dataeval 1.0.6__tar.gz → 1.1.0__tar.gz

{dataeval-1.0.6 → dataeval-1.1.0}/.gitignore

@@ -16,6 +16,12 @@ docs/source/tutorials/notebooks/checkpoints/
 # See scripts/README.md for details
 .jupyter_cache/
 
+# IPython runtime files and configuration
+docs/source/.ipython/*
+!docs/source/.ipython/profile_default/
+docs/source/.ipython/profile_default/*
+!docs/source/.ipython/profile_default/ipython_kernel_config.py
+
 # Generated notebook files - stored in docs-artifacts branches for Colab
 docs/source/notebooks/*.ipynb
 
@@ -24,6 +30,7 @@ output/
 
 .tox/
 .nox/
+.numba-cache/
 .python-version
 .cuda-version
 

dataeval-1.0.6/README.md → dataeval-1.1.0/PKG-INFO

@@ -1,4 +1,68 @@
+Metadata-Version: 2.5
+Name: dataeval
+Version: 1.1.0
+Summary: DataEval provides a simple interface to characterize image data and its impact on model performance across classification and object-detection tasks
+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>, Christina Doty <christina.doty@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>
+Maintainer-email: ARiA <dataeval@ariacoustics.com>
+License-Expression: MIT
+License-File: LICENSE
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.10
+Requires-Dist: lightgbm>=4
+Requires-Dist: maite>=0.9.4
+Requires-Dist: numba>=0.61.0
+Requires-Dist: numpy>=1.24.2
+Requires-Dist: polars>=1.0.0
+Requires-Dist: psutil>=7.0.0
+Requires-Dist: pydantic>=2.8
+Requires-Dist: scikit-learn>=1.5.0
+Requires-Dist: scipy>=1.10.0
+Requires-Dist: torch>=2.2.0
+Requires-Dist: typing-extensions>=4.12
+Requires-Dist: xxhash>=3.4
+Provides-Extra: cpu
+Requires-Dist: torch>=2.2.0; extra == 'cpu'
+Requires-Dist: torchvision>=0.17.0; extra == 'cpu'
+Provides-Extra: cu126
+Requires-Dist: torch>=2.2.0; extra == 'cu126'
+Requires-Dist: torchvision>=0.17.0; extra == 'cu126'
+Provides-Extra: cu130
+Requires-Dist: torch>=2.2.0; extra == 'cu130'
+Requires-Dist: torchvision>=0.17.0; extra == 'cu130'
+Provides-Extra: litert
+Requires-Dist: ai-edge-litert>=2.0; (python_version <= '3.14') and extra == 'litert'
+Provides-Extra: onnx
+Requires-Dist: onnx>=1.14.0; extra == 'onnx'
+Requires-Dist: onnxruntime>=1.17; extra == 'onnx'
+Provides-Extra: onnx-cu126
+Requires-Dist: onnx>=1.14.0; extra == 'onnx-cu126'
+Requires-Dist: onnxruntime-gpu<1.24,>=1.17; (python_version == '3.10' and extra != 'onnx-cu130') and extra == 'onnx-cu126'
+Requires-Dist: onnxruntime-gpu<1.27,>=1.17; (python_version >= '3.11' and extra != 'onnx-cu130') and extra == 'onnx-cu126'
+Requires-Dist: onnxruntime-gpu<1.27,>=1.24; (python_version >= '3.14' and extra != 'onnx-cu130') and extra == 'onnx-cu126'
+Provides-Extra: onnx-cu130
+Requires-Dist: onnx>=1.14.0; extra == 'onnx-cu130'
+Requires-Dist: onnxruntime-gpu>=1.27; (python_version >= '3.11' and extra != 'onnx-cu126') and extra == 'onnx-cu130'
+Requires-Dist: onnxruntime>=1.17; (python_version == '3.10' and extra != 'onnx-cu126') and extra == 'onnx-cu130'
+Provides-Extra: ontology
+Requires-Dist: rdflib>=7.0; extra == 'ontology'
+Provides-Extra: opencv
+Requires-Dist: opencv-python-headless>=4.8.0; extra == 'opencv'
+Description-Content-Type: text/markdown
+
 <!-- markdownlint-disable MD041 -->
+
 ![dataeval-logo](docs/source/_static/images/DataEval_ImageText.png)
 
 <!-- :auto badges: -->
@@ -64,6 +128,7 @@ Choose your preferred method of installation below or follow our
 [installation guide](docs/source/getting-started/installation.md).
 
