{"id":27595695,"url":"https://github.com/tymill/synthpred","last_synced_at":"2025-04-22T12:16:52.112Z","repository":{"id":284547901,"uuid":"955290469","full_name":"TyMill/SynthPred","owner":"TyMill","description":"A Julia package for synthetic data analysis, advanced imputation (ARIMA, RNN), AutoML, and ensemble modeling.","archived":false,"fork":false,"pushed_at":"2025-04-16T11:40:12.000Z","size":315,"stargazers_count":2,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-22T12:16:47.469Z","etag":null,"topics":["arima","automl","ensemble","flux","imputation","julia","machine-learning","synthetic-data","time-series"],"latest_commit_sha":null,"homepage":"","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/TyMill.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.bib","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-03-26T12:13:52.000Z","updated_at":"2025-04-17T18:49:15.000Z","dependencies_parsed_at":null,"dependency_job_id":"7974c919-3ec7-4ad5-9c6c-96042cfc9a74","html_url":"https://github.com/TyMill/SynthPred","commit_stats":null,"previous_names":["tymill/synthpred"],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TyMill%2FSynthPred","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TyMill%2FSynthPred/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TyMill%2FSynthPred/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TyMill%2FSynthPred/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TyMill","download_url":"https://codeload.github.com/TyMill/SynthPred/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250237843,"owners_count":21397403,"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":["arima","automl","ensemble","flux","imputation","julia","machine-learning","synthetic-data","time-series"],"created_at":"2025-04-22T12:16:51.478Z","updated_at":"2025-04-22T12:16:52.098Z","avatar_url":"https://github.com/TyMill.png","language":"Julia","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SynthPred.jl\n[![Docs](https://img.shields.io/badge/docs-dev-blue.svg)](https://tymill.github.io/SynthPred/)\n\n[![DOI](https://zenodo.org/badge/955290469.svg)](https://doi.org/10.5281/zenodo.15090892)\n\n![GitHub all releases](https://img.shields.io/github/downloads/TyMill/SynthPred/total?label=📦%20Downloads\u0026style=plastic)\n\n\n**SynthPred.jl** is a Julia package for synthetic data analysis, advanced imputation (ARIMA, RNN), AutoML, and ensemble modeling.\n\n---\n\n## 🚀 Features\n\n- 🔍 Descriptive statistics and missing data reporting\n- 🧼 Simple and advanced imputation:\n  - Mean, median, mode\n  - Forward/backward fill\n  - Gaussian distribution sampling\n  - Time series-based: ARIMA\n  - Sequence learning-based: RNN (Flux.jl)\n- 🤖 AutoML for classification (MLJ.jl-based)\n- ⚖️ Blending top-performing models via ensembling\n- 📊 Predictions on new data\n- 📑 JSON/CSV imputation reports\n\n---\n\n## 📦 Installation\n\n```julia\nusing Pkg\nPkg.add(url=\"https://github.com/TyMill/SynthPred.jl\")\n```\n\n---\n\n## 🧪 Quick Example\n\n```julia\nusing SynthPred\nusing CSV, DataFrames\n\n# Load training data\ndf = CSV.read(\"data/example.csv\", DataFrame)\n\n# Explore data\nSynthPred.Exploration.describe_data(df)\n\n# Impute missing values (e.g. RNN strategy)\ndf_clean, report = SynthPred.Imputer.impute_advanced(df, \"rnn\", threshold=0.1)\nSynthPred.Imputer.save_imputation_report(report, \"reports/imputation_report.json\")\n\n# Run AutoML pipeline\ntop_models, scores = SynthPred.AutoML.run_automl(df_clean, :target)\nX = select(df_clean, Not(:target))\ny = df_clean[:, :target]\nensemble = SynthPred.AutoML.blend_top_models(top_models, X, y)\n\n# Predict on new data\nXnew = CSV.read(\"data/new_data.csv\", DataFrame)\npreds = SynthPred.AutoML.predict_ensemble(ensemble, Xnew)\nprintln(preds)\n```\n\n---\n\n## 📚 Documentation\n\nFull documentation is available at: [https://your-username.github.io/SynthPred.jl](https://tymill.github.io/SynthPred.jl)\n\n---\n\n## 🧪 Project Structure\n\n```\nSynthPred/\n├── Project.toml\n├── src/\n│   ├── SynthPred.jl\n│   ├── Exploration.jl\n│   ├── Imputer.jl\n│   └── AutoML.jl\n├── data/\n│   ├── example.csv\n│   └── new_data.csv\n├── reports/\n│   └── imputation_report.json\n├── docs/\n│   └── src/index.md\n├── test/\n│   └── runtests.jl\n└── main.jl\n```\n\n---\n\n## 📌 Roadmap\n\n- [x] Core modules: Exploration, Imputer, AutoML\n- [x] ARIMA and RNN-based imputations\n- [x] AutoML + model blending with MLJ.jl\n- [x] Imputation reports (CSV/JSON)\n- [x] Documentation (Documenter.jl + GitHub Pages)\n- [ ] Exporting trained models (`JLD2`, `BSON`)\n- [ ] Web GUI with Pluto.jl or Dash.jl\n- [ ] Integration with JuliaHub and Zenodo DOI\n\n---\n\n## 🤝 Contributing\n\nPull requests are welcome! For major changes, please open an issue first to discuss your proposal.\n\n---\n\n## 📜 License\n\nMIT License © 2025 Tymoteusz Miller\n\n---\n\n## 📬 Contact\n\n📧 me@tymoteuszmiller.dev\n\n\n---\n\nBuilt with ❤️ in Julia for real-world ML and scientific discovery.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftymill%2Fsynthpred","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftymill%2Fsynthpred","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftymill%2Fsynthpred/lists"}