Displaying 1 to 20 from 52 results

PyMC3 - Probabilistic Programming in Python: Bayesian Modeling and Probabilistic Machine Learning with Theano

  •    Python

PyMC3 is a Python package for Bayesian statistical modeling and Probabilistic Machine Learning which focuses on advanced Markov chain Monte Carlo and variational fitting algorithms. Its flexibility and extensibility make it applicable to a large suite of problems.Note: Running pip install pymc will install PyMC 2.3, not PyMC3, from PyPI.

stan - Stan development repository (home page is linked below)

  •    R

There are interfaces available in R, Python, MATLAB, Julia, Stata, Mathematica, and for the command line. There are separate repositories in the stan-dev GitHub organization for the interfaces, higher-level libraries and lower-level libraries.

BDA_py_demos - Bayesian Data Analysis demos for Python

  •    Jupyter

to interactively run the IPython Notebooks in the browser. This repository contains some Python demos for the book Bayesian Data Analysis, 3rd ed by Gelman, Carlin, Stern, Dunson, Vehtari, and Rubin (BDA3).

rstan - RStan, the R interface to Stan

  •    R

RStan is the R interface to Stan. RStan's source code repository is hosted here on GitHub. Stan's source repository is defined as a submodule. See how to work with stan submodule in rstan repo.




infer - Infer.NET is a framework for running Bayesian inference in graphical models

  •    CSharp

Infer.NET is a framework for running Bayesian inference in graphical models. It can also be used for probabilistic programming. One can use Infer.NET to solve many different kinds of machine learning problems - from standard problems like classification, recommendation or clustering through to customised solutions to domain-specific problems.

Pyro - Deep universal probabilistic programming with Python and PyTorch

  •    Python

Pyro is a universal probabilistic programming language (PPL) written in Python and supported by PyTorch on the backend. Pyro enables flexible and expressive deep probabilistic modeling, unifying the best of modern deep learning and Bayesian modeling.

DSGE

  •    Julia

This Julia-language implementation mirrors the MATLAB code included in the Liberty Street Economics blog post The FRBNY DSGE Model Forecast. For the latest documentation on the code, click on the docs|latest button above. Documentation for the most recent model version is available here.

brms - brms R package for Bayesian generalized multivariate non-linear multilevel models using Stan

  •    R

The brms package provides an interface to fit Bayesian generalized (non-)linear multivariate multilevel models using Stan, which is a C++ package for performing full Bayesian inference (see http://mc-stan.org/). The formula syntax is very similar to that of the package lme4 to provide a familiar and simple interface for performing regression analyses. A wide range of distributions and link functions are supported, allowing users to fit -- among others -- linear, robust linear, count data, survival, response times, ordinal, zero-inflated, hurdle, and even self-defined mixture models all in a multilevel context. Further modeling options include non-linear and smooth terms, auto-correlation structures, censored data, missing value imputation, and quite a few more. In addition, all parameters of the response distribution can be predicted in order to perform distributional regression. Multivariate models (i.e. models with multiple response variables) can be fitted, as well. Prior specifications are flexible and explicitly encourage users to apply prior distributions that actually reflect their beliefs. Model fit can easily be assessed and compared with posterior predictive checks, leave-one-out cross-validation, and Bayes factors. As a simple example, we use poisson regression to model the seizure counts in epileptic patients to investigate whether the treatment (represented by variable Trt) can reduce the seizure counts and whether the effect of the treatment varies with the baseline number of seizures a person had before treatment (variable log_Base4_c). As we have multiple observations per person, a group-level intercept is incorporated to account for the resulting dependency in the data.