 - [Installing with pip](#installing-with-pip)
+- [Installing with uv](#installing-with-uv)
 - [Installing with conda/mamba](#installing-with-conda)
 - [Installing from GitHub](#installing-from-github)
 
@@ -75,14 +140,76 @@ You can install DataEval directly from pypi.org using the following command.
 pip install dataeval
 ```
 
+By default, PyTorch is installed from PyPI, which bundles CUDA support on Linux
+and is a much larger download than the CPU build. To choose a specific PyTorch
+variant, install `torch` from that variant's wheel index **first**, then install
+DataEval — it accepts the build already present in the environment:
+
+```bash
+# 1. Pick your PyTorch build (cpu / cu126 / cu130)
+pip install torch --index-url https://download.pytorch.org/whl/cu130
+
+# 2. Install DataEval
+pip install dataeval
+```
+
+> **Use `--index-url`, not `--extra-index-url`, to pick a CUDA build.**
+> `--extra-index-url` *adds* an index instead of replacing PyPI, and pip then
+> takes the highest version across both. The CUDA indexes lag the latest PyTorch
+> release, so PyPI usually wins and you silently get the default CUDA-bundled
+> build — the install succeeds with no warning. `--index-url` replaces the index
+> outright, so it is reliable. (For CPU only,
+> `pip install dataeval --extra-index-url https://download.pytorch.org/whl/cpu`
+> does work, because the CPU index tracks the latest release.)
+>
+> **The `cpu` / `cu126` / `cu130` extras do not select a PyTorch variant under
+> pip.** All three declare the same requirements (`torch`, `torchvision`); what
+> distinguishes them is `[tool.uv.sources]`, which routes those packages to the
+> right wheel index. That is project metadata applied by uv when resolving **from
+> source** — it is not part of the published wheel. Select the variant with
+> `--index-url` under pip, `--torch-backend` under `uv pip`, and use the extras
+> only for source installs.
+
+### **torchvision (optional)**
+
+`torchvision` is not a DataEval dependency, and nothing imports it until you reach
+for `TorchvisionTransform` — the escape hatch for running a torchvision v2
+transform across a dataset view. If you want that class, install torchvision
+yourself, from the **same index as your torch build**:
+
+```bash
+pip install torchvision --index-url https://download.pytorch.org/whl/cu130
+```
+
+> **Do not mix indexes.** A `torchvision` from PyPI alongside a torch installed
+> from a wheel index resolves and installs cleanly, then fails on
+> `import torchvision` with
+> `RuntimeError: operator torchvision::nms does not exist`. torchvision's compiled
+> ops are built against one specific torch build, so both packages must come from
+> the same index — which is also why `pip install dataeval[cpu]` is the wrong way
+> to obtain it.
+
+### **Installing with uv**
+
+```bash
+uv pip install dataeval --torch-backend cpu   # or cu126 / cu130 / auto
+```
+
 ### **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`
-channel, the channel is specified in the below example.
+DataEval can be installed from conda-forge:
 
 ```bash
-micromamba create -f environment\environment.yaml -c pytorch
+conda install -c conda-forge dataeval
+```
+
+Alternatively, create an environment from the provided `environment.yml` at the
+repository root. PyTorch is installed into that environment from PyPI via `pip`,
+so this path gives you the CPU/CUDA-bundled PyPI build rather than a specific
+variant.
+
+```bash
+micromamba create -f environment.yml
 ```
 
 ### **Installing from GitHub**
@@ -95,6 +222,11 @@ git clone https://github.com/aria-ml/dataeval.git
 cd dataeval
 ```
 
+> **Contributing rather than just installing?** Use
+> `uvx --with nox-uv nox -s dev` to build a full development environment — tests,
+> linting, type checking and docs tooling included. See
+> [Development Setup](./CONTRIBUTING.md#development-setup) for the options it takes.
+
 #### **Using Poetry**
 
 Install DataEval.
@@ -346,7 +478,7 @@ shape: (3, 5)
 
 A result with many large groups is a signal that your dataset contains
 repeated collection events. Before training, remove all but one sample from
-each group. See the [deduplication how-to guide](./docs/source/notebooks/h2_deduplicate.md)
+each group. See the [deduplication how-to guide](./docs/source/notebooks/h2_deduplicate.py)
 for a complete walkthrough, including how to choose which sample to keep.
 
