dataeval 0.84.1__py3-none-any.whl → 1.0.0__py3-none-any.whl

dataeval/detectors/linters/duplicates.py

@@ -4,13 +4,13 @@ __all__ = []
 
 from typing import Any, Sequence, overload
 
+from dataeval.data._images import Images
 from dataeval.metrics.stats import hashstats
 from dataeval.metrics.stats._base import combine_stats, get_dataset_step_from_idx
 from dataeval.outputs import DuplicatesOutput, HashStatsOutput
 from dataeval.outputs._base import set_metadata
 from dataeval.outputs._linters import DatasetDuplicateGroupMap, DuplicateGroup
 from dataeval.typing import ArrayLike, Dataset
-from dataeval.utils.data._images import Images
 
 
 class Duplicates:

dataeval/detectors/linters/outliers.py

@@ -7,6 +7,7 @@ from typing import Any, Literal, Sequence, overload
 import numpy as np
 from numpy.typing import NDArray
 
+from dataeval.data._images import Images
 from dataeval.metrics.stats._base import combine_stats, get_dataset_step_from_idx
 from dataeval.metrics.stats._imagestats import imagestats
 from dataeval.outputs import DimensionStatsOutput, ImageStatsOutput, OutliersOutput, PixelStatsOutput, VisualStatsOutput
@@ -14,7 +15,6 @@ from dataeval.outputs._base import set_metadata
 from dataeval.outputs._linters import IndexIssueMap, OutlierStatsOutput
 from dataeval.outputs._stats import BOX_COUNT, SOURCE_INDEX
 from dataeval.typing import ArrayLike, Dataset
-from dataeval.utils.data._images import Images
 
 
 def _get_outlier_mask(

dataeval/metadata/_distance.py

@@ -9,11 +9,11 @@ import numpy as np
 from scipy.stats import iqr, ks_2samp
 from scipy.stats import wasserstein_distance as emd
 
+from dataeval.data import Metadata
 from dataeval.metadata._utils import _compare_keys, _validate_factors_and_data
 from dataeval.outputs import MetadataDistanceOutput, MetadataDistanceValues
 from dataeval.outputs._base import set_metadata
 from dataeval.typing import ArrayLike
-from dataeval.utils.data import Metadata
 
 
 class KSType(NamedTuple):

dataeval/metadata/_ood.py

@@ -9,10 +9,10 @@ from numpy.typing import NDArray
 from sklearn.feature_selection import mutual_info_classif
 
 from dataeval.config import get_seed
+from dataeval.data import Metadata
 from dataeval.metadata._utils import _compare_keys, _validate_factors_and_data
 from dataeval.outputs import MostDeviatedFactorsOutput, OODOutput, OODPredictorOutput
 from dataeval.outputs._base import set_metadata
-from dataeval.utils.data import Metadata
 
 
 def _combine_discrete_continuous(metadata: Metadata) -> tuple[list[str], NDArray[np.float64]]:
@@ -201,7 +201,7 @@ def find_most_deviated_factors(
     MostDeviatedFactorsOutput([])
     """
 
-    ood_mask: NDArray[np.bool] = ood.is_ood
+    ood_mask: NDArray[np.bool_] = ood.is_ood
 
     # No metadata correlated with out of distribution data
     if not any(ood_mask):
@@ -303,7 +303,7 @@ def find_ood_predictors(
     OODPredictorOutput({})
     """
 
-    ood_mask: NDArray[np.bool] = ood.is_ood
+    ood_mask: NDArray[np.bool_] = ood.is_ood
 
     discrete_features_count = len(metadata.discrete_factor_names)
     factors, data = _combine_discrete_continuous(metadata)  # (F, ), (S, F) => F = Fd + Fc
@@ -320,7 +320,7 @@ def find_ood_predictors(
     # Calculate mean, std of each factor over all samples
     scaled_data = (data - np.mean(data, axis=0)) / np.std(data, axis=0, ddof=1)  # (S, F)
 
