opendp 0.15.0

Python bindings for the OpenDP Library

The OpenDP Library is a modular collection of statistical algorithms that adhere to the definition of differential privacy. It can be used to build applications of privacy-preserving computations, using a number of different models of privacy. OpenDP is implemented in Rust, with bindings for easy use from Python and R.

The architecture of the OpenDP Library is based on a conceptual framework for expressing privacy-aware computations. This framework is described in the paper A Programming Framework for OpenDP.

[!NOTE] This software is part of the OpenDP Commons. As such, the OpenDP Executive Committee commits to:

• Releasing this software under an OSI approved licence, in this case the MIT License.
• Ensuring there are at least two maintainers, in this case Michael Shoemate (Shoeboxam) and Chuck McCallum (mccalluc), who will respond within a week to new issues and PRs.
• Only making changes on main through PRs, and getting approval on these PRs before merging.
• On an annual basis, recruiting one or more volunteers (not active contributors) who will conduct a health-check, focussed not on the details of the algorithms but on the health of this repo as open source software. Their report will be linked here. The next (and first) health-check is scheduled for September 2026.

Status

OpenDP is under development, and we expect to release new versions frequently, incorporating feedback and code contributions from the OpenDP Community. It's a work in progress, but it can already be used to build some applications and to prototype contributions that will expand its functionality. We welcome you to try it and look forward to feedback on the library! However, please be aware of the following limitations:

OpenDP, like all real-world software, has both known and unknown issues. If you intend to use OpenDP for a privacy-critical application, you should evaluate the impact of these issues on your use case.

More details can be found in the Limitations section of the User Guide.

Installation

Install OpenDP for Python with pip (the package installer for Python):

$ pip install opendp

Install OpenDP for R from an R session:

install.packages("opendp", repos = "https://opendp.r-universe.dev")

More information can be found in the Getting Started section of the User Guide.

Documentation

The full documentation for OpenDP is located at https://docs.opendp.org. Here are some helpful entry points:

• User Guide
• Python API Docs
• Contributor Guide

Getting Help

If you're having problems using OpenDP, or want to submit feedback, please reach out! Here are some ways to contact us:

• Report a bug or request a feature on Github.
• Send general queries to [e-mail], or email [e-mail] if it is related to security.
• Join the conversation on Slack, or the mailing list.

Contributing

OpenDP is a community effort, and we welcome your contributions to its development! If you'd like to participate, please contact us! We also have a contribution process section in the Contributor Guide.