dataeval 0.84.1__py3-none-any.whl → 0.86.0__py3-none-any.whl

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/__init__.py

@@ -5,7 +5,7 @@ as well as runtime metadata for reproducibility and logging.
 
 from ._base import ExecutionMetadata
 from ._bias import BalanceOutput, CompletenessOutput, CoverageOutput, DiversityOutput, LabelParityOutput, ParityOutput
-from ._drift import DriftMMDOutput, DriftOutput
+from ._drift import DriftMMDOutput, DriftMVDCOutput, DriftOutput
 from ._estimators import BEROutput, ClustererOutput, DivergenceOutput, UAPOutput
 from ._linters import DuplicatesOutput, OutliersOutput
 from ._metadata import MetadataDistanceOutput, MetadataDistanceValues, MostDeviatedFactorsOutput, OODPredictorOutput
@@ -34,6 +34,7 @@ __all__ = [
     "DivergenceOutput",
     "DiversityOutput",
     "DriftMMDOutput",
+    "DriftMVDCOutput",
     "DriftOutput",
     "DuplicatesOutput",
     "ExecutionMetadata",

dataeval/outputs/_bias.py

@@ -7,17 +7,17 @@ from dataclasses import asdict, dataclass
 from typing import Any, Literal, TypeVar, overload
 
 import numpy as np
+import pandas as pd
 from numpy.typing import NDArray
 
 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])
 
@@ -38,8 +38,6 @@ class ToDataFrameMixin:
         -----
         This method requires `pandas <https://pandas.pydata.org/>`_ to be installed.
         """
-        import pandas as pd
-
         return pd.DataFrame(
             index=self.factor_names,  # type: ignore - list[str] is documented as acceptable index type
             data={

dataeval/outputs/_drift.py

@@ -2,11 +2,17 @@ from __future__ import annotations
 
 __all__ = []
 
+import contextlib
 from dataclasses import dataclass
 
 import numpy as np
+import pandas as pd
 from numpy.typing import NDArray
 
+with contextlib.suppress(ImportError):
+    from matplotlib.figure import Figure
+
+from dataeval.detectors.drift._nml._result import Metric, PerMetricResult
 from dataeval.outputs._base import Output
 
 
@@ -81,3 +87,65 @@ class DriftOutput(DriftBaseOutput):
     feature_threshold: float
     p_vals: NDArray[np.float32]
     distances: NDArray[np.float32]
+
+
+class DriftMVDCOutput(PerMetricResult):
+    """Class wrapping the results of the classifier for drift detection and providing plotting functionality."""
+
+    def __init__(self, results_data: pd.DataFrame) -> None:
+        """Initialize a DomainClassifierCalculator results object.
+
+        Parameters
+        ----------
+        results_data : pd.DataFrame
+            Results data returned by a DomainClassifierCalculator.
+        """
+        metric = Metric(display_name="Domain Classifier", column_name="domain_classifier_auroc")
+        super().__init__(results_data, [metric])
+
+    def plot(self, showme: bool = True) -> Figure:
+        """
+        Render the roc_auc metric over the train/test data in relation to the threshold.
+
+        Parameters
+        ----------
+        showme : bool, default True
+            Option to display the figure.
+
+        Returns
+        -------
+        matplotlib.figure.Figure
+
+        """
+        import matplotlib.pyplot as plt
+
+        fig, ax = plt.subplots(dpi=300)
+        resdf = self.to_df()
+        xticks = np.arange(resdf.shape[0])
+        trndf = resdf[resdf["chunk"]["period"] == "reference"]
+        tstdf = resdf[resdf["chunk"]["period"] == "analysis"]
+        # Get local indices for drift markers
+        driftx = np.where(resdf["domain_classifier_auroc"]["alert"].values)  # type: ignore | dataframe
+        if np.size(driftx) > 2:
+            ax.plot(resdf.index, resdf["domain_classifier_auroc"]["upper_threshold"], "r--", label="thr_up")
+            ax.plot(resdf.index, resdf["domain_classifier_auroc"]["lower_threshold"], "r--", label="thr_low")
+            ax.plot(trndf.index, trndf["domain_classifier_auroc"]["value"], "b", label="train")
+            ax.plot(tstdf.index, tstdf["domain_classifier_auroc"]["value"], "g", label="test")
+            ax.plot(
+                resdf.index.values[driftx],  # type: ignore | dataframe
+                resdf["domain_classifier_auroc"]["value"].values[driftx],  # type: ignore | dataframe
+                "dm",
+                markersize=3,
+                label="drift",
+            )
+            ax.set_xticks(xticks)
+            ax.tick_params(axis="x", labelsize=6)
+            ax.tick_params(axis="y", labelsize=6)
+            ax.legend(loc="lower left", fontsize=6)
+            ax.set_title("Domain Classifier, Drift Detection", fontsize=8)
+            ax.set_ylabel("ROC AUC", fontsize=7)
+            ax.set_xlabel("Chunk Index", fontsize=7)
+            ax.set_ylim((0.0, 1.1))
+            if showme:
+                plt.show()
+        return fig