-    discrete_features = np.zeros_like(factors, dtype=np.bool)
+    discrete_features = np.zeros_like(factors, dtype=np.bool_)
     discrete_features[:discrete_features_count] = True
 
     mutual_info_values = (

dataeval/metrics/bias/_balance.py

@@ -9,10 +9,10 @@ import scipy as sp
 from sklearn.feature_selection import mutual_info_classif, mutual_info_regression
 
 from dataeval.config import EPSILON, get_seed
+from dataeval.data import Metadata
 from dataeval.outputs import BalanceOutput
 from dataeval.outputs._base import set_metadata
 from dataeval.utils._bin import get_counts
-from dataeval.utils.data import Metadata
 
 
 def _validate_num_neighbors(num_neighbors: int) -> int:

dataeval/metrics/bias/_diversity.py

@@ -8,11 +8,11 @@ import numpy as np
 import scipy as sp
 from numpy.typing import NDArray
 
+from dataeval.data import Metadata
 from dataeval.outputs import DiversityOutput
 from dataeval.outputs._base import set_metadata
 from dataeval.utils._bin import get_counts
 from dataeval.utils._method import get_method
-from dataeval.utils.data import Metadata
 
 
 def diversity_shannon(

dataeval/metrics/bias/_parity.py

@@ -10,11 +10,11 @@ from numpy.typing import NDArray
 from scipy.stats import chisquare
 from scipy.stats.contingency import chi2_contingency, crosstab
 
+from dataeval.data import Metadata
 from dataeval.outputs import LabelParityOutput, ParityOutput
 from dataeval.outputs._base import set_metadata
 from dataeval.typing import ArrayLike
 from dataeval.utils._array import as_numpy
-from dataeval.utils.data import Metadata
 
 
 def normalize_expected_dist(expected_dist: NDArray[Any], observed_dist: NDArray[Any]) -> NDArray[Any]:

dataeval/metrics/stats/_labelstats.py

@@ -5,10 +5,10 @@ __all__ = []
 from collections import Counter, defaultdict
 from typing import Any, Mapping, TypeVar
 
+from dataeval.data._metadata import Metadata
 from dataeval.outputs import LabelStatsOutput
 from dataeval.outputs._base import set_metadata
 from dataeval.typing import AnnotatedDataset
-from dataeval.utils.data._metadata import Metadata
 
 TValue = TypeVar("TValue")
 
@@ -38,7 +38,7 @@ def labelstats(dataset: Metadata | AnnotatedDataset[Any]) -> LabelStatsOutput:
     --------
     Calculate basic :term:`statistics<Statistics>` on labels for a dataset.
 
-    >>> from dataeval.utils.data import Metadata
+    >>> from dataeval.data import Metadata
     >>> stats = labelstats(Metadata(dataset))
     >>> print(stats.to_table())
     Class Count: 5

dataeval/outputs/_bias.py

@@ -13,11 +13,11 @@ with contextlib.suppress(ImportError):
     import pandas as pd
     from matplotlib.figure import Figure
 
+from dataeval.data._images import Images
 from dataeval.outputs._base import Output
 from dataeval.typing import ArrayLike, Dataset
 from dataeval.utils._array import as_numpy, channels_first_to_last
 from dataeval.utils._plot import heatmap
-from dataeval.utils.data._images import Images
 
 TData = TypeVar("TData", np.float64, NDArray[np.float64])
 

dataeval/typing.py

@@ -98,6 +98,22 @@ class DatasetMetadata(TypedDict, total=False):
     index2label: NotRequired[ReadOnly[dict[int, str]]]
 
 
+class ModelMetadata(TypedDict, total=False):
+    """
+    Model metadata required for all `AnnotatedModel` classes.
+
+    Attributes
+    ----------
+    id : Required[str]
+        A unique identifier for the model
+    index2label : NotRequired[dict[int, str]]
+        A lookup table converting label value to class name
+    """
+
+    id: Required[ReadOnly[str]]
+    index2label: NotRequired[ReadOnly[dict[int, str]]]
+
+
 @runtime_checkable
 class Dataset(Generic[_T_co], Protocol):
     """
@@ -238,6 +254,21 @@ SegmentationDataset: TypeAlias = AnnotatedDataset[SegmentationDatum]
 Type alias for an :class:`AnnotatedDataset` of :class:`SegmentationDatum` elements.
 """
 
