0TK1UmaKQlUuxqxt64_OAUqZkHjicBf06cvTyrQ,4082
+dataeval/data/__init__.py,sha256=qNnRRiVP_sLthkkHpUrMgI_r8dQK-cC-xoGrrjQeRKc,544
+dataeval/data/_embeddings.py,sha256=PFjpdV9bfusCB4taTIYSzx1hP8nJb_KCkZTN8kMw-Hs,12885
+dataeval/data/_images.py,sha256=3d4Cv-xg5z6_LVtw1eL_QdFwzbDI1cwvPNQblkrMEMk,2622
+dataeval/data/_metadata.py,sha256=GzXtecy7EvrB3ZJJbaCQjmpsdHXRL5788ckKbzeI54w,14994
+dataeval/data/_selection.py,sha256=r06xeiyK8nTWPLyItkoPQRWZI1i6LATSue_cuEbCdc4,4463
+dataeval/data/_split.py,sha256=nQABR05vxil2Qx7-uX4Fm0_DWpibskBGDJOYj_b1u3I,16737
+dataeval/data/_targets.py,sha256=pXrHBwT4Pi8DauaOxDVnIMwowWWlXuvSb07ShW7O2zk,3119
+dataeval/data/selections/__init__.py,sha256=2m8ZB53wXzqLcqmc6p5atO6graB6ZyiRSNJFxf11X_g,613
+dataeval/data/selections/_classbalance.py,sha256=7v8ApoL3X8eCZ6fGDNTehE_bZ1loaP3TlhsJLaICVWg,1458
+dataeval/data/selections/_classfilter.py,sha256=KQOmcTIcV3ZPWuiwqOmwX0SB5I2qlbxLSlwINUZWOjU,4339
+dataeval/data/selections/_indices.py,sha256=RFsR9z10aM3N0gJSfKrukFpi-LkiQGXoOwXhmOQ5cpg,630
+dataeval/data/selections/_limit.py,sha256=JG4GmEiNKt3sk4PbOUbBnGGzNlyz72H-kQrt8COMm4Y,512
+dataeval/data/selections/_prioritize.py,sha256=4dGUvgR7m6NGzzPU0N_bw0Xhujo8b72Wo8L4PGHbvBo,11233
+dataeval/data/selections/_reverse.py,sha256=b67kNC43A5KpQOic5gifjo9HpJ7FMh4LFCrfovPiJ-M,368
+dataeval/data/selections/_shuffle.py,sha256=TSCIZBgLAn09iMI_WIw0aqwSU4NZLAhHG7t8H_CuDUY,1195
+dataeval/detectors/__init__.py,sha256=3Sg-XWlwr75zEEH3hZKA4nWMtGvaRlnfzTWvZG_Ak6U,189
+dataeval/detectors/drift/__init__.py,sha256=Jqv98oOVeC2tvHlNGxQ8RJ6De2q4SyS5lTpaYlb4ocM,756
+dataeval/detectors/drift/_base.py,sha256=6aNF1LzG3w1sNUrmSBbsvuN5IkQnoRikRacqobYge84,7592
+dataeval/detectors/drift/_cvm.py,sha256=cS33zWJmFY1fft1XcANcP2jSD5ou7TxvIU2AldhTynM,3004
+dataeval/detectors/drift/_ks.py,sha256=uMc5-NA-lSV1IODrY8uJe87ll3uRJT_oXLJFXy95M1w,3186
+dataeval/detectors/drift/_mmd.py,sha256=uw8axM6dWxTBrCaXwkbldIDcdhe4hmim9yrsbuOwA-0,11523
+dataeval/detectors/drift/_mvdc.py,sha256=ABxGut6KzxF_oM-Hs87WARCR0692dhPVdZNoGGwJaa4,3058
+dataeval/detectors/drift/_nml/__init__.py,sha256=MNyKyZlfTjr5uQql2uBBfRkUdsuduie_WJdn09GYmqg,137
+dataeval/detectors/drift/_nml/_base.py,sha256=o34LcCsD9p1A6u8UdQn-dxIVwC2CMr6uCpC0vq16JX0,2663
+dataeval/detectors/drift/_nml/_chunk.py,sha256=t12eouanRNiu5DJXOaYDZXUvFMqfcp1BETLOufdV79M,13567
+dataeval/detectors/drift/_nml/_domainclassifier.py,sha256=n7Ttq5Ej7sAY9Jn2iagaGj4IIWiG8gmA3wwFizlBqes,7292
+dataeval/detectors/drift/_nml/_result.py,sha256=Nz_qTRu_EcJ1OcywSTVXFm9fx3UyuX66ZWACrffG5dI,3255
