dataeval 0.83.0__py3-none-any.whl → 0.84.1__py3-none-any.whl

dataeval/utils/data/datasets/_voc.py

@@ -14,6 +14,8 @@ from dataeval.utils.data.datasets._base import (
     BaseODDataset,
     BaseSegDataset,
     DataLocation,
+    _TArray,
+    _TTarget,
 )
 from dataeval.utils.data.datasets._mixin import BaseDatasetNumpyMixin, BaseDatasetTorchMixin
 from dataeval.utils.data.datasets._types import ObjectDetectionTarget, SegmentationTarget
@@ -21,9 +23,6 @@ from dataeval.utils.data.datasets._types import ObjectDetectionTarget, Segmentat
 if TYPE_CHECKING:
     from dataeval.typing import Transform
 
-_TArray = TypeVar("_TArray")
-_TTarget = TypeVar("_TTarget")
-
 VOCClassStringMap = Literal[
     "aeroplane",
     "bicycle",
@@ -121,19 +120,19 @@ class BaseVOCDataset(BaseDataset[_TArray, _TTarget, list[str]]):
     def __init__(
         self,
         root: str | Path,
-        year: Literal["2007", "2008", "2009", "2010", "2011", "2012"] = "2012",
         image_set: Literal["train", "val", "test", "base"] = "train",
-        download: bool = False,
+        year: Literal["2007", "2008", "2009", "2010", "2011", "2012"] = "2012",
         transforms: Transform[_TArray] | Sequence[Transform[_TArray]] | None = None,
+        download: bool = False,
         verbose: bool = False,
     ) -> None:
         self.year = year
         self._resource_index = self._get_year_image_set_index(year, image_set)
         super().__init__(
             root,
-            download,
             image_set,
             transforms,
+            download,
             verbose,
         )
 
@@ -191,10 +190,14 @@ class BaseVOCDataset(BaseDataset[_TArray, _TTarget, list[str]]):
         for entry in data:
             file_name = Path(entry).name
             file_stem = Path(entry).stem
-            # Remove file extension and split by "_"
-            parts = file_stem.split("_")
-            file_meta["year"].append(parts[0])
-            file_meta["image_id"].append(parts[1])
+            if self.year != "2007":
+                # Remove file extension and split by "_"
+                parts = file_stem.split("_")
+                file_meta["year"].append(parts[0])
+                file_meta["image_id"].append(parts[1])
+            else:
+                file_meta["year"].append(self.year)
+                file_meta["image_id"].append(file_stem)
             file_meta["mask_path"].append(str(seg_folder / file_name))
             annotations.append(str(ann_folder / file_stem) + ".xml")
 
@@ -250,9 +253,6 @@ class VOCDetection(
     ----------
     root : str or pathlib.Path
         Root directory of dataset where the ``vocdataset`` folder exists.
-    download : bool, default False
-        If True, downloads the dataset from the internet and puts it in root directory.
-        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     image_set : "train", "val", "test", or "base", default "train"
         If "test", then dataset year must be "2007".
         If "base", then the combined dataset of "train" and "val" is returned.
@@ -260,6 +260,9 @@ class VOCDetection(
         The dataset year.
     transforms : Transform, Sequence[Transform] or None, default None
         Transform(s) to apply to the data.
+    download : bool, default False
+        If True, downloads the dataset from the internet and puts it in root directory.
+        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     verbose : bool, default False
         If True, outputs print statements.
 
@@ -267,6 +270,8 @@ class VOCDetection(
     ----------
     path : pathlib.Path
         Location of the folder containing the data.
+    year : "2007", "2008", "2009", "2010", "2011" or "2012"
+        The selected dataset year.
     image_set : "train", "val", "test" or "base"
         The selected image set from the dataset.
     index2label : dict[int, str]
@@ -279,6 +284,10 @@ class VOCDetection(
         The transforms to be applied to the data.
     size : int
         The size of the dataset.
+
+    Note
+    ----
+    Data License: `Flickr Terms of Use <http://www.flickr.com/terms.gne?legacy=1>`_
     """
 
 
@@ -294,9 +303,6 @@ class VOCDetectionTorch(
     ----------
     root : str or pathlib.Path
         Root directory of dataset where the ``vocdataset`` folder exists.
-    download : bool, default False
-        If True, downloads the dataset from the internet and puts it in root directory.
-        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     image_set : "train", "val", "test", or "base", default "train"
         If "test", then dataset year must be "2007".
         If "base", then the combined dataset of "train" and "val" is returned.
@@ -304,6 +310,9 @@ class VOCDetectionTorch(
         The dataset year.
     transforms : Transform, Sequence[Transform] or None, default None
         Transform(s) to apply to the data.
+    download : bool, default False
+        If True, downloads the dataset from the internet and puts it in root directory.
+        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     verbose : bool, default False
         If True, outputs print statements.
 
