dataeval 0.86.7__tar.gz → 0.86.8__tar.gz

dataeval-0.86.8/.gitignore

@@ -0,0 +1,28 @@
+*venv*/
+__pycache__/
+dist/
+
+data/
+!src/dataeval/data
+!src/dataeval/utils/data
+!tests/data
+!tests/utils/data
+
+docs/build/
+docs/source/reference/autoapi
+docs/source/tutorials/notebooks/checkpoints/
+
+output/
+.coverage*
+
+.tox/
+.nox/
+.python-version
+
+# Used to store user customizable settings
+.settings
+# debug profiles
+.vscode/launch.json
+
+# Autogenerated version file
+src/dataeval/_version.py

{dataeval-0.86.7 → dataeval-0.86.8}/PKG-INFO

@@ -1,45 +1,52 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: dataeval
-Version: 0.86.7
+Version: 0.86.8
 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
-Author: Andrew Weng
-Author-email: andrew.weng@ariacoustics.com
-Maintainer: ARiA
-Maintainer-email: dataeval@ariacoustics.com
-Requires-Python: >=3.9,<3.13
+Project-URL: Homepage, https://dataeval.ai/
+Project-URL: Repository, https://github.com/aria-ml/dataeval/
+Project-URL: Documentation, https://dataeval.readthedocs.io/
+Author-email: Andrew Weng <andrew.weng@ariacoustics.com>, Bill Peria <bill.peria@ariacoustics.com>, Jon Botts <jonathan.botts@ariacoustics.com>, Jonathan Christian <jonathan.christian@ariacoustics.com>, Justin McMillan <justin.mcmillan@ariacoustics.com>, Ryan Wood <ryan.wood@ariacoustics.com>, Scott Swan <scott.swan@ariacoustics.com>, Shaun Jullens <shaun.jullens@ariacoustics.com>
+Maintainer-email: ARiA <dataeval@ariacoustics.com>
+License-Expression: MIT
+License-File: LICENSE.txt
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Topic :: Scientific/Engineering
+Requires-Python: <3.13,>=3.9
+Requires-Dist: defusedxml>=0.7.1
+Requires-Dist: fast-hdbscan==0.2.0
+Requires-Dist: lightgbm>=4
+Requires-Dist: numba>=0.59.1
+Requires-Dist: numpy>=1.24.2
+Requires-Dist: pandas>=2.0
+Requires-Dist: pillow>=10.3.0
+Requires-Dist: polars>=1.0.0
+Requires-Dist: requests>=2.32.3
+Requires-Dist: scikit-learn>=1.5.0
+Requires-Dist: scipy>=1.10
+Requires-Dist: torch>=2.2.0
+Requires-Dist: torchvision>=0.17.0
+Requires-Dist: tqdm>=4.66
+Requires-Dist: typing-extensions>=4.12; python_version ~= '3.9'
+Requires-Dist: xxhash>=3.3
 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)
-Requires-Dist: pillow (>=10.3.0)
-Requires-Dist: polars (>=1.0.0)
-Requires-Dist: requests
-Requires-Dist: scikit-learn (>=1.5.0)
-Requires-Dist: scipy (>=1.10)
-Requires-Dist: torch (>=2.2.0)
-Requires-Dist: torchvision (>=0.17.0)
-Requires-Dist: tqdm
-Requires-Dist: typing-extensions (>=4.12) ; python_version >= "3.9" and python_version < "4.0"
-Requires-Dist: xxhash (>=3.3)
-Project-URL: Documentation, https://dataeval.readthedocs.io/
-Project-URL: Repository, https://github.com/aria-ml/dataeval/
+Requires-Dist: matplotlib>=3.7.1; extra == 'all'
+Provides-Extra: cpu
+Requires-Dist: torch>=2.2.0; extra == 'cpu'
+Requires-Dist: torchvision>=0.17.0; extra == 'cpu'
+Provides-Extra: cu118
+Requires-Dist: torch>=2.2.0; extra == 'cu118'
+Requires-Dist: torchvision>=0.17.0; extra == 'cu118'
+Provides-Extra: cu124
+Requires-Dist: torch>=2.2.0; extra == 'cu124'
+Requires-Dist: torchvision>=0.17.0; extra == 'cu124'
 Description-Content-Type: text/markdown
 
 # DataEval
@@ -72,26 +79,28 @@ estimation, bias detection, and dataset linting.
 <!-- end needs -->
 
 <!-- start JATIC interop -->
+
 DataEval is easy to install, supports a wide range of Python versions, and is
 compatible with many of the most popular packages in the scientific and T&E
 communities.
 
