dataeval 0.75.0__tar.gz → 0.76.0__tar.gz

{dataeval-0.75.0 → dataeval-0.76.0}/LICENSE.txt

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2024 ARiA
+Copyright (c) 2025 ARiA
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
@@ -18,4 +18,4 @@ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+SOFTWARE.

{dataeval-0.75.0 → dataeval-0.76.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dataeval
-Version: 0.75.0
+Version: 0.76.0
 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
@@ -22,7 +22,7 @@ Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Topic :: Scientific/Engineering
 Provides-Extra: all
 Requires-Dist: matplotlib ; extra == "all"
-Requires-Dist: numpy (>=1.24.3)
+Requires-Dist: numpy (>=1.24.2)
 Requires-Dist: pillow (>=10.3.0)
 Requires-Dist: requests
 Requires-Dist: scikit-learn (>=1.5.0)
@@ -52,7 +52,7 @@ DataEval curates datasets to train and test performant, robust, unbiased and rel
 
 <!-- start needs -->
 
-DataEval is an effective, powerful, and reliable set of tools for any T&E engineer. Throughout all stages of the machine learning lifecycle, DataEval supports **model development, data analysis, and monitoring with state-of-the-art algorithms to help you solve difficult problems. With a focus on computer vision tasks, DataEval provides simple, but effective metrics for performance estimation, bias detection, and dataset linting.
+DataEval is an effective, powerful, and reliable set of tools for any T&E engineer. Throughout all stages of the machine learning lifecycle, DataEval supports model development, data analysis, and monitoring with state-of-the-art algorithms to help you solve difficult problems. With a focus on computer vision tasks, DataEval provides simple, but effective metrics for performance estimation, bias detection, and dataset linting.
 
 <!-- end needs -->
 
@@ -74,9 +74,10 @@ Choose your preferred method of installation below or follow our [installation g
 * [Installing from GitHub](#installing-from-github)
 
 ### **Installing with pip**
+
 You can install DataEval directly from pypi.org using the following command.  The optional dependencies of DataEval are `all`.
 
-```
+```bash
 pip install dataeval[all]
 ```
 
@@ -85,7 +86,7 @@ pip install dataeval[all]
 DataEval can be installed in a Conda/Mamba environment using the provided `environment.yaml` file.  As some dependencies
 are installed from the `pytorch` channel, the channel is specified in the below example.
 
-```
+```bash
 micromamba create -f environment\environment.yaml -c pytorch
 ```
 
@@ -93,24 +94,27 @@ micromamba create -f environment\environment.yaml -c pytorch
 
 To install DataEval from source locally on Ubuntu, you will need `git-lfs` to download larger, binary source files and `poetry` for project dependency management.
 
-```
+```bash
 sudo apt-get install git-lfs
 pip install poetry
 ```
 
 Pull the source down and change to the DataEval project directory.
-```
+
+```bash
 git clone https://github.com/aria-ml/dataeval.git
 cd dataeval
 ```
 
 Install DataEval with optional dependencies for development.
-```
+
+```bash
 poetry install --all-extras --with dev
 ```
 
 Now that DataEval is installed, you can run commands in the poetry virtual environment by prefixing shell commands with `poetry run`, or activate the virtual environment directly in the shell.
-```
+
+```bash
 poetry shell
 ```
 
@@ -118,19 +122,16 @@ poetry shell
 
 If you have any questions, feel free to reach out to the people below:
 
-- **POC**: Scott Swan @scott.swan
-- **DPOC**: Andrew Weng @aweng
+* **POC**: Scott Swan @scott.swan
+* **DPOC**: Andrew Weng @aweng
 
 ## Acknowledgement
 
-<!-- start attribution -->
-
-### Alibi-Detect
-This project uses code from the [Alibi-Detect](https://github.com/SeldonIO/alibi-detect) Python library developed by SeldonIO.\
-Additional documentation from their developers is available on the [Alibi-Detect documentation page](https://docs.seldon.io/projects/alibi-detect/en/stable/).
+<!-- start acknowledgement -->
 
 ### CDAO Funding Acknowledgement
+
 This material is based upon work supported by the Chief Digital and Artificial Intelligence Office under Contract No. W519TC-23-9-2033. The views and conclusions contained herein are those of the author(s) and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the U.S. Government.
 
