{"id":20603694,"url":"https://github.com/patrickm663/extremevaluetheory","last_synced_at":"2025-10-10T20:41:55.065Z","repository":{"id":187413499,"uuid":"676864323","full_name":"patrickm663/extremevaluetheory","owner":"patrickm663","description":"A demonstration of performing Extreme Value Theory (EVT) using the Block Maxima method with Bayesian sampling in Julia.","archived":false,"fork":false,"pushed_at":"2023-08-18T13:42:15.000Z","size":5242,"stargazers_count":1,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-10T20:41:54.664Z","etag":null,"topics":["bayesian-inference","extreme-value-statistics","julia","probabilistic-programming"],"latest_commit_sha":null,"homepage":"https://patrickm663.github.io/extremevaluetheory/","language":"Julia","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/patrickm663.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-08-10T07:28:45.000Z","updated_at":"2023-08-19T12:54:44.000Z","dependencies_parsed_at":null,"dependency_job_id":"7f5816e4-a8c4-4223-940a-9e6d8c51cdc0","html_url":"https://github.com/patrickm663/extremevaluetheory","commit_stats":null,"previous_names":["patrickm663/extremevaluetheory"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/patrickm663/extremevaluetheory","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/patrickm663%2Fextremevaluetheory","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/patrickm663%2Fextremevaluetheory/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/patrickm663%2Fextremevaluetheory/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/patrickm663%2Fextremevaluetheory/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/patrickm663","download_url":"https://codeload.github.com/patrickm663/extremevaluetheory/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/patrickm663%2Fextremevaluetheory/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279005276,"owners_count":26083864,"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","status":"online","status_checked_at":"2025-10-10T02:00:06.843Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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","extreme-value-statistics","julia","probabilistic-programming"],"created_at":"2024-11-16T09:18:10.768Z","updated_at":"2025-10-10T20:41:55.051Z","avatar_url":"https://github.com/patrickm663.png","language":"Julia","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Extreme Value Theory\n**_This investigation is currently a WIP_**\n\nA demonstration Extreme Value Theory (EVT) using the Block Maxima method with Bayesian sampling in Julia.\n\n## Approach\nThis repo makes use of the `battery` water levels dataset found in the `pyextremes` package. It takes the annual maximum water elevation level and fits a Generalised Extreme Value (GEV) to the observations.\n\nBayesian methods allow us to produce uncertainty quantifications for our results. In addition, we are also able to provide informative priors to encode expert knowledge into the system. In our example, our main source of prior knowledge is that the distribution is very likely Gumbel ($\\xi$ is zero), which allows our model to converge on a solution faster.\n\nThe end-to-end investigation is available in the Pluto notebook provided, and an HTLM copy is available at https://patrickm663.github.io/extremevaluetheory/.\n\n## Motivation\nThis repo was largely to showcase how `Turing.jl` can be used as a very flexible modelling library, given the support contraints when $\\xi$ fluxuates around zero.\n\n## TODO\n- [ ] Add example of Generalised Pareto Distribution\n- [ ] Demonstrate how Bayesian neural networks can help model rare events by utilising block maxima / peaks-over-threshold to model the tails.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpatrickm663%2Fextremevaluetheory","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpatrickm663%2Fextremevaluetheory","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpatrickm663%2Fextremevaluetheory/lists"}