@@ -311,6 +320,8 @@ class VOCDetectionTorch(
     ----------
     path : pathlib.Path
         Location of the folder containing the data.
+    year : "2007", "2008", "2009", "2010", "2011" or "2012"
+        The selected dataset year.
     image_set : "train", "val", "test" or "base"
         The selected image set from the dataset.
     index2label : dict[int, str]
@@ -323,6 +334,10 @@ class VOCDetectionTorch(
         The transforms to be applied to the data.
     size : int
         The size of the dataset.
+
+    Note
+    ----
+    Data License: `Flickr Terms of Use <http://www.flickr.com/terms.gne?legacy=1>`_
     """
 
 
@@ -338,9 +353,6 @@ class VOCSegmentation(
     ----------
     root : str or pathlib.Path
         Root directory of dataset where the ``vocdataset`` folder exists.
-    download : bool, default False
-        If True, downloads the dataset from the internet and puts it in root directory.
-        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     image_set : "train", "val", "test", or "base", default "train"
         If "test", then dataset year must be "2007".
         If "base", then the combined dataset of "train" and "val" is returned.
@@ -348,6 +360,9 @@ class VOCSegmentation(
         The dataset year.
     transforms : Transform, Sequence[Transform] or None, default None
         Transform(s) to apply to the data.
+    download : bool, default False
+        If True, downloads the dataset from the internet and puts it in root directory.
+        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     verbose : bool, default False
         If True, outputs print statements.
 
@@ -355,6 +370,8 @@ class VOCSegmentation(
     ----------
     path : pathlib.Path
         Location of the folder containing the data.
+    year : "2007", "2008", "2009", "2010", "2011" or "2012"
+        The selected dataset year.
     image_set : "train", "val", "test" or "base"
         The selected image set from the dataset.
     index2label : dict[int, str]
@@ -367,6 +384,10 @@ class VOCSegmentation(
         The transforms to be applied to the data.
     size : int
         The size of the dataset.
+
+    Note
+    ----
+    Data License: `Flickr Terms of Use <http://www.flickr.com/terms.gne?legacy=1>`_
     """
 
     def _load_data(self) -> tuple[list[str], list[str], dict[str, list[Any]]]:

dataeval/utils/data/selections/__init__.py

@@ -1,6 +1,7 @@
 """Provides selection classes for selecting subsets of Computer Vision datasets."""
 
 __all__ = [
+    "ClassBalance",
     "ClassFilter",
     "Indices",
     "Limit",
@@ -9,6 +10,7 @@ __all__ = [
     "Shuffle",
 ]
 
+from dataeval.utils.data.selections._classbalance import ClassBalance
 from dataeval.utils.data.selections._classfilter import ClassFilter
 from dataeval.utils.data.selections._indices import Indices
 from dataeval.utils.data.selections._limit import Limit

dataeval/utils/data/selections/_classbalance.py

@@ -0,0 +1,38 @@
+from __future__ import annotations
+
+__all__ = []
+
+
+import numpy as np
+
+from dataeval.typing import Array, ImageClassificationDatum
+from dataeval.utils._array import as_numpy
+from dataeval.utils.data._selection import Select, Selection, SelectionStage
+
+
+class ClassBalance(Selection[ImageClassificationDatum]):
+    """
+    Balance the dataset by class.
+
+    Note
+    ----
+    The total number of instances of each class will be equalized which may result
+    in a lower total number of instances than specified by the selection limit.
+    """
+
+    stage = SelectionStage.FILTER
+
+    def __call__(self, dataset: Select[ImageClassificationDatum]) -> None:
+        class_indices: dict[int, list[int]] = {}
+        for i, idx in enumerate(dataset._selection):
+            target = dataset._dataset[idx][1]
+            if isinstance(target, Array):
+                label = int(np.argmax(as_numpy(target)))
+            else:
+                # ObjectDetectionTarget and SegmentationTarget not supported yet
+                raise TypeError("ClassFilter only supports classification targets as an array of confidence scores.")
+            class_indices.setdefault(label, []).append(i)
+
+        per_class_limit = min(min(len(c) for c in class_indices.values()), dataset._size_limit // len(class_indices))
+        subselection = sorted([i for v in class_indices.values() for i in v[:per_class_limit]])
+        dataset._selection = [dataset._selection[i] for i in subselection]

dataeval/utils/data/selections/_classfilter.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 __all__ = []
 
-from typing import Sequence, TypeVar
+from typing import Sequence
 
 import numpy as np
 
@@ -10,50 +10,35 @@ from dataeval.typing import Array, ImageClassificationDatum
 from dataeval.utils._array import as_numpy
 from dataeval.utils.data._selection import Select, Selection, SelectionStage
 
-TImageClassificationDatum = TypeVar("TImageClassificationDatum", bound=ImageClassificationDatum)
 
-
-class ClassFilter(Selection[TImageClassificationDatum]):
+class ClassFilter(Selection[ImageClassificationDatum]):
     """
-    Filter and balance the dataset by class.
+    Filter the dataset by class.
 