 DataEval also has native interoperability between JATIC's suite of tools when
 using MAITE-compliant datasets and models.
+
 <!-- end JATIC interop -->
 
 ## Getting Started
 
 **Python versions:** 3.9 - 3.12
 
-**Supported packages**: *NumPy*, *Pandas*, *Sci-kit learn*, *MAITE*, *NRTK*
+**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).
 
-* [Installing with pip](#installing-with-pip)
-* [Installing with conda/mamba](#installing-with-conda)
-* [Installing from GitHub](#installing-from-github)
+- [Installing with pip](#installing-with-pip)
+- [Installing with conda/mamba](#installing-with-conda)
+- [Installing from GitHub](#installing-from-github)
 
 ### **Installing with pip**
 
@@ -105,7 +114,7 @@ pip install dataeval[all]
 ### **Installing with conda**
 
 DataEval can be installed in a Conda/Mamba environment using the provided
-`environment.yaml` file.  As some dependencies are installed from the `pytorch`
+`environment.yaml` file. As some dependencies are installed from the `pytorch`
 channel, the channel is specified in the below example.
 
 ```bash
@@ -115,12 +124,10 @@ micromamba create -f environment\environment.yaml -c pytorch
 ### **Installing from GitHub**
 
 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.
+download larger, binary source files.
 
 ```bash
 sudo apt-get install git-lfs
-pip install poetry
 ```
 
 Pull the source down and change to the DataEval project directory.
@@ -130,26 +137,40 @@ git clone https://github.com/aria-ml/dataeval.git
 cd dataeval
 ```
 
-Install DataEval with optional dependencies for development.
+#### **Using Poetry**
+
+Install DataEval with all extras.
 
 ```bash
-poetry install --all-extras --with dev
+poetry install --extras=all
 ```
 
-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.
+Enable Poetry's virtual environment.
 
 ```bash
-poetry shell
+poetry env activate
+```
+
+#### **Using uv**
+
+Install DataEval with all extras and dependencies for development.
+
+```bash
+uv sync --extra=all
+```
+
+Enable uv's virtual environment.
+
+```bash
+source .venv/bin/activate
 ```
 
 ## Contact Us
 
 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
 
@@ -164,4 +185,3 @@ interpreted as necessarily representing the official policies or endorsements,
 either expressed or implied, of the U.S. Government.
 
 <!-- end acknowledgement -->
-

{dataeval-0.86.7 → dataeval-0.86.8}/README.md

@@ -28,26 +28,28 @@ estimation, bias detection, and dataset linting.
 <!-- end needs -->
 
 <!-- start JATIC interop -->
+
 DataEval is easy to install, supports a wide range of Python versions, and is
 compatible with many of the most popular packages in the scientific and T&E
 communities.
 
 DataEval also has native interoperability between JATIC's suite of tools when
 using MAITE-compliant datasets and models.
+
 <!-- end JATIC interop -->
 
 ## Getting Started
 
 **Python versions:** 3.9 - 3.12
 
-**Supported packages**: *NumPy*, *Pandas*, *Sci-kit learn*, *MAITE*, *NRTK*
+**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).
 
-* [Installing with pip](#installing-with-pip)
-* [Installing with conda/mamba](#installing-with-conda)
-* [Installing from GitHub](#installing-from-github)
+- [Installing with pip](#installing-with-pip)
+- [Installing with conda/mamba](#installing-with-conda)
+- [Installing from GitHub](#installing-from-github)
 
 ### **Installing with pip**
 
@@ -61,7 +63,7 @@ pip install dataeval[all]
 ### **Installing with conda**
 
 DataEval can be installed in a Conda/Mamba environment using the provided
-`environment.yaml` file.  As some dependencies are installed from the `pytorch`
+`environment.yaml` file. As some dependencies are installed from the `pytorch`
 channel, the channel is specified in the below example.
 
 ```bash
@@ -71,12 +73,10 @@ micromamba create -f environment\environment.yaml -c pytorch
 ### **Installing from GitHub**
 
 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.
+download larger, binary source files.
 