+# ========== MODEL ==========
+
+
+@runtime_checkable
+class AnnotatedModel(Protocol):
+    """
+    Protocol for an annotated model.
+    """
+
+    @property
+    def metadata(self) -> ModelMetadata: ...
+
+
+# ========== TRANSFORM ==========
+
 
 @runtime_checkable
 class Transform(Generic[_T], Protocol):

dataeval/utils/__init__.py

@@ -4,6 +4,6 @@ in setting up data and architectures that are guaranteed to work with applicable
 DataEval metrics.
 """
 
-__all__ = ["data", "metadata", "torch"]
+__all__ = ["data", "datasets", "torch"]
 
-from . import data, metadata, torch
+from . import data, datasets, torch

dataeval/utils/data/__init__.py

@@ -1,26 +1,11 @@
-"""Provides utility functions for interacting with Computer Vision datasets."""
+"""Provides access to common Computer Vision datasets."""
+
+from dataeval.utils.data import collate, metadata
+from dataeval.utils.data._dataset import to_image_classification_dataset, to_object_detection_dataset
 
 __all__ = [
     "collate",
-    "datasets",
-    "Embeddings",
-    "Images",
-    "Metadata",
-    "Select",
-    "SplitDatasetOutput",
-    "Targets",
-    "split_dataset",
+    "metadata",
     "to_image_classification_dataset",
     "to_object_detection_dataset",
 ]
-
-from dataeval.outputs._utils import SplitDatasetOutput
-from dataeval.utils.data._dataset import to_image_classification_dataset, to_object_detection_dataset
-from dataeval.utils.data._embeddings import Embeddings
-from dataeval.utils.data._images import Images
-from dataeval.utils.data._metadata import Metadata
-from dataeval.utils.data._selection import Select
-from dataeval.utils.data._split import split_dataset
-from dataeval.utils.data._targets import Targets
-
-from . import collate, datasets

dataeval/utils/data/collate.py

@@ -4,6 +4,8 @@ Collate functions used with a PyTorch DataLoader to load data from MAITE complia
 
 from __future__ import annotations
 
+__all__ = ["list_collate_fn", "numpy_collate_fn", "torch_collate_fn"]
+
 from typing import Any, Iterable, Sequence, TypeVar
 
 import numpy as np

dataeval/utils/datasets/__init__.py

@@ -0,0 +1,17 @@
+"""Provides access to common Computer Vision datasets."""
+
+from dataeval.utils.datasets._cifar10 import CIFAR10
+from dataeval.utils.datasets._milco import MILCO
+from dataeval.utils.datasets._mnist import MNIST
+from dataeval.utils.datasets._ships import Ships
+from dataeval.utils.datasets._voc import VOCDetection, VOCDetectionTorch, VOCSegmentation
+
+__all__ = [
+    "MNIST",
+    "Ships",
+    "CIFAR10",
+    "MILCO",
+    "VOCDetection",
+    "VOCDetectionTorch",
+    "VOCSegmentation",
+]

dataeval/utils/{data/datasets → datasets}/_base.py

@@ -6,9 +6,9 @@ from abc import abstractmethod
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Generic, Iterator, Literal, NamedTuple, Sequence, TypeVar
 
-from dataeval.utils.data.datasets._fileio import _ensure_exists
-from dataeval.utils.data.datasets._mixin import BaseDatasetMixin
-from dataeval.utils.data.datasets._types import (
+from dataeval.utils.datasets._fileio import _ensure_exists
+from dataeval.utils.datasets._mixin import BaseDatasetMixin
+from dataeval.utils.datasets._types import (
     AnnotatedDataset,
     DatasetMetadata,
     ImageClassificationDataset,

dataeval/utils/{data/datasets → datasets}/_cifar10.py

@@ -9,8 +9,8 @@ import numpy as np
 from numpy.typing import NDArray
 from PIL import Image
 