dataeval/outputs/_linters.py

@@ -2,15 +2,12 @@ from __future__ import annotations
 
 __all__ = []
 
-import contextlib
 from dataclasses import dataclass
 from typing import Generic, TypeVar, Union
 
+import pandas as pd
 from typing_extensions import TypeAlias
 
-with contextlib.suppress(ImportError):
-    import pandas as pd
-
 from dataeval.outputs._base import Output
 from dataeval.outputs._stats import DimensionStatsOutput, LabelStatsOutput, PixelStatsOutput, VisualStatsOutput
 
@@ -168,8 +165,6 @@ class OutliersOutput(Output, Generic[TIndexIssueMap]):
         -----
         This method requires `pandas <https://pandas.pydata.org/>`_ to be installed.
         """
-        import pandas as pd
-
         if isinstance(self.issues, dict):
             _, classwise = _reorganize_by_class_and_metric(self.issues, labelstats)
             data = _create_pandas_dataframe(classwise)

dataeval/outputs/_stats.py

@@ -2,17 +2,14 @@ from __future__ import annotations
 
 __all__ = []
 
-import contextlib
 from dataclasses import dataclass
 from typing import Any, Iterable, NamedTuple, Optional, Union
 
 import numpy as np
+import pandas as pd
 from numpy.typing import NDArray
 from typing_extensions import TypeAlias
 
-with contextlib.suppress(ImportError):
-    import pandas as pd
-
 from dataeval.outputs._base import Output
 from dataeval.utils._plot import channel_histogram_plot, histogram_plot
 
@@ -281,8 +278,6 @@ class LabelStatsOutput(Output):
         -------
         pd.DataFrame
         """
-        import pandas as pd
-
         total_count = []
         image_count = []
         for cls in range(len(self.class_names)):

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-0.86.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dataeval
-Version: 0.84.1
+Version: 0.86.0
 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
@@ -23,10 +23,11 @@ Classifier: Topic :: Scientific/Engineering
 Provides-Extra: all
 Requires-Dist: defusedxml (>=0.7.1)
 Requires-Dist: fast_hdbscan (==0.2.0)
+Requires-Dist: lightgbm (>=4)
 Requires-Dist: matplotlib (>=3.7.1) ; extra == "all"
 Requires-Dist: numba (>=0.59.1)
 Requires-Dist: numpy (>=1.24.2)
-Requires-Dist: pandas (>=2.0) ; extra == "all"
+Requires-Dist: pandas (>=2.0)
 Requires-Dist: pillow (>=10.3.0)
 Requires-Dist: requests
 Requires-Dist: scikit-learn (>=1.5.0)