     Parameters
     ----------
-    classes : Sequence[int] or None, default None
-        The classes to filter by. If None, all classes are included.
-    balance : bool, default False
-        Whether to balance the classes.
-
-    Note
-    ----
-    If `balance` is True, the total number of instances of each class will
-    be equalized. This may result in a lower total number of instances.
+    classes : Sequence[int]
+        The classes to filter by.
     """
 
     stage = SelectionStage.FILTER
 
-    def __init__(self, classes: Sequence[int] | None = None, balance: bool = False) -> None:
+    def __init__(self, classes: Sequence[int]) -> None:
         self.classes = classes
-        self.balance = balance
 
-    def __call__(self, dataset: Select[TImageClassificationDatum]) -> None:
-        if self.classes is None and not self.balance:
+    def __call__(self, dataset: Select[ImageClassificationDatum]) -> None:
+        if not self.classes:
             return
 
-        per_class_limit = dataset._size_limit // len(self.classes) if self.classes and self.balance else 0
-        class_indices: dict[int, list[int]] = {} if self.classes is None else {k: [] for k in self.classes}
-        for i, idx in enumerate(dataset._selection):
+        selection = []
+        for idx in dataset._selection:
             target = dataset._dataset[idx][1]
             if isinstance(target, Array):
                 label = int(np.argmax(as_numpy(target)))
             else:
                 # ObjectDetectionTarget and SegmentationTarget not supported yet
                 raise TypeError("ClassFilter only supports classification targets as an array of confidence scores.")
-            if not self.classes or label in self.classes:
-                class_indices.setdefault(label, []).append(i)
-            if per_class_limit and all(len(indices) >= per_class_limit for indices in class_indices.values()):
-                break
-
-        per_class_limit = min(len(c) for c in class_indices.values()) if self.balance else dataset._size_limit
-        subselection = sorted([i for v in class_indices.values() for i in v[:per_class_limit]])
-        dataset._selection = [dataset._selection[i] for i in subselection]
+            if label in self.classes:
+                selection.append(idx)
+
+        dataset._selection = selection

dataeval/utils/data/selections/_prioritize.py

@@ -272,7 +272,7 @@ class Prioritize(Selection[Any]):
             return _KMeansComplexitySorter(samples, self._c)
 
     def _to_normalized_ndarray(self, embeddings: Embeddings, selection: list[int] | None = None) -> NDArray[Any]:
-        emb: NDArray[Any] = embeddings.to_tensor(selection).cpu().numpy()
+        emb: NDArray[Any] = embeddings.to_numpy(selection)
         emb /= max(np.max(np.linalg.norm(emb, axis=1)), EPSILON)
         return emb
 

dataeval/utils/data/selections/_shuffle.py

@@ -8,7 +8,7 @@ import numpy as np
 from numpy.random import BitGenerator, Generator, SeedSequence
 from numpy.typing import NDArray
 
-from dataeval.typing import Array, ArrayLike
+from dataeval.typing import Array
 from dataeval.utils._array import as_numpy
 from dataeval.utils.data._selection import Select, Selection, SelectionStage
 
@@ -30,7 +30,7 @@ class Shuffle(Selection[Any]):
     seed: int | NDArray[Any] | SeedSequence | BitGenerator | Generator | None
     stage = SelectionStage.ORDER
 
-    def __init__(self, seed: int | ArrayLike | SeedSequence | BitGenerator | Generator | None = None):
+    def __init__(self, seed: int | Sequence[int] | Array | SeedSequence | BitGenerator | Generator | None = None):
         self.seed = as_numpy(seed) if isinstance(seed, (Sequence, Array)) else seed
 
     def __call__(self, dataset: Select[Any]) -> None:

dataeval/utils/metadata.py

@@ -214,7 +214,7 @@ def flatten(
                 output[k] = cv
             else:
                 dropped_inner.setdefault(k, set()).add(DropReason.INCONSISTENT_KEY)
-        elif not isinstance(cv, list):
+        else:
             output[k] = cv if not size else [cv] * size
 
     if fully_qualified:

dataeval/utils/torch/_internal.py

@@ -2,7 +2,6 @@ from __future__ import annotations
 
 __all__ = []
 
-from functools import partial
 from typing import Any, Callable
 
 import numpy as np
@@ -12,16 +11,16 @@ from torch.utils.data import DataLoader, TensorDataset
 from tqdm import tqdm
 
 from dataeval.config import DeviceLike, get_device
+from dataeval.typing import Array
 
 
 def predict_batch(
-    x: NDArray[Any] | torch.Tensor,
-    model: Callable | torch.nn.Module | torch.nn.Sequential,
+    x: Array,
+    model: torch.nn.Module,
     device: DeviceLike | None = None,
     batch_size: int = int(1e10),
     preprocess_fn: Callable[[torch.Tensor], torch.Tensor] | None = None,
-    dtype: type[np.generic] | torch.dtype = np.float32,
-) -> NDArray[Any] | torch.Tensor | tuple[Any, ...]:
+) -> torch.Tensor:
     """
     Make batch predictions on a model.
 
@@ -29,7 +28,7 @@ def predict_batch(
     ----------
     x : np.ndarray | torch.Tensor
         Batch of instances.
-    model : Callable | nn.Module | nn.Sequential
+    model : nn.Module
         PyTorch model.
     device : DeviceLike or None, default None
         The hardware device to use if specified, otherwise uses the DataEval
@@ -38,21 +37,18 @@ def predict_batch(
         Batch size used during prediction.
     preprocess_fn : Callable | None, default None
         Optional preprocessing function for each batch.
-    dtype : np.dtype | torch.dtype, default np.float32
-        Model output type, either a :term:`NumPy` or torch dtype, e.g. np.float32 or torch.float32.
 