-from dataeval.utils.data.datasets._base import BaseICDataset, DataLocation
-from dataeval.utils.data.datasets._mixin import BaseDatasetNumpyMixin
+from dataeval.utils.datasets._base import BaseICDataset, DataLocation
+from dataeval.utils.datasets._mixin import BaseDatasetNumpyMixin
 
 if TYPE_CHECKING:
     from dataeval.typing import Transform

dataeval/utils/{data/datasets → datasets}/_milco.py

@@ -7,8 +7,8 @@ from typing import TYPE_CHECKING, Any, Literal, Sequence
 
 from numpy.typing import NDArray
 
-from dataeval.utils.data.datasets._base import BaseODDataset, DataLocation
-from dataeval.utils.data.datasets._mixin import BaseDatasetNumpyMixin
+from dataeval.utils.datasets._base import BaseODDataset, DataLocation
+from dataeval.utils.datasets._mixin import BaseDatasetNumpyMixin
 
 if TYPE_CHECKING:
     from dataeval.typing import Transform

dataeval/utils/{data/datasets → datasets}/_mnist.py

@@ -8,8 +8,8 @@ from typing import TYPE_CHECKING, Any, Literal, Sequence, TypeVar
 import numpy as np
 from numpy.typing import NDArray
 
-from dataeval.utils.data.datasets._base import BaseICDataset, DataLocation
-from dataeval.utils.data.datasets._mixin import BaseDatasetNumpyMixin
+from dataeval.utils.datasets._base import BaseICDataset, DataLocation
+from dataeval.utils.datasets._mixin import BaseDatasetNumpyMixin
 
 if TYPE_CHECKING:
     from dataeval.typing import Transform

dataeval/utils/{data/datasets → datasets}/_ships.py

@@ -8,8 +8,8 @@ from typing import TYPE_CHECKING, Any, Sequence
 import numpy as np
 from numpy.typing import NDArray
 
-from dataeval.utils.data.datasets._base import BaseICDataset, DataLocation
-from dataeval.utils.data.datasets._mixin import BaseDatasetNumpyMixin
+from dataeval.utils.datasets._base import BaseICDataset, DataLocation
+from dataeval.utils.datasets._mixin import BaseDatasetNumpyMixin
 
 if TYPE_CHECKING:
     from dataeval.typing import Transform

dataeval/utils/{data/datasets → datasets}/_voc.py

@@ -9,7 +9,7 @@ import torch
 from defusedxml.ElementTree import parse
 from numpy.typing import NDArray
 
-from dataeval.utils.data.datasets._base import (
+from dataeval.utils.datasets._base import (
     BaseDataset,
     BaseODDataset,
     BaseSegDataset,
@@ -17,8 +17,8 @@ from dataeval.utils.data.datasets._base import (
     _TArray,
     _TTarget,
 )
-from dataeval.utils.data.datasets._mixin import BaseDatasetNumpyMixin, BaseDatasetTorchMixin
-from dataeval.utils.data.datasets._types import ObjectDetectionTarget, SegmentationTarget
+from dataeval.utils.datasets._mixin import BaseDatasetNumpyMixin, BaseDatasetTorchMixin
+from dataeval.utils.datasets._types import ObjectDetectionTarget, SegmentationTarget
 
 if TYPE_CHECKING:
     from dataeval.typing import Transform

{dataeval-0.84.1.dist-info → dataeval-1.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dataeval
-Version: 0.84.1
+Version: 1.0.0
 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

