https://github.com/facebookresearch/beanmachine

A library that allows for inference on probabilistic models
https://github.com/facebookresearch/beanmachine

Last synced: 3 months ago
JSON representation

A library that allows for inference on probabilistic models

• Host: GitHub
• URL: https://github.com/facebookresearch/beanmachine
• Owner: facebookresearch
• License: mit
• Archived: true
• Created: 2019-08-07T18:06:50.000Z (over 5 years ago)
• Default Branch: main
• Last Pushed: 2023-10-18T18:11:54.000Z (about 1 year ago)
• Last Synced: 2024-07-13T13:23:33.372Z (4 months ago)
• Language: Python
• Homepage: https://beanmachine.org/
• Size: 489 MB
• Stars: 264
• Watchers: 30
• Forks: 48
• Open Issues: 81
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md

Awesome Lists containing this project

README

        
# Bean Machine



   



[![Lint](https://github.com/facebookresearch/beanmachine/actions/workflows/lint.yml/badge.svg)](https://github.com/facebookresearch/beanmachine/actions/workflows/lint.yml)

[![Tests](https://github.com/facebookresearch/beanmachine/actions/workflows/test.yml/badge.svg)](https://github.com/facebookresearch/beanmachine/actions/workflows/test.yml)

[![PyPI](https://img.shields.io/pypi/v/beanmachine)](https://pypi.org/project/beanmachine)

## Overview

Bean Machine is a probabilistic programming language for inference over statistical models written in the Python language using a declarative syntax. Bean Machine is built on top of PyTorch and Bean Machine Graph, a custom C++ backend.

Check out our [tutorials](https://beanmachine.org/docs/overview/tutorials/Coin_flipping/CoinFlipping/) and [Quick Start](https://beanmachine.org/docs/overview/quick_start/) to get started!

## Installation

Bean Machine supports Python 3.7-3.10 and PyTorch 1.12.

### Install the Latest Release with Pip

```bash

pip install beanmachine

```

### Install from Source

To download the latest Bean Machine source code from GitHub:

```bash

git clone https://github.com/facebookresearch/beanmachine.git

cd beanmachine

```

Then, you can choose from any of the following installation options.

#### Package Managers (Conda)

Installing Bean Machine from source requires three external dependencies: [Boost](https://www.boost.org/), [Eigen](https://eigen.tuxfamily.org/index.php?title=Main_Page), and [`range-v3`](https://github.com/ericniebler/range-v3).

We recommend using [conda](https://docs.conda.io/en/latest/) to manage the virtual environment and install the necessary build dependencies.

```bash

conda create -n {env name} python=3.8; conda activate {env name}

conda install -c conda-forge boost-cpp eigen range-v3

```

Once dependencies are installed, install Bean Machine by running Pip:

```

pip install .

```

#### Docker

```bash

docker build -t beanmachine .

docker run -it beanmachine:latest bash

```

#### Validate Installation

If you would like to run the builtin unit tests:

```bash

pip install "beanmachine[test]"

pytest .

```

## License

Bean Machine is MIT licensed, as found in the [LICENSE](LICENSE) file.