Turing.jl - The Turing language for probabilistic programming

  •    Julia

News: Turing.jl is now Julia 1.0 compatible now! Be aware that some things still might fail. Turing was originally created and is now managed by Hong Ge. Current and past Turing team members include Hong Ge, Adam Scibior, Matej Balog, Zoubin Ghahramani, Kai Xu, Emma Smith, Emile Mathieu, Martin Trapp. You can see the full list of on Github: https://github.com/TuringLang/Turing.jl/graphs/contributors.

gelato - Bayesian dessert for Lasagne

  •    Python

Recent results in Bayesian statistics for constructing robust neural networks have proved that it is one of the best ways to deal with uncertainty, overfitting but still having good performance. Gelato will help to use bayes for neural networks. Library heavily relies on Theano, Lasagne and PyMC3.I use generic approach for decorating all Lasagne at once. Thus, for using Gelato you need to replace import statements for layers only. For constructing a network you need to be the in pm.Model context environment.

beat - Bayesian Earthquake Analysis Tool

  •    Python

This repository is still beta version and under development! There might be future changes in the API that cause previous versions to break.An alternative: The geodetic data may be saved using the package "pickle" as a file "geodetic_data.pkl" containing a list of "GeodeticTarget", especially "CompoundGPS" or "DiffIFG" objects. Please see the heart.py module for specifics.

revrand - A library of scalable Bayesian generalised linear models with fancy features

  •    Python

Note: we are not actively developing this library anymore, but we are still maintaining it. We recommend instead looking at Aboleth, which has similar functionality and is implemented on top of TensorFlow. revrand is a python (2 and 3) supervised machine learning library that contains implementations of various Bayesian linear and generalized linear models (i.e. Bayesian linear regression and Bayesian generalized linear regression).

libtext_bayes - Just another Naive Bayes text classifier library for C++

  •    C++

This is a example how to use Naive Bayes to classify SPAM messages, you can use it for other purposes... Optimizing with inline ASM (I think do it by using SiMD)...

DNest4 - Diffusive Nested Sampling

  •    C++

DNest4 is a C++11 implementation of Diffusive Nested Sampling, a Markov Chain Monte Carlo (MCMC) algorithm for Bayesian Inference and Statistical Mechanics. There is a manuscript describing DNest4 installation and usage in the paper/ directory of this repository. You can compile it with pdflatex. Alternatively, you can get the preprint here.

AutoGP - Code for AutoGP

  •    Python

An implementation of the model described in AutoGP: Exploring the Capabilities and Limitations of Gaussian Process Models. The code was tested on Python 2.7 and TensorFlow 0.12.

pymc3_vs_pystan - Personal project to compare hierarchical linear regression in PyMC3 and PyStan, as presented at http://pydata

  •    Jupyter

This set of Notebooks and scripts comprise the pymc3_vs_pystan personal project by Jonathan Sedar of Applied AI Ltd, written primarily for presentation at the PyData London 2016 Conference. The project demonstrates hierarchical linear regression using two Bayesian inference frameworks: PyMC3 and PyStan. The project borrows heavily from code written for Applied AI Ltd and is supplied here for educational purposes only. No copyright or license is extended to users.

DynamicHMC.jl - Bare-bones implementation of robust dynamic Hamiltonian Monte Carlo methods.

  •    Julia

Bare-bones implementation of robust dynamic Hamiltonian Monte Carlo methods. This package implements a modern version of the “No-U-turn sampler” in the Julia language, mostly as described in Betancourt (2017), with some tweaks.

geobipy

  •    Python

This package uses a Bayesian formulation and Markov chain Monte Carlo sampling methods to derive posterior distributions of subsurface and measured data properties. The current implementation is applied to time and frequency domain electro-magnetic data. Application outside of these data types is well within scope. Currently there are two types of data that we have implemented; frequency domain electromagnetic data, and time domain electromagnetic data. The package comes with a frequency domain forward modeller, but it does not come with a time domain forward modeller. See the section Installing the time domain forward modeller for more information.

vae_cf - Variational autoencoders for collaborative filtering

  •    Jupyter

This notebook accompanies the paper "Variational autoencoders for collaborative filtering" by Dawen Liang, Rahul G. Krishnan, Matthew D. Hoffman, and Tony Jebara, in The Web Conference (aka WWW) 2018. In this notebook, we show a complete self-contained example of training a variational autoencoder (as well as a denoising autoencoder) with multinomial likelihood (described in the paper) on the public Movielens-20M dataset, including both data preprocessing and model training.