{dataeval-0.84.1.dist-info → dataeval-1.0.0.dist-info}/RECORD

@@ -1,33 +1,48 @@
-dataeval/__init__.py,sha256=QzrctVrymZuLN8tnHcF1wp0RTXYM3WSWMozX3NOzIos,1636
+dataeval/__init__.py,sha256=xd1GfD7QmzBG-WN7K6BMJSzV9_UZlX5OiKICdQ5xGfU,1635
 dataeval/_log.py,sha256=Mn5bRWO0cgtAYd5VGYSFiPgu57ta3zoktrtHAZ1m3dU,357
 dataeval/config.py,sha256=lD1YDH8HosFeRU5rQEYRBcmXMZy-csWaMlJTRZGd9iU,3582
+dataeval/data/__init__.py,sha256=qNnRRiVP_sLthkkHpUrMgI_r8dQK-cC-xoGrrjQeRKc,544
+dataeval/data/_embeddings.py,sha256=6Medqj_JCQt1iwZwWGSs1OeX-bHB8bg5BJqADY1N2s8,12883
+dataeval/data/_images.py,sha256=WF9XJRka8ohUdyI2IKBMAy3JoJhOm1iC-8tbYl8woRM,2642
+dataeval/data/_metadata.py,sha256=hNgsCEN8EyfDDX7zLKcQnsaDl-9xvvs5tUzqMjVLvI4,14457
+dataeval/data/_selection.py,sha256=V61_pTFj0hSzmltA6CV5t51Znqw2dIQZ71Iu46bLm44,4486
+dataeval/data/_split.py,sha256=6Jtm_i__CcPtNE3eSeBdPxc7gn7Cp-GM7g9wJWFlVus,16761
+dataeval/data/_targets.py,sha256=ws5d9wRiDkIuOV7GSAKNxzgSm6AWTgb0BFroQK5nAmM,3057
+dataeval/data/selections/__init__.py,sha256=2m8ZB53wXzqLcqmc6p5atO6graB6ZyiRSNJFxf11X_g,613
+dataeval/data/selections/_classbalance.py,sha256=7v8ApoL3X8eCZ6fGDNTehE_bZ1loaP3TlhsJLaICVWg,1458
+dataeval/data/selections/_classfilter.py,sha256=rEeq959p_SLl_etS7pcM8ZxK4yzEYlYZAQ3FlcLV0R8,4330
+dataeval/data/selections/_indices.py,sha256=RFsR9z10aM3N0gJSfKrukFpi-LkiQGXoOwXhmOQ5cpg,630
+dataeval/data/selections/_limit.py,sha256=JG4GmEiNKt3sk4PbOUbBnGGzNlyz72H-kQrt8COMm4Y,512
+dataeval/data/selections/_prioritize.py,sha256=yw51ZQk6FPvyC38M4_pS_Se2Dq0LDFcdDhfbsELzTZc,11306
+dataeval/data/selections/_reverse.py,sha256=b67kNC43A5KpQOic5gifjo9HpJ7FMh4LFCrfovPiJ-M,368
+dataeval/data/selections/_shuffle.py,sha256=gVz_2T4rlucq8Ytqz5jvmmZdTrZDaIv43jJbq97tLjQ,1173
 dataeval/detectors/__init__.py,sha256=3Sg-XWlwr75zEEH3hZKA4nWMtGvaRlnfzTWvZG_Ak6U,189
 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/_base.py,sha256=amGqzUAe8fU5qwM5lq1p8PCuhjGh9MHkdW1zeBF1LEE,7574
+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=wHUy_vUafCikrZ_WX8qQXpxFwzw07-5zVutloR6hl1k,11589
 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=x36-0EAlO_AuOttvElJOZCa0R3VzrlII0NxjwhdkrpE,4969
-dataeval/detectors/linters/outliers.py,sha256=Z0Sbtluu2im1IRGsjhXF2AhrShKDrEkF8BWzAZyPwlA,9054
+dataeval/detectors/linters/duplicates.py,sha256=X5WSEvI_BHkLoXjkaHK6wTnSkx4IjpO_exMRjSlhc70,4963
+dataeval/detectors/linters/outliers.py,sha256=D8A-Fov5iUrlU9xMX5Ht33FqUY8Lk5ulC6BlHbUoLwU,9048
 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/detectors/ood/vae.py,sha256=Fcq0-WbLhzYCgYOAJPBklHm7yuXmFJuEpBkhgwM5kiA,2291
 dataeval/metadata/__init__.py,sha256=XDDmJbOZBNM6pL0r6Nbu6oMRoyAh22IDkPYGndNlkZU,316
-dataeval/metadata/_distance.py,sha256=xsXMMg1pJkHcEZ-KIlqv9YOGYVID3ELjt3-fr1QVnOs,4082
-dataeval/metadata/_ood.py,sha256=HbS5MusWl62hjixUAd-xaaT0KXkYY1M-MlnUaAI_-8M,12751
+dataeval/metadata/_distance.py,sha256=T1Umju_QwBiLmn1iUbxZagzBS2VnHaDIdp6j-NpaZuk,4076
+dataeval/metadata/_ood.py,sha256=lnKtKModArnUrAhH_XswEtUAhUkh1U_oNsLt1UmNP44,12748
 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=UnUgbPk2ybFfS5qxv8e_uim7RxamWj0UQP71x3omGs0,6158
+dataeval/metrics/bias/_balance.py,sha256=l1hTVkVwD85bP20MTthA-I5BkvbytylQkJu3Q6iTuPA,6152
 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
+dataeval/metrics/bias/_diversity.py,sha256=B_qWVDMZfh818U0qVm8yidquB0H0XvW8N75OWVWXy2g,5814
+dataeval/metrics/bias/_parity.py,sha256=ea1D-eJh6cJxQ11XD6VbDXBKecE0jJJwptGD7LQJmBw,11529
 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
@@ -39,12 +54,12 @@ dataeval/metrics/stats/_boxratiostats.py,sha256=8Kd2FTZ5PLNYZfdAjU_R385gb0Z16JY0