 ```bash
 sudo apt-get install git-lfs
-pip install poetry
 ```
 
 Pull the source down and change to the DataEval project directory.
@@ -86,26 +86,40 @@ git clone https://github.com/aria-ml/dataeval.git
 cd dataeval
 ```
 
-Install DataEval with optional dependencies for development.
+#### **Using Poetry**
+
+Install DataEval with all extras.
+
+```bash
+poetry install --extras=all
+```
+
+Enable Poetry's virtual environment.
+
+```bash
+poetry env activate
+```
+
+#### **Using uv**
+
+Install DataEval with all extras and dependencies for development.
 
 ```bash
-poetry install --all-extras --with dev
+uv sync --extra=all
 ```
 
-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.
+Enable uv's virtual environment.
 
 ```bash
-poetry shell
+source .venv/bin/activate
 ```
 
 ## Contact Us
 
 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
 

dataeval-0.86.8/pyproject.toml

@@ -0,0 +1,261 @@
+[project]
+name = "dataeval"
+dynamic = ["version"]
+description = "DataEval provides a simple interface to characterize image data and its impact on model performance across classification and object-detection tasks"
+authors = [
+  { name = "Andrew Weng", email = "andrew.weng@ariacoustics.com" },
+  { name = "Bill Peria", email = "bill.peria@ariacoustics.com" },
+  { name = "Jon Botts", email = "jonathan.botts@ariacoustics.com" },
+  { name = "Jonathan Christian", email = "jonathan.christian@ariacoustics.com" },
+  { name = "Justin McMillan", email = "justin.mcmillan@ariacoustics.com" },
+  { name = "Ryan Wood", email = "ryan.wood@ariacoustics.com" },
+  { name = "Scott Swan", email = "scott.swan@ariacoustics.com" },
+  { name = "Shaun Jullens", email = "shaun.jullens@ariacoustics.com" },
+]
+requires-python = ">=3.9,<3.13"
+readme = "README.md"
+license = "MIT"
+maintainers = [
+  { name = "ARiA", email = "dataeval@ariacoustics.com" },
+]
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "Operating System :: OS Independent",
+  "Intended Audience :: Science/Research",
+  "License :: OSI Approved :: MIT License",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Topic :: Scientific/Engineering",
+]
+dependencies = [
+  "defusedxml>=0.7.1",
+  "fast_hdbscan==0.2.0",
+  "lightgbm>=4",
+  "numba>=0.59.1",
+  "numpy>=1.24.2",
+  "pandas>=2.0",
+  "pillow>=10.3.0",
+  "polars>=1.0.0",
+  "requests>=2.32.3",
+  "scipy>=1.10",
+  "scikit-learn>=1.5.0",
+  "torch>=2.2.0",
+  "torchvision>=0.17.0",
+  "tqdm>=4.66",
+  "typing-extensions>=4.12 ; python_version ~= '3.9'",
+  "xxhash>=3.3",
+]
+
+[project.optional-dependencies]
+cpu = [
+  "torch>=2.2.0",
+  "torchvision>=0.17.0",
+]
+cu118 = [
+  "torch>=2.2.0",
+  "torchvision>=0.17.0",
+]
+cu124 = [
+  "torch>=2.2.0",
+  "torchvision>=0.17.0",
+]
+all = ["matplotlib>=3.7.1"]
+
+[project.urls]
+Homepage = "https://dataeval.ai/"
+Repository = "https://github.com/aria-ml/dataeval/"
+Documentation = "https://dataeval.readthedocs.io/"
+
+[dependency-groups]
+base = [
+  "nox[uv]>=2025.5.1",
+  "uv>=0.7.8",
+  "pip>=25",
+]
+lint = [
+  "ruff>=0.11",
+  "codespell[toml]>=2.3",
+]
+test = [
+  "pytest>=8.3",
+  "pytest-cov>=6.1",
+  "pytest-xdist>=3.6.1",
+  "coverage[toml]>=7.6",
+]
+type = [
+  "pyright[nodejs]>=1.1.400",
+]
+docs = [
+  "numpy>=2.0.2",
+  "certifi>=2024.07.04",
+  "ipykernel>=6.26.0",
+  "ipywidgets>=8.1.1",
+  "jinja2>=3.1.6",
+  "jupyter-client>=8.6.0",
+  "jupyter-cache>=1.0",
+  "myst-nb>=1.0",
+  "sphinx-autoapi>=3.6.0",
+  "sphinx-design>=0.6.1",
+  "sphinx-immaterial>=0.12.5",
+  "sphinx-new-tab-link>=0.8.0",
+  "sphinx-tabs>=3.4.7",
+  "Sphinx>=7.2.6",