 ### Where to go next
@@ -354,8 +486,9 @@ for a complete walkthrough, including how to choose which sample to keep.
 Not sure what to evaluate first? Use the [Which tool should I use?](./docs/source/getting-started/which-tool.md)
 guide to find the right evaluator for your situation.
 
-Know which tool to use, then check out the [Functional Overview](./docs/source/reference/FunctionalOverview.md)
-for a quick-reference table of each algorithm's inputs, outputs, and task applicability.
+Know which tool to use, then check out [What data does each tool need?](./docs/source/getting-started/input-requirements.md)
+for a quick-reference table of every algorithm's inputs, and the
+[Functional Overview](./docs/source/reference/FunctionalOverview.md) for task applicability.
 
 Want to just explore the documentation? The [Where to go next](./docs/source/getting-started/where-to-go-next.md)
 page allows you to jump around between the different areas of the documentation with small summaries of what each page covers.

dataeval-1.0.6/PKG-INFO → dataeval-1.1.0/README.md

@@ -1,59 +1,5 @@
-Metadata-Version: 2.4
-Name: dataeval
-Version: 1.0.6
-Summary: DataEval provides a simple interface to characterize image data and its impact on model performance across classification and object-detection tasks
-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>, Christina Doty <christina.doty@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>
-Maintainer-email: ARiA <dataeval@ariacoustics.com>
-License-Expression: MIT
-License-File: LICENSE
-Classifier: Development Status :: 5 - Production/Stable
-Classifier: Intended Audience :: Science/Research
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Programming Language :: Python :: 3.14
-Classifier: Topic :: Scientific/Engineering
-Requires-Python: >=3.10
-Requires-Dist: lightgbm>=4
-Requires-Dist: numba>=0.61.0
-Requires-Dist: numpy>=1.24.2
-Requires-Dist: polars>=1.0.0
-Requires-Dist: psutil>=7.0.0
-Requires-Dist: pydantic>=2.8
-Requires-Dist: scikit-learn>=1.5.0
-Requires-Dist: scipy>=1.10.0
-Requires-Dist: torch>=2.2.0
-Requires-Dist: typing-extensions>=4.12
-Requires-Dist: xxhash>=3.4
-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'
-Provides-Extra: cu128
-Requires-Dist: torch>=2.2.0; extra == 'cu128'
-Requires-Dist: torchvision>=0.17.0; extra == 'cu128'
-Provides-Extra: onnx
-Requires-Dist: onnx; extra == 'onnx'
-Requires-Dist: onnxruntime>=1.14.0; extra == 'onnx'
-Provides-Extra: onnx-gpu
-Requires-Dist: onnx; extra == 'onnx-gpu'
-Requires-Dist: onnxruntime-gpu>=1.14.0; extra == 'onnx-gpu'
-Provides-Extra: opencv
-Requires-Dist: opencv-python-headless>=4.8.0; extra == 'opencv'
-Description-Content-Type: text/markdown
-
 <!-- markdownlint-disable MD041 -->
+
 ![dataeval-logo](docs/source/_static/images/DataEval_ImageText.png)
 
 <!-- :auto badges: -->
@@ -119,6 +65,7 @@ Choose your preferred method of installation below or follow our
 [installation guide](docs/source/getting-started/installation.md).
 
 - [Installing with pip](#installing-with-pip)
+- [Installing with uv](#installing-with-uv)
 - [Installing with conda/mamba](#installing-with-conda)
 - [Installing from GitHub](#installing-from-github)
 