 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/_labelstats.py,sha256=lz8I6eSd8tFkmQqy5cOG8hn9yxs0mP-Ic9ratFHiuoU,2813
 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=GwbjLdppUODOeudYb_7ki2ejDmAYthlRKGijVwgVePE,12407
+dataeval/outputs/_bias.py,sha256=7L-d3DUWY6Vud7iX_VoQT0HG0KaV1U35gvmRApqzyB0,12401
 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
@@ -54,8 +69,8 @@ dataeval/outputs/_stats.py,sha256=c73Yc3Kkrl-MN6BGKe1V0Yr6Ix2Yp_DZZfFSp8fZMZ0,13
 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=zn6smomSdcO7EeZpeeSP5-8sknTdgUuU7TKe-3UFVrg,6550
-dataeval/utils/__init__.py,sha256=T8F8zJh4ZAeu0wDzfpld92I2zJg9mWBmkGCHrDPU7gk,264
+dataeval/typing.py,sha256=GDMuef-oFFukNtsiKFmsExHdNvYR_j-tQcsCwZ9reow,7198
+dataeval/utils/__init__.py,sha256=hRvyUK7b3d6JBEV5u47rFcOHEcmDYqAvZQw_T5pDAWw,264
 dataeval/utils/_array.py,sha256=KqAdXEMjcXYvdWdYEEoEbigwQJ4S9VYxQS3sRFeY5XY,5929
 dataeval/utils/_bin.py,sha256=nylthmsC3vzLHLhlUMACvZs--h7xvAh9Pt75InaQJW8,7322
 dataeval/utils/_clusterer.py,sha256=fw5x-2QN0TIbiodDKHZxRgxKHINedpPcOklzce0Rbjg,5436
@@ -64,34 +79,20 @@ dataeval/utils/_image.py,sha256=capzF_X5H0jy0PmTP3Hf52GFgLqrnfU6gS4tiwck9jo,1939
 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/__init__.py,sha256=xGzrjrOxOP2DP1tU84AWMKPnSxFvSjM81CTlDg4rNM8,331
 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=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=bVVDl5W8TdTPU2RiwoPXrfFDM1rKyb-LslwTThBXEr0,7583
-dataeval/utils/data/datasets/_mixin.py,sha256=FJgZP_cpJkgAHA3j3ai_j3Wt7aFSEjIMVmt9NpvVXzg,1757
-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=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=uRQjeQiAc-vvwHMH4CQtXTGJCfjj_h5dgGlhQYFMz1c,11318
-dataeval/utils/data/selections/_reverse.py,sha256=6SWpELC9Wgx-kPqzhDrPNn4NKU6FqDJveLrxV4D2Ypk,374
-dataeval/utils/data/selections/_shuffle.py,sha256=_jwms0qcwrknf2Fx84cCXyNOJyhE_V8rcnDOTDn1S2A,1179
-dataeval/utils/metadata.py,sha256=1XeGYj_e97-nJ_IrWEHPhWICmouYU5qbXWbp7uhZrIE,14171
+dataeval/utils/data/collate.py,sha256=5egEEKhNNCGeNLChO1p6dZ4Wg6x51VEaMNHz7hEZUxI,3936
+dataeval/utils/data/metadata.py,sha256=1XeGYj_e97-nJ_IrWEHPhWICmouYU5qbXWbp7uhZrIE,14171
+dataeval/utils/datasets/__init__.py,sha256=Jfe7XI_9U5S4wuI_2QCoeuWNOxz4j0nAQvxc5wG5mWY,486
+dataeval/utils/datasets/_base.py,sha256=TpmgPzF3EShCLAF5S4Zf9lFN78q17bTZF6AUE1qKdlk,8857
+dataeval/utils/datasets/_cifar10.py,sha256=oSX5JEzbBM4zGC9kC7-hVTOglms3rYaUuYiA00_DUJ4,5439
+dataeval/utils/datasets/_fileio.py,sha256=SixIk5nIlIwJdX9zjNXS10vHA3hL8aaYbqHsDg1xSpY,6447
+dataeval/utils/datasets/_milco.py,sha256=BF2XvyzuOop1mg5pFZcRfYmZcezlbpZWHyd_TtEHFF4,7573
+dataeval/utils/datasets/_mixin.py,sha256=FJgZP_cpJkgAHA3j3ai_j3Wt7aFSEjIMVmt9NpvVXzg,1757
+dataeval/utils/datasets/_mnist.py,sha256=4WOkQTORYMs6KEeyyJgChTnH03797y4ezgaZtYqplh4,8102
+dataeval/utils/datasets/_ships.py,sha256=RMdX2KlnXJYOTzBb6euA5TAqxs-S8b56pAGiyQhNMuo,4870
+dataeval/utils/datasets/_types.py,sha256=iSKyHXRlGuomXs0FHK6md8lXLQrQQ4fxgVOwr4o81bo,1089
+dataeval/utils/datasets/_voc.py,sha256=kif6ms_romK6VElP4pf2SK4cJ5dEHDOkxSaSaeP3c5k,15565
 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
@@ -100,7 +101,7 @@ dataeval/utils/torch/models.py,sha256=hmroEs6C6jQ5tAoZa71RFeIvXLxfXrTJSFH_jG2LGQ
 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-0.84.1.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,,
+dataeval-1.0.0.dist-info/LICENSE.txt,sha256=uAooygKWvX6NbU9Ran9oG2msttoG8aeTeHSTe5JeCnY,1061
+dataeval-1.0.0.dist-info/METADATA,sha256=ma_TquWQQl0QETiK4-wH1jfAe2my33Cl37GswNe0ZM8,5307
+dataeval-1.0.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+dataeval-1.0.0.dist-info/RECORD,,