-<!-- end attribution -->
+<!-- end acknowledgement -->
 

{dataeval-0.75.0 → dataeval-0.76.0}/README.md

@@ -14,7 +14,7 @@ DataEval curates datasets to train and test performant, robust, unbiased and rel
 
 <!-- start needs -->
 
-DataEval is an effective, powerful, and reliable set of tools for any T&E engineer. Throughout all stages of the machine learning lifecycle, DataEval supports **model development, data analysis, and monitoring with state-of-the-art algorithms to help you solve difficult problems. With a focus on computer vision tasks, DataEval provides simple, but effective metrics for performance estimation, bias detection, and dataset linting.
+DataEval is an effective, powerful, and reliable set of tools for any T&E engineer. Throughout all stages of the machine learning lifecycle, DataEval supports model development, data analysis, and monitoring with state-of-the-art algorithms to help you solve difficult problems. With a focus on computer vision tasks, DataEval provides simple, but effective metrics for performance estimation, bias detection, and dataset linting.
 
 <!-- end needs -->
 
@@ -36,9 +36,10 @@ Choose your preferred method of installation below or follow our [installation g
 * [Installing from GitHub](#installing-from-github)
 
 ### **Installing with pip**
+
 You can install DataEval directly from pypi.org using the following command.  The optional dependencies of DataEval are `all`.
 
-```
+```bash
 pip install dataeval[all]
 ```
 
@@ -47,7 +48,7 @@ pip install dataeval[all]
 DataEval can be installed in a Conda/Mamba environment using the provided `environment.yaml` file.  As some dependencies
 are installed from the `pytorch` channel, the channel is specified in the below example.
 
-```
+```bash
 micromamba create -f environment\environment.yaml -c pytorch
 ```
 
@@ -55,24 +56,27 @@ micromamba create -f environment\environment.yaml -c pytorch
 
 To install DataEval from source locally on Ubuntu, you will need `git-lfs` to download larger, binary source files and `poetry` for project dependency management.
 
-```
+```bash
 sudo apt-get install git-lfs
 pip install poetry
 ```
 
 Pull the source down and change to the DataEval project directory.
-```
+
+```bash
 git clone https://github.com/aria-ml/dataeval.git
 cd dataeval
 ```
 
 Install DataEval with optional dependencies for development.
-```
+
+```bash
 poetry install --all-extras --with dev
 ```
 
 Now that DataEval is installed, you can run commands in the poetry virtual environment by prefixing shell commands with `poetry run`, or activate the virtual environment directly in the shell.
-```
+
+```bash
 poetry shell
 ```
 
@@ -80,18 +84,15 @@ poetry shell
 
 If you have any questions, feel free to reach out to the people below:
 
-- **POC**: Scott Swan @scott.swan
-- **DPOC**: Andrew Weng @aweng
+* **POC**: Scott Swan @scott.swan
+* **DPOC**: Andrew Weng @aweng
 
 ## Acknowledgement
 
-<!-- start attribution -->
-
-### Alibi-Detect
-This project uses code from the [Alibi-Detect](https://github.com/SeldonIO/alibi-detect) Python library developed by SeldonIO.\
-Additional documentation from their developers is available on the [Alibi-Detect documentation page](https://docs.seldon.io/projects/alibi-detect/en/stable/).
+<!-- start acknowledgement -->
 
 ### CDAO Funding Acknowledgement
+
 This material is based upon work supported by the Chief Digital and Artificial Intelligence Office under Contract No. W519TC-23-9-2033. The views and conclusions contained herein are those of the author(s) and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the U.S. Government.
 