dataeval-0.86.0.dist-info/RECORD

@@ -0,0 +1,114 @@
+dataeval/__init__.py,sha256=GdieNQ3woQUTyIFklJx7AgEeiBCz9gXzo-UVt6YFHPo,1636
+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=mK-WbrFkMo3v8f66uHT4B6-Fsc1odh0CcMTuz2aXSZc,14968
+dataeval/data/_selection.py,sha256=rYCM4KTqLSOYOzyjKCQKH2KQgJhxNnB2g3pY4JbOEYc,4503
+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=VSNl_BSPRHQOBU6GYQwPZhl7j2jYESVJSSdyqWiG_vA,4394
+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=Jqv98oOVeC2tvHlNGxQ8RJ6De2q4SyS5lTpaYlb4ocM,756
+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/_mvdc.py,sha256=ABxGut6KzxF_oM-Hs87WARCR0692dhPVdZNoGGwJaa4,3058
+dataeval/detectors/drift/_nml/__init__.py,sha256=MNyKyZlfTjr5uQql2uBBfRkUdsuduie_WJdn09GYmqg,137
+dataeval/detectors/drift/_nml/_base.py,sha256=g8RmOnsBVN8vV1S9B9JaQQLudcbyKERwy4OuDjGIxb8,2632
+dataeval/detectors/drift/_nml/_chunk.py,sha256=QxohvSycm_cjldmK-ll-APfIsopPgeATHV-9aejyIKE,13826
+dataeval/detectors/drift/_nml/_domainclassifier.py,sha256=ccb1tgJ_K7gMYtg1Wdy2gPIpYIhconHQVu3xW5v0hjs,7743
+dataeval/detectors/drift/_nml/_result.py,sha256=mnWnP1CwzrDChJygcsuFhkKR5g3yAQS520oo-l9PcZU,3273
+dataeval/detectors/drift/_nml/_thresholds.py,sha256=jnhfd0qR99TKF0PyUVcbtE7cj9lic0QxwrWq_fwoAHM,12687
+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=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=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=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=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
+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=YIfOVGd7E19B4dpAnzDYRQkaikvRRyJIpznJNfVtPdw,10750
+dataeval/metrics/stats/_boxratiostats.py,sha256=8Kd2FTZ5PLNYZfdAjU_R385gb0Z16JY0L9H_d5ZhgQs,6341
+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=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=geHB5M3QOiFFaQGV4ZwDTTKpqZPvPePbqG7lzaPhaXQ,1741
+dataeval/outputs/_base.py,sha256=aZFbgybnZSQ3ws7QYRLTbDFqUfBFRVtIwX2LZfeGFUA,5703
+dataeval/outputs/_bias.py,sha256=_4qgboPstvEFBjTPZOVAOOaXb_BMARLiHY_ElA5wD8E,12368
+dataeval/outputs/_drift.py,sha256=kS6gGfaf0XOivf1D8go2fzF5yxl0EHlWFlkwv-4LMNI,4770
+dataeval/outputs/_estimators.py,sha256=a2oAIxxEDZ9WLGfMWH8KD-BVUS_SnULRPR-iI9hFPoQ,3047
+dataeval/outputs/_linters.py,sha256=PqLa2wIAkwC-NCb5dhDN29PtTiCUk2TLDFpsMO7Awrc,6325
+dataeval/outputs/_metadata.py,sha256=ffZgpX8KWURPHXpOWjbvJ2KRqWQkS2nWuIjKUzoHhMI,1710
+dataeval/outputs/_ood.py,sha256=suLKVXULGtXH0rq9eXHI1d3d2jhGmItJtz4QiQd47A4,1718
+dataeval/outputs/_stats.py,sha256=ACUzwsalDl-bV8llaBArZQ1tLj07RFvzmv-IXViAvSA,13089
+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=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
+dataeval/utils/_fast_mst.py,sha256=4_7ykVihCL5jWtxcGnrecIsDQo65kUml9SZ1JxgBZYY,7172
+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=xGzrjrOxOP2DP1tU84AWMKPnSxFvSjM81CTlDg4rNM8,331
+dataeval/utils/data/_dataset.py,sha256=MHY582yRm4FxQkkLWUhKZBb7ZyvWypM6ldUG89vd3uE,7936
+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
+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-0.86.0.dist-info/LICENSE.txt,sha256=uAooygKWvX6NbU9Ran9oG2msttoG8aeTeHSTe5JeCnY,1061
+dataeval-0.86.0.dist-info/METADATA,sha256=viF0VCgv5_1SzwfTVCTNdbw1q5k1D3hgJhB7PoZ1tCM,5321
+dataeval-0.86.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+dataeval-0.86.0.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