{"id":16506510,"url":"https://github.com/theogf/bayesiansvm","last_synced_at":"2025-03-07T09:30:56.981Z","repository":{"id":118798853,"uuid":"88799045","full_name":"theogf/BayesianSVM","owner":"theogf","description":"Source code of the Bayesian SVM described in the paper by Wenzel et al. \"Bayesian Nonlinear Support Vector Machines for Big Data\"","archived":false,"fork":false,"pushed_at":"2020-02-08T14:36:31.000Z","size":2184,"stargazers_count":17,"open_issues_count":0,"forks_count":8,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-02-17T13:22:50.348Z","etag":null,"topics":["bayesian-inference","bsvm","julia","svm"],"latest_commit_sha":null,"homepage":"","language":"Julia","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/theogf.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2017-04-19T23:11:49.000Z","updated_at":"2024-08-05T14:13:33.000Z","dependencies_parsed_at":null,"dependency_job_id":"837cb369-39fb-48d5-8e2e-b81827191107","html_url":"https://github.com/theogf/BayesianSVM","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theogf%2FBayesianSVM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theogf%2FBayesianSVM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theogf%2FBayesianSVM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theogf%2FBayesianSVM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/theogf","download_url":"https://codeload.github.com/theogf/BayesianSVM/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242097414,"owners_count":20071252,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bayesian-inference","bsvm","julia","svm"],"created_at":"2024-10-11T15:20:10.193Z","updated_at":"2025-03-07T09:30:56.185Z","avatar_url":"https://github.com/theogf.png","language":"Julia","funding_links":[],"categories":[],"sub_categories":[],"readme":"# !!!DISCLAIMER!!! #\n##  A better and more recent Julia implementation exists now at : [AugmentedGaussianProcesses.jl](https://github.com/theogf/AugmentedGaussianProcesses.jl) , this repository only contains an older version of the algorithm as well the experiments presented in our paper, it is relying on an outdated version of Julia\n\n## README ##\n\n\n### Objective ###\n\n* This repository contains the updated source code for the ***Bayesian Nonlinear Support Vector Machine (BSVM)*** both in its **stochastic (and with inducing points)** and its **batch version**\n* It relates to the paper published at the conference track of ECML 17' __\"Bayesian Nonlinear Support Vector Machines for Big Data\"__ by Florian Wenzel, Théo Galy-Fajou, Matthäus Deutsch and Marius Kloft. Paper is available at [https://arxiv.org/abs/1707.05532][arxiv]\n\n### How do I install the package? ###\n\n* First clone this repository (`git clone https://github.com/theogf/BayesianSVM.git`)\n* If you simply want to try out the package you need to install the **Julia** dependencies :\n    - [Distributions][dist]\n    - [PyPlot][pyplot]\n    - [StatsBase][statsbase]\n    - [GaussianMixtures][gaussm]\n    - [Clustering][clustering]\n    - [ScikitLearn][scikitjl]\n    \n    *Note: to install new packages use the Pkg.add(\"ModuleName\") function in Julia*\n* If you want to try the competitors as well you will need to install these **Julia** and **Python** dependencies (as well as Python ofc): \n    * (Julia)[PyCall][pycall]\n    * (Python)[ScikitLearn][scikit]\n    * (Python)[Tensorflow][tflow]\n    * (Python)[GPflow][gpflow]\n    \n    *Note: to use Tensorflow and GPflow, they must me included in the search path of PyCall, to do this use : `unshift!(PyVector(pyimport(\"sys\")[\"path\"]), \"path_to_add\")` and call `Pkg.build(\"PyCall\")`, also note that they are much more complicate to install*\n* Both tests and source files are written in Julia (v0.5), one first needs to julia to run those, however a Python or Matlab user should be able to read easily through the code as the syntax is quite similar\n* Some light datasets are included (especially the **Rätsch Benchmark dataset**), the SUSY dataset can be found on UCI\n### How to run tests? ###\n\n* Go to the \"test\" folder, open \"run_test.jl\", chose the dataset and change the parameters (more is explained in the file) and simply run the file. (*for example change the type of BSVM (linear/nonlinear, sparse, use of stochasticity etc*)\n* If you want to also use the competitors, open \"paper_experiments.jl\", chose the dataset, chose the methods you want to test and adapt the parameters (more details in the file).\n* For more custom usage of the BSVM method, look at the source code of src/BSVM.jl, where all the options are explained. More documentation will be there soon.\n\n### Who to contact ###\n\n**For any queries please contact theo.galyfajou at gmail.com**\n\n   [arxiv]: \u003chttps://arxiv.org/abs/1707.05532\u003e\n   [dist]: \u003chttps://github.com/JuliaStats/Distributions.jl\u003e\n   [pyplot]: \u003chttps://github.com/JuliaPy/PyPlot.jl\u003e\n   [pycall]:\u003chttps://github.com/JuliaPy/PyCall.jl\u003e\n   [statsbase]:\u003chttps://github.com/JuliaStats/StatsBase.jl\u003e\n   [gaussm]:\u003chttps://github.com/davidavdav/GaussianMixtures.jl\u003e\n   [clustering]:\u003chttps://github.com/JuliaStats/Clustering.jl\u003e\n   [scikitjl]:\u003chttps://github.com/cstjean/ScikitLearn.jl\u003e\n   [scikit]:\u003chttp://scikit-learn.org/stable/\u003e\n   [tflow]:\u003chttps://www.tensorflow.org/\u003e\n   [gpflow]:\u003chttps://github.com/GPflow/GPflow\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftheogf%2Fbayesiansvm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftheogf%2Fbayesiansvm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftheogf%2Fbayesiansvm/lists"}