+dataeval/detectors/drift/_nml/_thresholds.py,sha256=WGdkLei9w_EvvsRHQzWdDyFVoZHIwM78k_aB3eoh31Q,12060
+dataeval/detectors/drift/_uncertainty.py,sha256=BHlykJ-r7TGLJxdPfoazXnoAJ1qVDzbk5HjAMdsnHz8,5847
+dataeval/detectors/drift/updates.py,sha256=L1PnrPlIE1x6ujCc5mCwjcAZwadVTn-Zjb6MnTDvzJQ,2251
+dataeval/detectors/linters/__init__.py,sha256=xn2zPwUcmsuf-Jd9uw6AVI11C9z1b1Y9fYtuFnXenZ0,404
+dataeval/detectors/linters/duplicates.py,sha256=X5WSEvI_BHkLoXjkaHK6wTnSkx4IjpO_exMRjSlhc70,4963
+dataeval/detectors/linters/outliers.py,sha256=R3-p8kzia77Q3k2grXeRXnRiv7nMhosoPY1sDLQVKrs,9049
+dataeval/detectors/ood/__init__.py,sha256=juCYBDs7CQEAtMhnEpPqF6uTrOIH9kTBSuQ_GRw6a8o,283
+dataeval/detectors/ood/ae.py,sha256=fTrUfFxv6xUqzKpwMC8rW3JrizA16M_bgzqLuBKMrS0,2944
+dataeval/detectors/ood/base.py,sha256=9b-Ljznf0lB1SXF4F_Aj3eJ4Y3ijGEDPMjucUsWOGJM,3051
+dataeval/detectors/ood/mixin.py,sha256=0_o-1HPvgf3-Lf1MSOIfjj5UB8LTLEBGYtJJfyCCzwc,5431
+dataeval/metadata/__init__.py,sha256=XDDmJbOZBNM6pL0r6Nbu6oMRoyAh22IDkPYGndNlkZU,316
+dataeval/metadata/_distance.py,sha256=AABrGoQyD13z9Fqlz3NyfX0Iow_vjBwAugIv6OSRTTE,4187
+dataeval/metadata/_ood.py,sha256=lNPHouj_9WfM_uTtsaiRaPn46RcVy3YebD1c32vDj-c,8981
+dataeval/metadata/_utils.py,sha256=r8qBJT83RblobD5W5zyTVi6vYi51Dwkqswizdbzss-M,1169
+dataeval/metrics/__init__.py,sha256=8VC8q3HuJN3o_WN51Ae2_wXznl3RMXIvA5GYVcy7vr8,225
+dataeval/metrics/bias/__init__.py,sha256=329S1_3WnWqeU4-qVcbe0fMy4lDrj9uKslWHIQf93yg,839
+dataeval/metrics/bias/_balance.py,sha256=FcMOA3ge-sQ-0Id2E0K_6hTjNAV3ejJhlB5r4lxlJWI,5519
+dataeval/metrics/bias/_completeness.py,sha256=BysXU2Jpw33n5dl3acJFEqF3mFGiJLsfG4n5Q2fkTaY,4608
+dataeval/metrics/bias/_coverage.py,sha256=PeUoOiaghUEdn6Ov8z2-am7-fnBVIPcFbJK7Ty5JObA,3647
+dataeval/metrics/bias/_diversity.py,sha256=25udDKmel9IjeVT5nM4dOa1apda66QdRxBc922yuUvI,5830
+dataeval/metrics/bias/_parity.py,sha256=OHUSHPOeC8e1I3acALHbQv5bK4V7SqAT7ds9gNVNzSU,11371
+dataeval/metrics/estimators/__init__.py,sha256=Pnds8uIyAovt2fKqZjiHCIP_kVoBWlVllekYuK5UmmU,568
+dataeval/metrics/estimators/_ber.py,sha256=C30E5LiGGTAfo31zWFYDptDg0R7CTJGJ-a60YgzSkYY,5382
+dataeval/metrics/estimators/_clusterer.py,sha256=1HrpihGTJ63IkNSOy4Ibw633Gllkm1RxKmoKT5MOgt0,1434
+dataeval/metrics/estimators/_divergence.py,sha256=-np4nWNtRrHnvo4xdWuTzkyJJmobyjDnVDBOMjtBS1Y,4003
+dataeval/metrics/estimators/_uap.py,sha256=BULEBbJ9BQ1IcTeZf0x7iI60QHAWCccBOM97FIu9VXA,1928
+dataeval/metrics/stats/__init__.py,sha256=6tA_9nbbM5ObJ6cds8Y1VBtTQiTOxrpGQSFLu_lWGGA,1098