-<!-- end attribution -->
+<!-- end acknowledgement -->

{dataeval-0.75.0 → dataeval-0.76.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "dataeval"
-version = "0.75.0" # dynamic
+version = "0.76.0" # dynamic
 description = "DataEval provides a simple interface to characterize image data and its impact on model performance across classification and object-detection tasks"
 license = "MIT"
 readme = "README.md"
@@ -42,7 +42,7 @@ packages = [
 [tool.poetry.dependencies]
 # required
 python = ">=3.9,<3.13"
-numpy = {version = ">=1.24.3"}
+numpy = {version = ">=1.24.2"}
 pillow = {version = ">=10.3.0"}
 requests = {version = "*"}
 scipy = {version = ">=1.10"}
@@ -88,10 +88,11 @@ certifi = {version = ">=2024.07.04"}
 enum_tools = {version = ">=0.12.0", extras = ["sphinx"]}
 ipykernel = {version = ">=6.26.0"}
 ipywidgets = {version = ">=8.1.1"}
+jinja2 = {version = ">=3.1.5"}
 jupyter-client = {version = ">=8.6.0"}
 jupyter-cache = {version = "*"}
 myst-nb = {version = ">=1.0.0"}
-pydata-sphinx-theme = {version = ">=0.15.4"}
+sphinx-immaterial = {version = "*"}
 sphinx-autoapi = {version = "*"}
 sphinx-design = {version = "*"}
 sphinx-tabs = {version = "*"}
@@ -137,6 +138,7 @@ parallel = true
 [tool.coverage.report]
 exclude_also = [
   "raise NotImplementedError",
+  ": \\.\\.\\."
 ]
 include = ["*/src/dataeval/*"]
 omit = [
@@ -184,7 +186,7 @@ docstring-code-format = true
 docstring-code-line-length = "dynamic"
 
 [tool.codespell]
-skip = './*env*,./prototype,./output,./docs/build,./docs/.jupyter_cache,CHANGELOG.md,poetry.lock,*.html'
+skip = './*env*,./prototype,./output,./docs/build,./docs/source/.jupyter_cache,CHANGELOG.md,poetry.lock,*.html'
 ignore-words-list = ["Hart"]
 
 [build-system]

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/__init__.py

@@ -8,7 +8,7 @@ shifts that impact performance of deployed models.
 from __future__ import annotations
 
 __all__ = ["detectors", "log", "metrics", "utils", "workflows"]
-__version__ = "0.75.0"
+__version__ = "0.76.0"
 
 import logging
 
@@ -24,10 +24,10 @@ def log(level: int = logging.DEBUG, handler: logging.Handler | None = None) -> N
     Parameters
     ----------
     level : int, default logging.DEBUG(10)
-        Set the logging level for the logger
+        Set the logging level for the logger.
     handler : logging.Handler, optional
         Sets the logging handler for the logger if provided, otherwise logger will be
-        provided with a StreamHandler
+        provided with a StreamHandler.
     """
     import logging
 

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/detectors/drift/base.py

@@ -45,7 +45,7 @@ class UpdateStrategy(ABC):
 @dataclass(frozen=True)
 class DriftBaseOutput(Output):
     """
-    Base output class for Drift detector classes
+    Base output class for Drift Detector classes
 
     Attributes
     ----------
@@ -64,7 +64,7 @@ class DriftBaseOutput(Output):
 @dataclass(frozen=True)
 class DriftOutput(DriftBaseOutput):
     """
-    Output class for :class:`DriftCVM`, :class:`DriftKS`, and :class:`DriftUncertainty` drift detectors
+    Output class for :class:`DriftCVM`, :class:`DriftKS`, and :class:`DriftUncertainty` drift detectors.
 
     Attributes
     ----------

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/detectors/drift/ks.py

@@ -22,7 +22,8 @@ from dataeval.interop import to_numpy
 
 class DriftKS(BaseDriftUnivariate):
     """
-    :term:`Drift` detector employing the Kolmogorov-Smirnov (KS) distribution test.
+    :term:`Drift` detector employing the :term:`Kolmogorov-Smirnov (KS) \
+    distribution<Kolmogorov-Smirnov (K-S) test>` test.
 
     The KS test detects changes in the maximum distance between two data
     distributions with Bonferroni or :term:`False Discovery Rate (FDR)` correction

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/detectors/drift/mmd.py

@@ -26,7 +26,7 @@ from dataeval.utils.torch.internal import get_device
 @dataclass(frozen=True)
 class DriftMMDOutput(DriftBaseOutput):
     """
-    Output class for :class:`DriftMMD` :term:`drift<Drift>` detector
+    Output class for :class:`DriftMMD` :term:`drift<Drift>` detector.
 
     Attributes
     ----------
@@ -51,7 +51,8 @@ class DriftMMDOutput(DriftBaseOutput):
 
 class DriftMMD(BaseDrift):
     """
-    :term:`Maximum Mean Discrepancy (MMD) Drift Detection` algorithm using a permutation test.
+    :term:`Maximum Mean Discrepancy (MMD) Drift Detection` algorithm \
+    using a permutation test.
 