     Returns
     -------
-    NDArray | torch.Tensor | tuple
-        Numpy array, torch tensor or tuples of those with model outputs.
+    torch.Tensor
+        PyTorch tensor with model outputs.
     """
     device = get_device(device)
-    if isinstance(x, np.ndarray):
-        x = torch.tensor(x, device=device)
+    if isinstance(model, torch.nn.Module):
+        model = model.to(device).eval()
+    x = torch.tensor(x, device=device)
     n = len(x)
     n_minibatch = int(np.ceil(n / batch_size))
-    return_np = not isinstance(dtype, torch.dtype)
-    preds_tuple = None
     preds_array = []
     with torch.no_grad():
         for i in range(n_minibatch):
@@ -60,28 +56,9 @@ def predict_batch(
             x_batch = x[istart:istop]
             if isinstance(preprocess_fn, Callable):
                 x_batch = preprocess_fn(x_batch)
+            preds_array.append(model(x_batch.to(dtype=torch.float32)).cpu())
 
-            preds_tmp = model(x_batch.to(dtype=torch.float32))
-            if isinstance(preds_tmp, (list, tuple)):
-                if preds_tuple is None:  # init tuple with lists to store predictions
-                    preds_tuple = tuple([] for _ in range(len(preds_tmp)))
-                for j, p in enumerate(preds_tmp):
-                    p = p.cpu() if isinstance(p, torch.Tensor) else p
-                    preds_tuple[j].append(p if not return_np or isinstance(p, np.ndarray) else p.numpy())
-            elif isinstance(preds_tmp, (np.ndarray, torch.Tensor)):
-                preds_tmp = preds_tmp.cpu() if isinstance(preds_tmp, torch.Tensor) else preds_tmp
-                preds_array.append(
-                    preds_tmp if not return_np or isinstance(preds_tmp, np.ndarray) else preds_tmp.numpy()
-                )
-            else:
-                raise TypeError(
-                    f"Model output type {type(preds_tmp)} not supported. The model \
-                    output type needs to be one of list, tuple, NDArray or \
-                    torch.Tensor."
-                )
-    concat = partial(np.concatenate, axis=0) if return_np else partial(torch.cat, dim=0)
-    out = tuple(concat(p) for p in preds_tuple) if preds_tuple is not None else concat(preds_array)
-    return out
+    return torch.cat(preds_array, dim=0)
 
 
 def trainer(

{dataeval-0.83.0.dist-info → dataeval-0.84.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dataeval
-Version: 0.83.0
+Version: 0.84.1
 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
@@ -82,8 +82,7 @@ using MAITE-compliant datasets and models.
 
 **Python versions:** 3.9 - 3.12
 
-**Supported packages**: *NumPy*, *Pandas*, *Sci-kit learn*, *MAITE*, *NRTK*,
-*Gradient*
+**Supported packages**: *NumPy*, *Pandas*, *Sci-kit learn*, *MAITE*, *NRTK*
 
 Choose your preferred method of installation below or follow our
 [installation guide](https://dataeval.readthedocs.io/en/v0.74.2/installation.html).