+dataeval/metrics/stats/_base.py,sha256=-TIDSHT-zwNXqWMTM6Nu3BQ11cWP4TFYFaUF40vIChs,12534
+dataeval/metrics/stats/_boxratiostats.py,sha256=ROZrlqgbowkGfCR5PJ5TL7Og40iMOdUqJnsCtaz_Xek,6450
+dataeval/metrics/stats/_dimensionstats.py,sha256=EVO-BlxrZl8qrP09lwPbyWdrG1ZeDtgj4LiswDwEZ1I,2896
+dataeval/metrics/stats/_hashstats.py,sha256=qa1CYRgOebkxqkALfffaPM-kJ074ZbyfpWbfOfuObSs,4758
+dataeval/metrics/stats/_imagestats.py,sha256=gUPNgN5Zwzdr7WnSwbve1NXNsyxd5dy3cSnlR_7guCg,3007
+dataeval/metrics/stats/_labelstats.py,sha256=lz8I6eSd8tFkmQqy5cOG8hn9yxs0mP-Ic9ratFHiuoU,2813
+dataeval/metrics/stats/_pixelstats.py,sha256=5RCQh0OQkHiCkn3DgCPVxKoFfifX_FOtwsnotADSZ0I,3265
+dataeval/metrics/stats/_visualstats.py,sha256=0k6bvAL_d66nQMfG7bydCOFJb7B0dhgG7fqCjVTp1sg,3707
+dataeval/outputs/__init__.py,sha256=geHB5M3QOiFFaQGV4ZwDTTKpqZPvPePbqG7lzaPhaXQ,1741
+dataeval/outputs/_base.py,sha256=7KRWFIEw0UHdhb1em92bPE1YqbMYumAW1QD0QfPwVLc,5900
+dataeval/outputs/_bias.py,sha256=W5QWjtZzMfCaztw6lf0VTZsuSDrNgCcdAvNx6P4fIAo,10254
+dataeval/outputs/_drift.py,sha256=rKn5vqMR6XNujgSqfHsH76oFkoGsUusquZL2Qy4Ae6Y,4581
+dataeval/outputs/_estimators.py,sha256=a2oAIxxEDZ9WLGfMWH8KD-BVUS_SnULRPR-iI9hFPoQ,3047
+dataeval/outputs/_linters.py,sha256=3vI8zsSF-JecQut500A629sICidQLWqhEZcj7o7_cfs,6554
+dataeval/outputs/_metadata.py,sha256=ffZgpX8KWURPHXpOWjbvJ2KRqWQkS2nWuIjKUzoHhMI,1710
+dataeval/outputs/_ood.py,sha256=suLKVXULGtXH0rq9eXHI1d3d2jhGmItJtz4QiQd47A4,1718
+dataeval/outputs/_stats.py,sha256=YDdVQmFcOvb4_NYc_d2a2JCA0Zkuh1o6_qupQkc_X1w,15142
+dataeval/outputs/_utils.py,sha256=HHlGC7sk416m_3Bgn075Qdblz_aPup_UOafJpB0RuXY,893
+dataeval/outputs/_workflows.py,sha256=0xSwPxBATa29tvwJtpovjYrq4la9fkbamHM_qsw-Llc,10799
+dataeval/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dataeval/typing.py,sha256=GDMuef-oFFukNtsiKFmsExHdNvYR_j-tQcsCwZ9reow,7198
+dataeval/utils/__init__.py,sha256=hRvyUK7b3d6JBEV5u47rFcOHEcmDYqAvZQw_T5pDAWw,264
+dataeval/utils/_array.py,sha256=ftX8S6HKAIUOuc1xd30VC3Pz5yUzRglDpCLisWY_tHs,5888
+dataeval/utils/_bin.py,sha256=w3eJ2Szw5eapqQ0cGv731rhNgLFGW0cCz2pXo9I6CuY,7296
+dataeval/utils/_clusterer.py,sha256=XmyW2j_JLMYLds8QYgV0nAfdqxWfNR0ZI-6rnZsyHwU,5630
+dataeval/utils/_fast_mst.py,sha256=pv42flr1Uf5RBa9qDG0YLDXWH7Mr7a9zpauO1HqZXaY,8061
+dataeval/utils/_image.py,sha256=4uxTIOYZZlRJOfNmdA3ek3no3FrLWCK5un48kStMDt8,3578
+dataeval/utils/_method.py,sha256=9B9JQbgqWJBRhQJb7glajUtWaQzUTIUuvrZ9_bisxsM,394