dataeval/utils/data/datasets/__init__.py

@@ -1,17 +0,0 @@
-"""Provides access to common Computer Vision datasets."""
-
-from dataeval.utils.data.datasets._cifar10 import CIFAR10
-from dataeval.utils.data.datasets._milco import MILCO
-from dataeval.utils.data.datasets._mnist import MNIST
-from dataeval.utils.data.datasets._ships import Ships
-from dataeval.utils.data.datasets._voc import VOCDetection, VOCDetectionTorch, VOCSegmentation
-
-__all__ = [
-    "MNIST",
-    "Ships",
-    "CIFAR10",
-    "MILCO",
-    "VOCDetection",
-    "VOCDetectionTorch",
-    "VOCSegmentation",
-]

dataeval/utils/data/selections/__init__.py

@@ -1,19 +0,0 @@
-"""Provides selection classes for selecting subsets of Computer Vision datasets."""
-
-__all__ = [
-    "ClassBalance",
-    "ClassFilter",
-    "Indices",
-    "Limit",
-    "Prioritize",
-    "Reverse",
-    "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
-from dataeval.utils.data.selections._prioritize import Prioritize
-from dataeval.utils.data.selections._reverse import Reverse
-from dataeval.utils.data.selections._shuffle import Shuffle

dataeval/utils/data/selections/_classfilter.py

@@ -1,44 +0,0 @@
-from __future__ import annotations
-
-__all__ = []
-
-from typing import Sequence
-
-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 ClassFilter(Selection[ImageClassificationDatum]):
-    """
-    Filter the dataset by class.
-
-    Parameters
-    ----------
-    classes : Sequence[int]
-        The classes to filter by.
-    """
-
-    stage = SelectionStage.FILTER
-
-    def __init__(self, classes: Sequence[int]) -> None:
-        self.classes = classes
-
-    def __call__(self, dataset: Select[ImageClassificationDatum]) -> None:
-        if not self.classes:
-            return
-
-        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 label in self.classes:
-                selection.append(idx)
-
-        dataset._selection = selection