{dataeval-0.83.0.dist-info → dataeval-0.84.1.dist-info}/RECORD

@@ -1,20 +1,19 @@
-dataeval/__init__.py,sha256=uL-JSd_dKVJpGx4H8f6aOiQVpli46zeTLFqjb4Pa69c,1636
+dataeval/__init__.py,sha256=QzrctVrymZuLN8tnHcF1wp0RTXYM3WSWMozX3NOzIos,1636
 dataeval/_log.py,sha256=Mn5bRWO0cgtAYd5VGYSFiPgu57ta3zoktrtHAZ1m3dU,357
-dataeval/config.py,sha256=oQ0XQsgIF4_z4n1j0Di6B-JCRUFzzPgJgpQUm3ZlYhs,3539
+dataeval/config.py,sha256=lD1YDH8HosFeRU5rQEYRBcmXMZy-csWaMlJTRZGd9iU,3582
 dataeval/detectors/__init__.py,sha256=3Sg-XWlwr75zEEH3hZKA4nWMtGvaRlnfzTWvZG_Ak6U,189
-dataeval/detectors/drift/__init__.py,sha256=6is_XBtG1d-vUbhHvqXGOdnAwxJ7NA5yRfURn7pCeIw,651
-dataeval/detectors/drift/_base.py,sha256=mJdKvyROgWvz-p1VlAIJqUI6BAj9ss8riUvR5An5wIw,13459
-dataeval/detectors/drift/_cvm.py,sha256=H2w-I0eMD7yP-CSmpdodeJ0-TYznJT7w_H7JuobESow,3859
-dataeval/detectors/drift/_ks.py,sha256=-5k3RBPA3kadX7oD14Wc52rAqQf1udwFeW7Qf3Sv4Tw,4058
-dataeval/detectors/drift/_mmd.py,sha256=NEXowx9UHIvmEKS8sqssw6PMLJMh0BZPhRNX1hYlkz4,7239
-dataeval/detectors/drift/_torch.py,sha256=VrFCyTaRrUslFPy_mYZ4UL70LZ8faH4eHwLurZ9qqNE,7628
-dataeval/detectors/drift/_uncertainty.py,sha256=O5h6_bJbeQEE660SLLP8k-EHqImmKegIcxzcnUKI7X4,5714
-dataeval/detectors/drift/updates.py,sha256=Btu2iaZW7fbO59G1w5v3ykFot0YPzy2U6VjF0d440VE,2195
+dataeval/detectors/drift/__init__.py,sha256=gD8aY5PotS-S2ot7iB_z_zzSOjIbQLw5znFBNj0jtHE,646
+dataeval/detectors/drift/_base.py,sha256=PdWyEuYqExFdyxvyOh7Q8yXnjNm0D3KfpDUn0bUixtY,7580
+dataeval/detectors/drift/_cvm.py,sha256=CSEyNN9u1MzUI6QmCSlexTUSlHzK1kYh36Nv2L72WbY,3016
+dataeval/detectors/drift/_ks.py,sha256=ifFb_0JcyykJyF9DAVkQqWCXc-3aA0AC8c8to_oOPKo,3198
+dataeval/detectors/drift/_mmd.py,sha256=DOHBNyNNxosR67yM9HTxbvqp1IZ8_KSvTVlX-JtKtjM,11601
+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=tcxniL8rRZkDdQqfuS502UmfKxS3a7iRA22Dtt_vQIk,4935
-dataeval/detectors/linters/outliers.py,sha256=Hln2dPQZjF_uV2QYptA_o6ZF3ugyCImVT-XLDB2-q3A,9042
+dataeval/detectors/linters/duplicates.py,sha256=x36-0EAlO_AuOttvElJOZCa0R3VzrlII0NxjwhdkrpE,4969
+dataeval/detectors/linters/outliers.py,sha256=Z0Sbtluu2im1IRGsjhXF2AhrShKDrEkF8BWzAZyPwlA,9054
 dataeval/detectors/ood/__init__.py,sha256=juCYBDs7CQEAtMhnEpPqF6uTrOIH9kTBSuQ_GRw6a8o,283
-dataeval/detectors/ood/ae.py,sha256=YQfhB1ShQLjM1V4uCz9Oo2tCZpOfAZ_-SBCAl4Ac67Y,2921
+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/detectors/ood/vae.py,sha256=Fcq0-WbLhzYCgYOAJPBklHm7yuXmFJuEpBkhgwM5kiA,2291
@@ -23,8 +22,9 @@ dataeval/metadata/_distance.py,sha256=xsXMMg1pJkHcEZ-KIlqv9YOGYVID3ELjt3-fr1QVnO
 dataeval/metadata/_ood.py,sha256=HbS5MusWl62hjixUAd-xaaT0KXkYY1M-MlnUaAI_-8M,12751
 dataeval/metadata/_utils.py,sha256=r8qBJT83RblobD5W5zyTVi6vYi51Dwkqswizdbzss-M,1169
 dataeval/metrics/__init__.py,sha256=8VC8q3HuJN3o_WN51Ae2_wXznl3RMXIvA5GYVcy7vr8,225
-dataeval/metrics/bias/__init__.py,sha256=1yTLmgiu1kwT_7ZWcjOUbj8R0NJ0DjGoCuWdA0_T7kc,683
+dataeval/metrics/bias/__init__.py,sha256=329S1_3WnWqeU4-qVcbe0fMy4lDrj9uKslWHIQf93yg,839
 dataeval/metrics/bias/_balance.py,sha256=UnUgbPk2ybFfS5qxv8e_uim7RxamWj0UQP71x3omGs0,6158
+dataeval/metrics/bias/_completeness.py,sha256=BysXU2Jpw33n5dl3acJFEqF3mFGiJLsfG4n5Q2fkTaY,4608
