{"id":47444119,"url":"https://github.com/aicenter/GenerativeAD.jl","last_synced_at":"2026-04-06T13:01:01.246Z","repository":{"id":38412930,"uuid":"290753788","full_name":"aicenter/GenerativeAD.jl","owner":"aicenter","description":"Generative models for anomaly detection","archived":false,"fork":false,"pushed_at":"2022-12-16T09:24:00.000Z","size":1459,"stargazers_count":4,"open_issues_count":9,"forks_count":2,"subscribers_count":3,"default_branch":"master","last_synced_at":"2026-02-06T22:31:29.186Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Julia","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aicenter.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}},"created_at":"2020-08-27T11:09:23.000Z","updated_at":"2024-04-17T19:03:21.000Z","dependencies_parsed_at":"2022-08-09T03:30:43.791Z","dependency_job_id":null,"html_url":"https://github.com/aicenter/GenerativeAD.jl","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/aicenter/GenerativeAD.jl","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aicenter%2FGenerativeAD.jl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aicenter%2FGenerativeAD.jl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aicenter%2FGenerativeAD.jl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aicenter%2FGenerativeAD.jl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aicenter","download_url":"https://codeload.github.com/aicenter/GenerativeAD.jl/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aicenter%2FGenerativeAD.jl/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31473271,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-06T08:36:52.050Z","status":"ssl_error","status_checked_at":"2026-04-06T08:36:51.267Z","response_time":112,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":[],"created_at":"2026-03-23T06:00:59.902Z","updated_at":"2026-04-06T13:01:01.238Z","avatar_url":"https://github.com/aicenter.png","language":"Julia","funding_links":[],"categories":["Machine Learning for Security"],"sub_categories":["Anomaly and Outlier Detection"],"readme":"# GenerativeAD.jl\nGenerative models for anomaly detection. This Julia package contains code for the paper \"Comparison of Anomaly Detectors: Context Matters\" [arXiv preprint](https://arxiv.org/abs/2012.06260).\n\n## Installation\n1. Clone this repo somewhere.\n2. Run Julia in the cloned dir.\n```bash\ncd path/to/repo/GenerativeAD.jl\njulia --project\n```\n3. Install all the packages using `]instantiate` and compile the package.\n```julia\n(@julia) pkg\u003e instantiate\n(@julia) using GenerativeAD\n```\n\nSome of the bash scripts are calling `julia` without `--project` flag and uses `@quickactivate` macro to activate the environment, however this fails, unless `DrWatson` is installed in the base julia environment. In order to avoid these problems install `DrWatson` in your base environment.\n```bash\ncd ~\njulia -e 'using Pkg; Pkg.add(\"DrWatson\");'\n```\n\n### Python instalation\nSome models (PIDforest, scikit-learn, PyOD) are available only through PyCall with appropriate environment active. With upcoming bayesian optimisation from `scikit-optimize` every model will require an active environment, which can be setup in following way using python's `venv` module. (Most of the scripts have hardcoded path to this environment, though this can be easily changed).\n```bash\ncd ~\npython -m venv sklearn-env\n\nsource ${HOME}/sklearn-env/bin/activate\nexport PYTHON=\"${HOME}/sklearn-env/bin/python\"\n```\nThen install requirements inside this repository\n```bash\ncd path/to/repo/GenerativeAD.jl\n\npip install -r requirements.txt\npip install git+https://github.com/janfrancu/pidforest.git # not registerd anywhere\n\njulia --project -e 'using Pkg; Pkg.build(\"PyCall\");' # rebuilds PyCall.jl to point to the current environment\n```\n\n## Running experiments on the RCI cluster\n\n0. First, load Julia and Python modules.\n```bash\nml Julia\nml Python\n```\n1. Install the package somewhere on the RCI cluster.\n2. Then the experiments can be run via `slurm`. This will run 20 experiments with the basic VAE model, each with 5 crossvalidation repetitions on all datasets in the text file with 10 parallel processes for each dataset. All data will be saved in `GenerativeAD.jl/data/experiments/tabular`\n```bash\ncd GenerativeAD.jl/scripts/experiments_tabular\n./run_parallel.sh vae 20 5 10 datasets_tabular.txt\n```\n\n## Data:\n\nOnly UCI datasets are available upon installation via the `UCI` package. Remaining tabular and image datasets are downloaded upon first request (e.g. via the `GenerativeAD.Datasets.load_data(dataset)` function). First download requires user input to accept download terms for individual datasets. If you want to avoid this, do\n```bash\nexport DATADEPS_ALWAYS_ACCEPT=true\n```\nbefore running Julia.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faicenter%2FGenerativeAD.jl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faicenter%2FGenerativeAD.jl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faicenter%2FGenerativeAD.jl/lists"}