Metadata-Version: 2.1
Name: daml
Version: 0.38.2
Summary: DAML provides a simple interface to characterize image data and its impact on model performance across classification and object-detection tasks
Home-page: https://daml.ai/
License: MIT
Author: Andrew Weng
Author-email: andrew.weng@ariacoustics.com
Maintainer: ARiA
Maintainer-email: daml@ariacoustics.com
Requires-Python: >=3.8.1,<3.12
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 :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.8
Classifier: Topic :: Scientific/Engineering
Requires-Dist: matplotlib (<3.8) ; python_full_version >= "3.8.1" and python_full_version < "3.9.0"
Requires-Dist: matplotlib ; python_version >= "3.9" and python_version < "3.12"
Requires-Dist: numpy (>=1.24.2)
Requires-Dist: nvidia-cudnn-cu11 (==8.6.0.163)
Requires-Dist: scikit-learn (>=1.2.1)
Requires-Dist: scipy (>=1.10)
Requires-Dist: tensorflow (>=2.13.1,<2.14.0) ; python_full_version >= "3.8.1" and python_full_version < "3.9.0"
Requires-Dist: tensorflow (>=2.14.1,<2.15.0) ; python_version >= "3.9" and python_version < "3.12"
Requires-Dist: tensorflow-io-gcs-filesystem (>=0.34.0,<0.35.0) ; python_full_version >= "3.8.1" and python_full_version < "3.9.0"
Requires-Dist: tensorflow-io-gcs-filesystem (>=0.35.0,<0.36.0) ; python_version >= "3.9" and python_version < "3.12"
Requires-Dist: tensorflow_probability (>=0.21.0,<0.22.0) ; python_full_version >= "3.8.1" and python_full_version < "3.9.0"
Requires-Dist: tensorflow_probability (>=0.22.1,<0.23.0) ; python_version >= "3.9" and python_version < "3.12"
Requires-Dist: torch (>=2.1.0)
Requires-Dist: torchmetrics (>=1.0.0)
Requires-Dist: torchvision (>=0.16.0)
Project-URL: Documentation, https://daml.readthedocs.io/
Project-URL: Repository, https://github.com/aria-ml/daml/
Description-Content-Type: text/markdown

# Data-Analysis Metrics Library (DAML)

## About DAML

The Data-Analysis Metrics Library, or DAML, focuses on characterizing image data and its impact on model performance across classification and object-detection tasks.

**Model-agnostic metrics that bound real-world performance**
- relevance/completeness/coverage
- metafeatures (data complexity)

**Model-specific metrics that guide model selection and training**
- dataset sufficiency
- data/model complexity mismatch

**Metrics for post-deployment monitoring of data with bounds on model performance to guide retraining**
- dataset-shift metrics
- model performance bounds under covariate shift
- guidance on sampling to assess model error and model retraining

## Getting Started

### Installing DAML

To install the package from the GitLab Pypi repository, run the following command in an environment with Python 3.8-3.11 installed:

`pip install daml`

### Additional Tutorials
For more ideas on getting started using DAML in your workflow, additional information and tutorials are in our Sphinx documentation hosted on [Read the Docs](https://daml.readthedocs.io/).

## Contributing
For steps on how to get started on contributing to the project, you can follow the steps in [CONTRIBUTING.md](CONTRIBUTING.md).

## Attribution
This project uses code from the [Alibi-Detect](https://github.com/SeldonIO/alibi-detect) python library developed by SeldonIO.  Additional documentation from the developers are also available [here](https://docs.seldon.io/projects/alibi-detect/en/stable/).

## POCs
- **POC**: Scott Swan @scott.swan
- **DPOC**: Andrew Weng @aweng