 dataeval/metrics/bias/_coverage.py,sha256=PeUoOiaghUEdn6Ov8z2-am7-fnBVIPcFbJK7Ty5JObA,3647
 dataeval/metrics/bias/_diversity.py,sha256=U_l4oYjH39rON2Io0BdCIwJxxob0cKTW8bZNufG0CWs,5820
 dataeval/metrics/bias/_parity.py,sha256=8JRZv4wLpxN9zTvMDlcpKgz-2nO-9eVjqccODcf2nbw,11535
@@ -34,29 +34,29 @@ dataeval/metrics/estimators/_clusterer.py,sha256=1HrpihGTJ63IkNSOy4Ibw633Gllkm1R
 dataeval/metrics/estimators/_divergence.py,sha256=QDWl1lyAYoO9D3Ho7qOHSk6ud8Gi2MGuXEsYwO1HxvA,4043
 dataeval/metrics/estimators/_uap.py,sha256=BULEBbJ9BQ1IcTeZf0x7iI60QHAWCccBOM97FIu9VXA,1928
 dataeval/metrics/stats/__init__.py,sha256=6tA_9nbbM5ObJ6cds8Y1VBtTQiTOxrpGQSFLu_lWGGA,1098
-dataeval/metrics/stats/_base.py,sha256=rn0CrRCvVh3QLDEi_JlOFVUoQ-xtclnOoHt_o1E26J4,10656
+dataeval/metrics/stats/_base.py,sha256=YIfOVGd7E19B4dpAnzDYRQkaikvRRyJIpznJNfVtPdw,10750
 dataeval/metrics/stats/_boxratiostats.py,sha256=8Kd2FTZ5PLNYZfdAjU_R385gb0Z16JY0L9H_d5ZhgQs,6341
-dataeval/metrics/stats/_dimensionstats.py,sha256=h2wCLn4UuW7-GV6tM5E1SqSeGa_-4ie9oaEXpSC7EKI,2690
-dataeval/metrics/stats/_hashstats.py,sha256=yD6cXMvOo10-xtwUr7ftBRbCqMhReNfQJMInEWV_8Mk,4757
-dataeval/metrics/stats/_imagestats.py,sha256=hyjijPXAfUIJ1lwWiIyYK9VSLiq7Vg2-YhJ5Q8s1rkY,2979
-dataeval/metrics/stats/_labelstats.py,sha256=PtGyqj4RHw0cyLAWAR9FzZGqgA81AtxLGHZiuMAL2h0,4100
-dataeval/metrics/stats/_pixelstats.py,sha256=Q0-ldG-znDYBP_qTqm6S4qYm0ZV5FTTHf8MlyGHSYEc,3235
-dataeval/metrics/stats/_visualstats.py,sha256=ZxBDTerZ8ixibY2pGl7mwwcIz3DWl-k_Jb4YwBjHLNw,3686
-dataeval/outputs/__init__.py,sha256=uxTAr1Kn0QNwC7zn1U_5WBAgwZxupM3JGgD25DyO6yI,1655
+dataeval/metrics/stats/_dimensionstats.py,sha256=73mFP-Myxne0peFliwvTntc0kk4cpq0krzMvSLDSIMM,2702
+dataeval/metrics/stats/_hashstats.py,sha256=gp9X_pnTT3mPH9YNrWLdn2LQPK_epJ3dQRoyOCwmKlg,4758
+dataeval/metrics/stats/_imagestats.py,sha256=gUPNgN5Zwzdr7WnSwbve1NXNsyxd5dy3cSnlR_7guCg,3007
+dataeval/metrics/stats/_labelstats.py,sha256=WbvXZ831a5BDfm58HF8Z8i5JUV1tgw7tcfzUh8pOXSo,2825
+dataeval/metrics/stats/_pixelstats.py,sha256=SfergRbjNJE4h0xqe-0c8RnKtZmEkZ9MwExdipLSGvg,3247
+dataeval/metrics/stats/_visualstats.py,sha256=cq4AbF2B50Ihbzb86FphcnKQ1TSwNnP3PsnbpiPQZWw,3698
+dataeval/outputs/__init__.py,sha256=ciK-RdXgtn_s7MSCUW1UXvrXltMbltqbpfe9_V7xGrI,1701
 dataeval/outputs/_base.py,sha256=aZFbgybnZSQ3ws7QYRLTbDFqUfBFRVtIwX2LZfeGFUA,5703
-dataeval/outputs/_bias.py,sha256=O5RHbTUJDwkwJfz2-YoOfRb4eDl5Tg1UFVtvs025wfA,12173
+dataeval/outputs/_bias.py,sha256=GwbjLdppUODOeudYb_7ki2ejDmAYthlRKGijVwgVePE,12407
 dataeval/outputs/_drift.py,sha256=gOiu2C-ERTWiRqlP0auMYxPBGdm9HecWPqWfg7I4tZg,2015
 dataeval/outputs/_estimators.py,sha256=a2oAIxxEDZ9WLGfMWH8KD-BVUS_SnULRPR-iI9hFPoQ,3047
 dataeval/outputs/_linters.py,sha256=YOdjrfm8ypdRrqYOaPM9nc6wVJI3-ita3Haj7LHDNaw,6416
 dataeval/outputs/_metadata.py,sha256=ffZgpX8KWURPHXpOWjbvJ2KRqWQkS2nWuIjKUzoHhMI,1710
 dataeval/outputs/_ood.py,sha256=suLKVXULGtXH0rq9eXHI1d3d2jhGmItJtz4QiQd47A4,1718
-dataeval/outputs/_stats.py,sha256=PhRdyWWZxewzenFx0MxK9y9ZLE2MnMA-a4-JeSJ_Bs8,13180
+dataeval/outputs/_stats.py,sha256=c73Yc3Kkrl-MN6BGKe1V0Yr6Ix2Yp_DZZfFSp8fZMZ0,13180
 dataeval/outputs/_utils.py,sha256=HHlGC7sk416m_3Bgn075Qdblz_aPup_UOafJpB0RuXY,893
 dataeval/outputs/_workflows.py,sha256=MkRD6ubI4NCBXb9v3kjXy64cUGs3G-JKkBdOpRD9XVE,10750