+  "torchmetrics>=1.0.0",
+  "markupsafe>=3,<3.0.2",
+]
+dev = [
+  { include-group = "base" },
+  { include-group = "lint" },
+  { include-group = "test" },
+  { include-group = "type" },
+  { include-group = "docs" },
+]
+
+[tool.uv]
+conflicts = [
+  [
+    { extra = "cpu" },
+    { extra = "cu118" },
+    { extra = "cu124" },
+  ],
+]
+
+[[tool.uv.index]]
+name = "pytorch-cpu"
+url = "https://download.pytorch.org/whl/cpu"
+explicit = true
+
+[[tool.uv.index]]
+name = "pytorch-cu118"
+url = "https://download.pytorch.org/whl/cu118"
+explicit = true
+
+[[tool.uv.index]]
+name = "pytorch-cu124"
+url = "https://download.pytorch.org/whl/cu124"
+explicit = true
+
+[tool.uv.sources]
+torch = [
+  { index = "pytorch-cpu", extra = "cpu" },
+  { index = "pytorch-cu118", extra = "cu118" },
+  { index = "pytorch-cu124", extra = "cu124" },
+]
+torchvision = [
+  { index = "pytorch-cpu", extra = "cpu" },
+  { index = "pytorch-cu118", extra = "cu118" },
+  { index = "pytorch-cu124", extra = "cu124" },
+]
+
+[tool.hatch.build.targets.sdist]
+include = ["src/dataeval"]
+
+[tool.hatch.build.targets.wheel]
+include = ["src/dataeval"]
+
+[tool.hatch.build.targets.wheel.sources]
+"src/dataeval" = "dataeval"
+
+[tool.hatch.version]
+source = "vcs"
+
+[tool.hatch.build.hooks.vcs]
+version-file = "src/dataeval/_version.py"
+
+[tool.poetry]
+version = "0.0.0"  # unused
+
+[tool.pyproject2conda.dependencies]
+torch = { pip = true }
+torchvision = { pip = true }
+xxhash = { skip = true, packages = "python-xxhash>=3.3" }
+
+[tool.pyright]
+reportMissingImports = false
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = [
+  "--pythonwarnings=ignore::DeprecationWarning",
+  "--verbose",
+  "--durations=20",
+  "--durations-min=1.0",
+]
+markers = [
+  "required: marks tests for required features",
+  "optional: marks tests for optional features",
+  "requires_all: marks tests that require matplotlib",
+  "cuda: marks tests that require cuda",
+  "year: marks tests that need a specified dataset year",
+]
+
+[tool.coverage.run]
+source = ["src/dataeval"]
+branch = true
+concurrency = ["multiprocessing"]
+parallel = true
+omit = ["src/dataeval/_version.py"]
+
+[tool.coverage.report]
+exclude_also = [
+  "raise NotImplementedError",
+  ": \\.\\.\\.",
+  "if TYPE_CHECKING:"
+]
+include = ["*/src/dataeval/*"]
+omit = [
+  "*/torch/_blocks.py",
+  "*/_clusterer.py",
+  "*/_fast_mst.py",
+]
+fail_under = 90
+
+[tool.ruff]
+exclude = [
+  ".devcontainer",
+  ".github",
+  ".vscode",
+  ".jupyter_cache",
+  "*env*",
+  "output",
+  "build",
+  ".nox",
+  ".tox",
+]
+line-length = 120
+indent-width = 4
+target-version = "py38"
+extend-include = ["*.ipynb"]
+
+[tool.ruff.lint]
+select = ["A", "ANN", "C4", "C90", "E", "F", "I", "NPY", "S", "SIM", "RET", "RUF100", "UP"]
+ignore = ["ANN401", "NPY002"]
+fixable = ["ALL"]
+unfixable = []
+dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
+per-file-ignores = { "*.ipynb" = ["E402"],  "!src/*" = ["ANN", "S", "RET"]}
+
+[tool.ruff.lint.isort]
+known-first-party = ["dataeval"]
+
+[tool.ruff.lint.flake8-builtins]
+builtins-strict-checking = false
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+skip-magic-trailing-comma = false
+line-ending = "auto"
+docstring-code-format = true
+docstring-code-line-length = "dynamic"
+
+[tool.codespell]
+skip = './*env*,./output,./docs/build,./docs/source/.jupyter_cache,CHANGELOG.md,uv.lock,requirements.txt,*.html,./docs/source/*/data'
+ignore-words-list = ["Hart"]
+
+[build-system]
+requires = ["hatchling", "hatch-vcs"]
+build-backend = "hatchling.build"