     Parameters
     ----------

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/detectors/drift/uncertainty.py

@@ -66,8 +66,8 @@ def classifier_uncertainty(
 
 class DriftUncertainty:
     """
-    Test for a change in the number of instances falling into regions on which the
-    model is uncertain.
+    Test for a change in the number of instances falling into regions on which \
+        the model is uncertain.
 
     Performs a K-S test on prediction entropies.
 

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/detectors/drift/updates.py

@@ -1,5 +1,5 @@
 """
-Update strategies inform how the :term:`drift<Drift>` detector classes update the reference data when monitoring
+Update strategies inform how the :term:`drift<Drift>` detector classes update the reference data when monitoring.
 for drift.
 """
 

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/detectors/linters/clusterer.py

@@ -18,7 +18,7 @@ from dataeval.utils.shared import flatten
 @dataclass(frozen=True)
 class ClustererOutput(Output):
     """
-    Output class for :class:`Clusterer` lint detector
+    Output class for :class:`Clusterer` lint detector.
 
     Attributes
     ----------
@@ -131,7 +131,8 @@ class _ClusterMergeEntry:
 
 class Clusterer:
     """
-    Uses hierarchical clustering to flag dataset properties of interest like Outliers and :term:`duplicates<Duplicates>`
+    Uses hierarchical clustering to flag dataset properties of interest like outliers \
+    and :term:`duplicates<Duplicates>`.
 
     Parameters
     ----------

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/detectors/linters/duplicates.py

@@ -19,7 +19,7 @@ TIndexCollection = TypeVar("TIndexCollection", DuplicateGroup, DatasetDuplicateG
 @dataclass(frozen=True)
 class DuplicatesOutput(Generic[TIndexCollection], Output):
     """
-    Output class for :class:`Duplicates` lint detector
+    Output class for :class:`Duplicates` lint detector.
 
     Attributes
     ----------
@@ -39,8 +39,8 @@ class DuplicatesOutput(Generic[TIndexCollection], Output):
 
 class Duplicates:
     """
-    Finds the duplicate images in a dataset using xxhash for exact :term:`duplicates<Duplicates>`
-    and pchash for near duplicates
+    Finds the duplicate images in a dataset using xxhash for exact \
+    :term:`duplicates<Duplicates>` and pchash for near duplicates.
 
     Attributes
     ----------
@@ -92,7 +92,7 @@ class Duplicates:
 
         Parameters
         ----------
-        data : HashStatsOutput | Sequence[HashStatsOutput]
+        hashes : HashStatsOutput | Sequence[HashStatsOutput]
             The output(s) from a hashstats analysis
 
         Returns

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/detectors/linters/outliers.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 __all__ = []
 
+# import contextlib
 from dataclasses import dataclass
 from typing import Generic, Iterable, Literal, Sequence, TypeVar, Union, overload
 
@@ -12,19 +13,78 @@ from dataeval.detectors.linters.merged_stats import combine_stats, get_dataset_s
 from dataeval.metrics.stats.base import BOX_COUNT, SOURCE_INDEX
 from dataeval.metrics.stats.datasetstats import DatasetStatsOutput, datasetstats
 from dataeval.metrics.stats.dimensionstats import DimensionStatsOutput
+from dataeval.metrics.stats.labelstats import LabelStatsOutput
 from dataeval.metrics.stats.pixelstats import PixelStatsOutput
 from dataeval.metrics.stats.visualstats import VisualStatsOutput
 from dataeval.output import Output, set_metadata
 
+# with contextlib.suppress(ImportError):
+#     import pandas as pd
+
+
 IndexIssueMap = dict[int, dict[str, float]]
 OutlierStatsOutput = Union[DimensionStatsOutput, PixelStatsOutput, VisualStatsOutput]
 TIndexIssueMap = TypeVar("TIndexIssueMap", IndexIssueMap, list[IndexIssueMap])
 