 dataeval/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-dataeval/typing.py,sha256=YQ1KteeK1zf2mcWwngWwQP8EC3pI4WsvAzp_x179b4g,6568
+dataeval/typing.py,sha256=zn6smomSdcO7EeZpeeSP5-8sknTdgUuU7TKe-3UFVrg,6550
 dataeval/utils/__init__.py,sha256=T8F8zJh4ZAeu0wDzfpld92I2zJg9mWBmkGCHrDPU7gk,264
-dataeval/utils/_array.py,sha256=fc04sYShIdsRS4qtG1UCnlGGk-yVRxlOHTNAmW7NpDY,4990
+dataeval/utils/_array.py,sha256=KqAdXEMjcXYvdWdYEEoEbigwQJ4S9VYxQS3sRFeY5XY,5929
 dataeval/utils/_bin.py,sha256=nylthmsC3vzLHLhlUMACvZs--h7xvAh9Pt75InaQJW8,7322
 dataeval/utils/_clusterer.py,sha256=fw5x-2QN0TIbiodDKHZxRgxKHINedpPcOklzce0Rbjg,5436
 dataeval/utils/_fast_mst.py,sha256=4_7ykVihCL5jWtxcGnrecIsDQo65kUml9SZ1JxgBZYY,7172
@@ -65,41 +65,42 @@ dataeval/utils/_method.py,sha256=9B9JQbgqWJBRhQJb7glajUtWaQzUTIUuvrZ9_bisxsM,394
 dataeval/utils/_mst.py,sha256=f0vXytTUjlOS6AyL7c6PkXmaHuuGUK-vMLpq-5xMgxk,2183
 dataeval/utils/_plot.py,sha256=mTRQNbJsA42QMiOwZbJaH8sNYgP996QFDEGVVE9HSgY,7076
 dataeval/utils/data/__init__.py,sha256=vldQ2ZXl8gnI3s4vAGqUUVi6dc_R58F3JMSpbCOyFRI,820
-dataeval/utils/data/_dataset.py,sha256=tjZUJnxj9IY71GKqdKltrwufkn0EC0S3a6ylrW5Bc2s,7756
-dataeval/utils/data/_embeddings.py,sha256=fKGFJXhb4ajnBE3jrKxIvBAhBQ6HpcYYkpO_sAk3jTE,3669
-dataeval/utils/data/_images.py,sha256=pv_vvpH8hWxPgLvjeVC2mZiyZivZFNLARNIOXam5ceY,1984
-dataeval/utils/data/_metadata.py,sha256=VqeePp7NtoFFWzmIhH4fn-cjrnATpgzgzs-d73cnBXM,14370
-dataeval/utils/data/_selection.py,sha256=nlslafwAfoZ5d5K_v9bIIvij-UP0NcalKqH4Nw7A-S4,4553
-dataeval/utils/data/_split.py,sha256=YdsqTRjKbdSfg8w0f4XgX7j0uOSdtfzvvyObAzyqgI0,18433
+dataeval/utils/data/_dataset.py,sha256=MHY582yRm4FxQkkLWUhKZBb7ZyvWypM6ldUG89vd3uE,7936
+dataeval/utils/data/_embeddings.py,sha256=iDtfLJY1uHoTP4UdQoOt-3wopc6kSOXH_4CVNnmXXA4,8356
+dataeval/utils/data/_images.py,sha256=WF9XJRka8ohUdyI2IKBMAy3JoJhOm1iC-8tbYl8woRM,2642
+dataeval/utils/data/_metadata.py,sha256=62z_qHjoGjiMdpuT36QpNhbWy2UClHWUcjHHlIWT470,14464
+dataeval/utils/data/_selection.py,sha256=2c6DjyeDIJapbI7xL36eBxFnJHIP8Yxt3oU3rBGMqLk,3948
+dataeval/utils/data/_split.py,sha256=q-2RwllJgazwuyxB_GoBqK_nLkqIjyTVr2SQKj_7lhw,16767
 dataeval/utils/data/_targets.py,sha256=ws5d9wRiDkIuOV7GSAKNxzgSm6AWTgb0BFroQK5nAmM,3057
 dataeval/utils/data/collate.py,sha256=Z5nmBnWV_IoJzMp_tj8RCKjMJA9sSCY_zZITqISGixc,3865
 dataeval/utils/data/datasets/__init__.py,sha256=jBrswiERrvBx4pJQJZIq_B5UE-Wy8a2_SBfM2crG8R8,511
-dataeval/utils/data/datasets/_base.py,sha256=CZ-hb-yWPLdnTQ3pURJMcityQ42ZNYj_Lbb1P5Junn4,8793
-dataeval/utils/data/datasets/_cifar10.py,sha256=I6HKksE2escos1aTdiZJObtiVXChBlez5BDa0eBfJ_Y,5449
+dataeval/utils/data/datasets/_base.py,sha256=827nSVhZ-tqeHw1HQ7Qj060CSDd90fEWZomN6FaWnQA,8872
+dataeval/utils/data/datasets/_cifar10.py,sha256=R7QgcCHowAkqhEXOvUhybXTmMlA4BJXkTuAeV9uDgfU,5449
 dataeval/utils/data/datasets/_fileio.py,sha256=SixIk5nIlIwJdX9zjNXS10vHA3hL8aaYbqHsDg1xSpY,6447
-dataeval/utils/data/datasets/_milco.py,sha256=ScBe7Ux-J9Kxs33jeKffhWKeSb8GCrWznTyEUt95Vt4,6369
+dataeval/utils/data/datasets/_milco.py,sha256=bVVDl5W8TdTPU2RiwoPXrfFDM1rKyb-LslwTThBXEr0,7583
 dataeval/utils/data/datasets/_mixin.py,sha256=FJgZP_cpJkgAHA3j3ai_j3Wt7aFSEjIMVmt9NpvVXzg,1757