{dataeval-0.86.7 → dataeval-0.86.8}/src/dataeval/__init__.py

@@ -7,12 +7,19 @@ shifts that impact performance of deployed models.
 
 from __future__ import annotations
 
-__all__ = ["config", "detectors", "log", "metrics", "typing", "utils", "workflows"]
-__version__ = "0.86.7"
+try:
+    from ._version import __version__
+except ImportError:
+    __version__ = "unknown"
+
+# Strongly type for pyright
+__version__ = str(__version__)
+
+__all__ = ["__version__", "config", "detectors", "log", "metrics", "typing", "utils", "workflows"]
 
 import logging
 
-from dataeval import config, detectors, metrics, typing, utils, workflows
+from . import config, detectors, metrics, typing, utils, workflows
 
 logging.getLogger(__name__).addHandler(logging.NullHandler())
 

dataeval-0.86.8/src/dataeval/_version.py

@@ -0,0 +1,21 @@
+# file generated by setuptools-scm
+# don't change, don't track in version control
+
+__all__ = ["__version__", "__version_tuple__", "version", "version_tuple"]
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple
+    from typing import Union
+
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+else:
+    VERSION_TUPLE = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+
+__version__ = version = '0.86.8'
+__version_tuple__ = version_tuple = (0, 86, 8)

{dataeval-0.86.7 → dataeval-0.86.8}/src/dataeval/config.py

@@ -77,7 +77,13 @@ def get_device(override: DeviceLike | None = None) -> torch.device:
     """
     if override is None:
         global _device
-        return torch.get_default_device() if _device is None else _device
+        return (
+            torch.get_default_device()
+            if hasattr(torch, "get_default_device")
+            else torch.device("cpu")
+            if _device is None
+            else _device
+        )
     return _todevice(override)
 
 

{dataeval-0.86.7 → dataeval-0.86.8}/src/dataeval/detectors/drift/_mvdc.py

@@ -1,16 +1,9 @@
 from __future__ import annotations
 
-from typing import TYPE_CHECKING
-
 import numpy as np
 import pandas as pd
 from numpy.typing import ArrayLike
 
-if TYPE_CHECKING:
-    from typing import Self
-else:
-    from typing_extensions import Self
-
 from dataeval.detectors.drift._nml._chunk import CountBasedChunker, SizeBasedChunker
 from dataeval.detectors.drift._nml._domainclassifier import DomainClassifierCalculator
 from dataeval.detectors.drift._nml._thresholds import ConstantThreshold
@@ -52,7 +45,7 @@ class DriftMVDC:
             threshold=ConstantThreshold(lower=self.threshold[0], upper=self.threshold[1]),
         )
 
-    def fit(self, x_ref: ArrayLike) -> Self:
+    def fit(self, x_ref: ArrayLike) -> DriftMVDC:
         """
         Fit the domain classifier on the training dataframe
 
@@ -63,7 +56,7 @@ class DriftMVDC:
 
         Returns
         -------
-        Self
+        DriftMVDC
 
         """
         # for 1D input, assume that is 1 sample: dim[1,n_features]