 
+def _reorganize_by_class_and_metric(result, lstats):
+    """Flip result from grouping by image to grouping by class and metric"""
+    metrics = {}
+    class_wise = {label: {} for label in lstats.image_indices_per_label}
+
+    # Group metrics and calculate class-wise counts
+    for img, group in result.items():
+        for extreme in group:
+            metrics.setdefault(extreme, []).append(img)
+            for label, images in lstats.image_indices_per_label.items():
+                if img in images:
+                    class_wise[label][extreme] = class_wise[label].get(extreme, 0) + 1
+
+    return metrics, class_wise
+
+
+def _create_table(metrics, class_wise):
+    """Create table for displaying the results"""
+    max_class_length = max(len(str(label)) for label in class_wise) + 2
+    max_total = max(len(metrics[group]) for group in metrics) + 2
+
+    table_header = " | ".join(
+        [f"{'Class':>{max_class_length}}"]
+        + [f"{group:^{max(5, len(str(group))) + 2}}" for group in sorted(metrics.keys())]
+        + [f"{'Total':<{max_total}}"]
+    )
+    table_rows = []
+
+    for class_cat, results in class_wise.items():
+        table_value = [f"{class_cat:>{max_class_length}}"]
+        total = 0
+        for group in sorted(metrics.keys()):
+            count = results.get(group, 0)
+            table_value.append(f"{count:^{max(5, len(str(group))) + 2}}")
+            total += count
+        table_value.append(f"{total:^{max_total}}")
+        table_rows.append(" | ".join(table_value))
+
+    table = [table_header] + table_rows
+    return table
+
+
+# def _create_pandas_dataframe(class_wise):
+#     """Create data for pandas dataframe"""
+#     data = []
+#     for label, metrics_dict in class_wise.items():
+#         row = {"Class": label}
+#         total = sum(metrics_dict.values())
+#         row.update(metrics_dict)  # Add metric counts
+#         row["Total"] = total
+#         data.append(row)
+#     return data
+
+
 @dataclass(frozen=True)
 class OutliersOutput(Generic[TIndexIssueMap], Output):
     """
-    Output class for :class:`Outliers` lint detector
+    Output class for :class:`Outliers` lint detector.
 
     Attributes
     ----------
@@ -45,6 +105,39 @@ class OutliersOutput(Generic[TIndexIssueMap], Output):
         else:
             return sum(len(d) for d in self.issues)
 
+    def to_table(self, labelstats: LabelStatsOutput) -> str:
+        if isinstance(self.issues, dict):
+            metrics, classwise = _reorganize_by_class_and_metric(self.issues, labelstats)
+            listed_table = _create_table(metrics, classwise)
+            table = "\n".join(listed_table)
+        else:
+            outertable = []
+            for d in self.issues:
+                metrics, classwise = _reorganize_by_class_and_metric(d, labelstats)
+                listed_table = _create_table(metrics, classwise)
+                str_table = "\n".join(listed_table)
+                outertable.append(str_table)
+            table = "\n\n".join(outertable)
+        return table
+
+    # def to_dataframe(self, labelstats: LabelStatsOutput) -> pd.DataFrame:
+    #     import pandas as pd
+
+    #     if isinstance(self.issues, dict):
+    #         _, classwise = _reorganize_by_class_and_metric(self.issues, labelstats)
+    #         data = _create_pandas_dataframe(classwise)
+    #         df = pd.DataFrame(data)
+    #     else:
+    #         df_list = []
+    #         for i, d in enumerate(self.issues):
+    #             _, classwise = _reorganize_by_class_and_metric(d, labelstats)
+    #             data = _create_pandas_dataframe(classwise)
+    #             single_df = pd.DataFrame(data)
+    #             single_df["Dataset"] = i
+    #             df_list.append(single_df)
+    #         df = pd.concat(df_list)
+    #     return df
+
 
 def _get_outlier_mask(
     values: NDArray, method: Literal["zscore", "modzscore", "iqr"], threshold: float | None
@@ -71,7 +164,7 @@ def _get_outlier_mask(
 
 class Outliers:
     r"""
-    Calculates statistical Outliers of a dataset using various statistical tests applied to each image
+    Calculates statistical outliers of a dataset using various statistical tests applied to each image.
 