-dataeval/utils/data/datasets/_mnist.py,sha256=iWWI9mq6TbZm7eTL9btzqjCNMhgXrLHQeMKENr7USsk,7988
-dataeval/utils/data/datasets/_ships.py,sha256=p3fScYLW2f1wUEPOroCX5nOFti0vMOSjeYltj6ox53U,4777
+dataeval/utils/data/datasets/_mnist.py,sha256=kNDJw0oyqa6QgU1y9lg-3AzStavK1BB8iHnDOdv9nyE,8112
+dataeval/utils/data/datasets/_ships.py,sha256=rsyIoRAIk40liFgaEb2dg0lYB7__bAGd9zh9ouzjFKg,4880
 dataeval/utils/data/datasets/_types.py,sha256=iSKyHXRlGuomXs0FHK6md8lXLQrQQ4fxgVOwr4o81bo,1089
-dataeval/utils/data/datasets/_voc.py,sha256=4poEer_G_mUBcz6eAro0Tc29CjdgjEAlms0Eu0tLBzE,14842
-dataeval/utils/data/selections/__init__.py,sha256=k86OpqGPkjT1MrOir5fOZ3AIq5UR81Az9ek7l1-GdIM,565
-dataeval/utils/data/selections/_classfilter.py,sha256=opSF8CGv4x1hUMe-GTQOu3UwJK80DzT0nJOV0l2uaW4,2404
+dataeval/utils/data/datasets/_voc.py,sha256=QUtpbh2EpiBoicsmOo-YIfwRwPXyHj-zB2hFn7tlz0Y,15580
+dataeval/utils/data/selections/__init__.py,sha256=iUbMZRDuBXwY3SNAtZTdCVu7SI4zbCyaL6ItXnnq1yI,655
+dataeval/utils/data/selections/_classbalance.py,sha256=hHq9frdwzFLCUmfeJq977Sot_SXhuGANlSsetokhRDc,1465
+dataeval/utils/data/selections/_classfilter.py,sha256=xdR5uX7W5Yivf-mE_CikbRi2fGrZLFrPYun3TeQHTA0,1267
 dataeval/utils/data/selections/_indices.py,sha256=QdLgXN7GABCvGPYe28PV1RAc_RSP_nZOyCvEpKRBdWg,636
 dataeval/utils/data/selections/_limit.py,sha256=ECvHRsp7OF4LZw2tE4sGqqJ085kjC-hd2c7QDMfvXr8,518
-dataeval/utils/data/selections/_prioritize.py,sha256=EAA4_uFVV7MmemhhufGmP7eunnbtyTc-TzgcnvRK5OE,11333
+dataeval/utils/data/selections/_prioritize.py,sha256=uRQjeQiAc-vvwHMH4CQtXTGJCfjj_h5dgGlhQYFMz1c,11318
 dataeval/utils/data/selections/_reverse.py,sha256=6SWpELC9Wgx-kPqzhDrPNn4NKU6FqDJveLrxV4D2Ypk,374
-dataeval/utils/data/selections/_shuffle.py,sha256=kY3xJvVbBArdrJu_u6mXmxk1HdNmmDE4w7MmxbevUmU,1178
-dataeval/utils/metadata.py,sha256=X8Hu4LdCzAaE9uk1hI4BflmFve_VOQCqK9lXq0sk9ow,14196
+dataeval/utils/data/selections/_shuffle.py,sha256=_jwms0qcwrknf2Fx84cCXyNOJyhE_V8rcnDOTDn1S2A,1179
+dataeval/utils/metadata.py,sha256=1XeGYj_e97-nJ_IrWEHPhWICmouYU5qbXWbp7uhZrIE,14171
 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=23DCnF7C7N3tZgZUpT2nyH7mMb8Pi4GcnQyjK0BKHpg,5735
+dataeval/utils/torch/_internal.py,sha256=vHy-DzPhmvE8h3wmWc3aciBJ8nDGzQ1z1jTZgGjmDyM,4154
 dataeval/utils/torch/models.py,sha256=hmroEs6C6jQ5tAoZa71RFeIvXLxfXrTJSFH_jG2LGQU,9749
 dataeval/utils/torch/trainer.py,sha256=iUotX4OdirH8-ZtjdpU8gbJavkYW9YY9qpA2mAlFy1Y,5520
 dataeval/workflows/__init__.py,sha256=ou8y0KO-d6W5lgmcyLjKlf-J_ckP3vilW7wHkgiDlZ4,255
 dataeval/workflows/sufficiency.py,sha256=mjKmfRrAjShLUFIARv5o8yT5fnFvDsS5Qu6ujIPUgQg,8497
-dataeval-0.83.0.dist-info/LICENSE.txt,sha256=uAooygKWvX6NbU9Ran9oG2msttoG8aeTeHSTe5JeCnY,1061
-dataeval-0.83.0.dist-info/METADATA,sha256=lVRLNQcl2DYQDo7GHpFv_z133aD5hn-uOCkXXltGK5s,5320
-dataeval-0.83.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-dataeval-0.83.0.dist-info/RECORD,,
+dataeval-0.84.1.dist-info/LICENSE.txt,sha256=uAooygKWvX6NbU9Ran9oG2msttoG8aeTeHSTe5JeCnY,1061
+dataeval-0.84.1.dist-info/METADATA,sha256=F7L5PSWHV3z0_4pwA-JSgucW2A4bEv_dtvIMzCTGLZ8,5308
+dataeval-0.84.1.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+dataeval-0.84.1.dist-info/RECORD,,