The easy way to ship Stan models
Project description
Strata
:mountain: The easy way to ship Stan models
Installation
Strata is a command line tool. To install, run:
pip install strata-cli
This will give you the strata
command.
Getting Started
Package a model
strata bernoulli.stan
This creates a dist
directory with:
bin
- Stan binarieslib
- TBB librarieslicenses
- license files
You can also package multiple models
strata bernoulli.stan regression.stan
Running Models
Run a model directly
dist/bin/bernoulli sample data ...
Or load it into CmdStanPy
from cmdstanpy import CmdStanModel
model = CmdStanModel(exe_file='dist/bin/bernoulli')
CmdStanR (not on CRAN yet)
library(cmdstanr)
model <- cmdstan_model(exe_file="dist/bin/bernoulli")
Or CmdStan.rb
require "cmdstan"
model = CmdStan::Model.new(exe_file: "dist/bin/bernoulli")
Portability
For Mac, models run on macOS 10.14+ by default. You can set MACOSX_DEPLOYMENT_TARGET
to override.
For Linux, compile on the oldest platform you support.
Cross-Compiling
Cross-compile for a different architecture (on the same OS)
strata --cross-compile ...
On Ubuntu, this requires:
sudo apt update
sudo apt install gcc-aarch64-linux-gnu g++-aarch64-linux-gnu
Reference
Specify output directory
strata -o dist ...
Show build output
strata --debug ...
Create a static build (Mac only, experimental)
strata --static ...
History
View the changelog
Contributing
Everyone is encouraged to help improve this project. Here are a few ways you can help:
- Report bugs
- Fix bugs and submit pull requests
- Write, clarify, or fix documentation
- Suggest or add new features
To get started with development:
git clone https://github.com/ankane/strata.git
cd strata
pip install -e .
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distribution
Hashes for strata_cli-0.1.0-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | ea23a53265dc2d39a651d361b95d3586d1e1f4b5e1ba00dec972c421eceabc5d |
|
MD5 | 7942435072c3c80c1e6c807b1e3ee972 |
|
BLAKE2b-256 | dfb05f1edde6a9a3023706039e32bf5abe0d2b642ac7c51a6e5a12c234c5800f |