+dataeval/utils/_mst.py,sha256=bLmJmu_1Dtj3hC5gQp3oAiJ_7TKtEjahTqusVRRU4eI,2168
+dataeval/utils/_plot.py,sha256=zP0bEvtrLdws7r1Jte8Camq-q5K5F6T8iuv3bStnEJc,7116
+dataeval/utils/data/__init__.py,sha256=xGzrjrOxOP2DP1tU84AWMKPnSxFvSjM81CTlDg4rNM8,331
+dataeval/utils/data/_dataset.py,sha256=CFK9h-XPN7J-iF2nXol6keMDbGm6VIweFAMAjXRUlhg,9527
+dataeval/utils/data/collate.py,sha256=5egEEKhNNCGeNLChO1p6dZ4Wg6x51VEaMNHz7hEZUxI,3936
+dataeval/utils/data/metadata.py,sha256=L1c2bCiMj0aR0QCoKkjwBujIftJDEMgW_3ZbgeS8WHo,14703
+dataeval/utils/datasets/__init__.py,sha256=pAXqHX76yAoBI8XB3m6zGuW-u3s3PCoIXG5GDzxH7Zs,572
+dataeval/utils/datasets/_antiuav.py,sha256=kA_ia1fYNcJiz9SpCvh-Z8iSc7iJrdogjBI3soyaa7A,8304
+dataeval/utils/datasets/_base.py,sha256=pyfpJda3ku469M3TFRsJn9S2oAiQODOGTlLcdcoEW9U,9031
+dataeval/utils/datasets/_cifar10.py,sha256=hZc_A30yKYBbv2kvVdEkZ9egyEe6XBUnmksoIAoJ-5Y,8265
+dataeval/utils/datasets/_fileio.py,sha256=OASFA9uX3KgfyPb5vza12BlZyAi9Y8Al9lUR_IYPcsM,5449
+dataeval/utils/datasets/_milco.py,sha256=iXf4C1I3Eg_3gHKUe4XPi21yFMBO51zxTIqAkGf9bYg,7869
+dataeval/utils/datasets/_mixin.py,sha256=S8iii-SoYUsFFYNXjw2thlZkpBvRLnZ4XI8wTqOKXgU,1729
+dataeval/utils/datasets/_mnist.py,sha256=uz46sE1Go3TgGjG6x2cXckSVQ0mSg2mhgk8BUvLWjb0,8149
+dataeval/utils/datasets/_ships.py,sha256=6U04HAoM3jgLl1qv-NnxjZeSsBipcqWJBMhBMn5iIUY,5115
+dataeval/utils/datasets/_types.py,sha256=iSKyHXRlGuomXs0FHK6md8lXLQrQQ4fxgVOwr4o81bo,1089
+dataeval/utils/datasets/_voc.py,sha256=pafY112O80isYkrdy7Quie9SBm_TmYhREuyl8SxtsR0,24586
+dataeval/utils/torch/__init__.py,sha256=dn5mjCrFp0b1aL_UEURhONU0Ag0cmXoTOBSGagpkTiA,325
+dataeval/utils/torch/_blocks.py,sha256=HVhBTMMD5NA4qheMUgyol1KWiKZDIuc8k5j4RcMKmhk,1466
+dataeval/utils/torch/_gmm.py,sha256=XM68GNEP97EjaB1U49-ZXRb81d0CEFnPS910alrcB3g,3740
+dataeval/utils/torch/_internal.py,sha256=vHy-DzPhmvE8h3wmWc3aciBJ8nDGzQ1z1jTZgGjmDyM,4154
+dataeval/utils/torch/models.py,sha256=1idpXyjrYcCBSsbxxRUOto8xr4MJNjDEqQHiIXVU5Zc,9700
+dataeval/utils/torch/trainer.py,sha256=Oc2lK13uPGhmLYbmAqlPWyKxgG4YJFlnSXCqFHUZbdA,5528
+dataeval/workflows/__init__.py,sha256=ou8y0KO-d6W5lgmcyLjKlf-J_ckP3vilW7wHkgiDlZ4,255
+dataeval/workflows/sufficiency.py,sha256=j-R8dg4XE6a66p_oTXG2GNzgg3vGk85CTblxhFXaxog,8513
+dataeval-0.86.2.dist-info/LICENSE.txt,sha256=uAooygKWvX6NbU9Ran9oG2msttoG8aeTeHSTe5JeCnY,1061
+dataeval-0.86.2.dist-info/METADATA,sha256=6y6bI8GBv_VjBs1mpjAZJ9R5UBTKT7RHQRRUGJdyPCk,5353
+dataeval-0.86.2.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+dataeval-0.86.2.dist-info/RECORD,,