     Parameters
     ----------
@@ -164,7 +257,7 @@ class Outliers:
         self, stats: OutlierStatsOutput | DatasetStatsOutput | Sequence[OutlierStatsOutput]
     ) -> OutliersOutput[IndexIssueMap] | OutliersOutput[list[IndexIssueMap]]:
         """
-        Returns indices of Outliers with the issues identified for each
+        Returns indices of Outliers with the issues identified for each.
 
         Parameters
         ----------

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/detectors/ood/__init__.py

@@ -1,5 +1,5 @@
 """
-Out-of-distribution (OOD)` detectors identify data that is different from the data used to train a particular model.
+Out-of-distribution (OOD) detectors identify data that is different from the data used to train a particular model.
 """
 
 __all__ = ["OODOutput", "OODScoreOutput", "OOD_AE"]

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/detectors/ood/base.py

@@ -87,24 +87,8 @@ class OODBaseGMM(OODBase, OODGMMMixin[GaussianMixtureModelParams]):
         batch_size: int,
         verbose: bool,
     ) -> None:
-        # Train the model
-        trainer(
-            model=self.model,
-            x_train=to_numpy(x_ref),
-            y_train=None,
-            loss_fn=loss_fn,
-            optimizer=optimizer,
-            preprocess_fn=None,
-            epochs=epochs,
-            batch_size=batch_size,
-            device=self.device,
-            verbose=verbose,
-        )
+        super().fit(x_ref, threshold_perc, loss_fn, optimizer, epochs, batch_size, verbose)
 
         # Calculate the GMM parameters
         _, z, gamma = cast(tuple[torch.Tensor, torch.Tensor, torch.Tensor], self.model(x_ref))
         self._gmm_params = gmm_params(z, gamma)
-
-        # Infer the threshold values
-        self._ref_score = self.score(x_ref, batch_size)
-        self._threshold_perc = threshold_perc

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/detectors/ood/output.py

@@ -36,7 +36,7 @@ class OODScoreOutput(Output):
     """
     Output class for instance and feature scores from out-of-distribution detectors.
 
-    Parameters
+    Attributes
     ----------
     instance_score : NDArray
         Instance score of the evaluated dataset.

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/interop.py

@@ -46,7 +46,7 @@ def to_numpy(array: ArrayLike | None, copy: bool = True) -> NDArray[Any]:
     if isinstance(array, np.ndarray):
         return array.copy() if copy else array
 
-    if array.__class__.__module__.startswith("tensorflow"):
+    if array.__class__.__module__.startswith("tensorflow"):  # pragma: no cover - removed tf from deps
         tf = _try_import("tensorflow")
         if tf and tf.is_tensor(array):
             _logger.log(logging.INFO, "Converting Tensorflow array to NumPy array.")

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/metrics/__init__.py

@@ -1,5 +1,5 @@
 """
-Metrics are a way to measure the performance of your models or datasets that
+Metrics are a way to measure the performance of your models or datasets that \
 can then be analyzed in the context of a given problem.
 """
 

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/metrics/bias/__init__.py

@@ -1,5 +1,5 @@
 """
-Bias metrics check for skewed or imbalanced datasets and incomplete feature
+Bias metrics check for skewed or imbalanced datasets and incomplete feature \
 representation which may impact model performance.
 """
 

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/metrics/bias/balance.py

@@ -23,8 +23,8 @@ with contextlib.suppress(ImportError):
 @dataclass(frozen=True)
 class BalanceOutput(Output):
     """
-    Output class for :func:`balance` bias metric
-
+    Output class for :func:`balance` :term:`bias<Bias>` metric.
+    
     Attributes
     ----------
     balance : NDArray[np.float64]
@@ -123,7 +123,7 @@ def balance(
     num_neighbors: int = 5,
 ) -> BalanceOutput:
     """
-    Mutual information (MI) between factors (class label, metadata, label/image properties)
+    Mutual information (MI) between factors (class label, metadata, label/image properties).
 
     Parameters
     ----------

{dataeval-0.75.0 → dataeval-0.76.0}/src/dataeval/metrics/bias/coverage.py

@@ -71,7 +71,7 @@ def _plot(images: NDArray[Any], num_images: int) -> Figure:
 @dataclass(frozen=True)
 class CoverageOutput(Output):
     """
-    Output class for :func:`coverage` :term:`bias<Bias>` metric
+    Output class for :func:`coverage` :term:`bias<Bias>` metric.
 
     Attributes
     ----------