@@ -130,14 +77,76 @@ You can install DataEval directly from pypi.org using the following command.
 pip install dataeval
 ```
 
+By default, PyTorch is installed from PyPI, which bundles CUDA support on Linux
+and is a much larger download than the CPU build. To choose a specific PyTorch
+variant, install `torch` from that variant's wheel index **first**, then install
+DataEval — it accepts the build already present in the environment:
+
+```bash
+# 1. Pick your PyTorch build (cpu / cu126 / cu130)
+pip install torch --index-url https://download.pytorch.org/whl/cu130
+
+# 2. Install DataEval
+pip install dataeval
+```
+
+> **Use `--index-url`, not `--extra-index-url`, to pick a CUDA build.**
+> `--extra-index-url` *adds* an index instead of replacing PyPI, and pip then
+> takes the highest version across both. The CUDA indexes lag the latest PyTorch
+> release, so PyPI usually wins and you silently get the default CUDA-bundled
+> build — the install succeeds with no warning. `--index-url` replaces the index
+> outright, so it is reliable. (For CPU only,
+> `pip install dataeval --extra-index-url https://download.pytorch.org/whl/cpu`
+> does work, because the CPU index tracks the latest release.)
+>
+> **The `cpu` / `cu126` / `cu130` extras do not select a PyTorch variant under
+> pip.** All three declare the same requirements (`torch`, `torchvision`); what
+> distinguishes them is `[tool.uv.sources]`, which routes those packages to the
+> right wheel index. That is project metadata applied by uv when resolving **from
+> source** — it is not part of the published wheel. Select the variant with
+> `--index-url` under pip, `--torch-backend` under `uv pip`, and use the extras
+> only for source installs.
+
+### **torchvision (optional)**
+
+`torchvision` is not a DataEval dependency, and nothing imports it until you reach
+for `TorchvisionTransform` — the escape hatch for running a torchvision v2
+transform across a dataset view. If you want that class, install torchvision
+yourself, from the **same index as your torch build**:
+
+```bash
+pip install torchvision --index-url https://download.pytorch.org/whl/cu130
+```
+
+> **Do not mix indexes.** A `torchvision` from PyPI alongside a torch installed
+> from a wheel index resolves and installs cleanly, then fails on
+> `import torchvision` with
+> `RuntimeError: operator torchvision::nms does not exist`. torchvision's compiled
+> ops are built against one specific torch build, so both packages must come from
+> the same index — which is also why `pip install dataeval[cpu]` is the wrong way
+> to obtain it.
+
+### **Installing with uv**
+
+```bash
+uv pip install dataeval --torch-backend cpu   # or cu126 / cu130 / auto
+```
+
 ### **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`
-channel, the channel is specified in the below example.
+DataEval can be installed from conda-forge:
 
 ```bash
-micromamba create -f environment\environment.yaml -c pytorch
+conda install -c conda-forge dataeval
+```
+
+Alternatively, create an environment from the provided `environment.yml` at the
+repository root. PyTorch is installed into that environment from PyPI via `pip`,
+so this path gives you the CPU/CUDA-bundled PyPI build rather than a specific
+variant.
+
+```bash
+micromamba create -f environment.yml
 ```
 
 ### **Installing from GitHub**
@@ -150,6 +159,11 @@ git clone https://github.com/aria-ml/dataeval.git
 cd dataeval
 ```
 
+> **Contributing rather than just installing?** Use
+> `uvx --with nox-uv nox -s dev` to build a full development environment — tests,
+> linting, type checking and docs tooling included. See
+> [Development Setup](./CONTRIBUTING.md#development-setup) for the options it takes.
+
 #### **Using Poetry**
 
 Install DataEval.
@@ -401,7 +415,7 @@ shape: (3, 5)
 
 A result with many large groups is a signal that your dataset contains
 repeated collection events. Before training, remove all but one sample from
-each group. See the [deduplication how-to guide](./docs/source/notebooks/h2_deduplicate.md)
+each group. See the [deduplication how-to guide](./docs/source/notebooks/h2_deduplicate.py)
 for a complete walkthrough, including how to choose which sample to keep.
 
 ### Where to go next
@@ -409,8 +423,9 @@ for a complete walkthrough, including how to choose which sample to keep.
 Not sure what to evaluate first? Use the [Which tool should I use?](./docs/source/getting-started/which-tool.md)
 guide to find the right evaluator for your situation.
 
-Know which tool to use, then check out the [Functional Overview](./docs/source/reference/FunctionalOverview.md)
-for a quick-reference table of each algorithm's inputs, outputs, and task applicability.
+Know which tool to use, then check out [What data does each tool need?](./docs/source/getting-started/input-requirements.md)
+for a quick-reference table of every algorithm's inputs, and the
+[Functional Overview](./docs/source/reference/FunctionalOverview.md) for task applicability.
 
 Want to just explore the documentation? The [Where to go next](./docs/source/getting-started/where-to-go-next.md)
 page allows you to jump around between the different areas of the documentation with small summaries of what each page covers.