{"id":23312414,"url":"https://github.com/rikeshamin/mlcharring","last_synced_at":"2025-04-07T02:29:35.875Z","repository":{"id":223513244,"uuid":"760534784","full_name":"rikeshamin/MLCharring","owner":"rikeshamin","description":"Instructions on how to deploy machine learning models to predict the charring rate of mass timber for structural calculations","archived":false,"fork":false,"pushed_at":"2024-12-26T03:07:09.000Z","size":36,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-13T07:36:56.375Z","etag":null,"topics":["containerization","fire","fire-engineering","fire-science","hazelab","machine-learning","mlops","python","regression","statistics","structural-engineering","vaqt"],"latest_commit_sha":null,"homepage":"https://doi.org/10.5281/zenodo.14238389","language":"Python","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/rikeshamin.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-02-20T15:44:33.000Z","updated_at":"2024-12-26T03:07:12.000Z","dependencies_parsed_at":"2024-11-28T21:34:44.170Z","dependency_job_id":null,"html_url":"https://github.com/rikeshamin/MLCharring","commit_stats":null,"previous_names":["rikeshamin/mlcharringrate","rikeshamin/mlcharring"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rikeshamin%2FMLCharring","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rikeshamin%2FMLCharring/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rikeshamin%2FMLCharring/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rikeshamin%2FMLCharring/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rikeshamin","download_url":"https://codeload.github.com/rikeshamin/MLCharring/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247581172,"owners_count":20961721,"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":["containerization","fire","fire-engineering","fire-science","hazelab","machine-learning","mlops","python","regression","statistics","structural-engineering","vaqt"],"created_at":"2024-12-20T14:29:15.646Z","updated_at":"2025-04-07T02:29:35.858Z","avatar_url":"https://github.com/rikeshamin.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"![Python](https://img.shields.io/badge/Python-blue?logo=python\u0026logoColor=white)\n![SQL](https://img.shields.io/badge/SQL-blue?logo=postgresql\u0026logoColor=white)\n![Structural Engineering](https://img.shields.io/badge/Structural%20Engineering-brightgreen)\n![Optimization](https://img.shields.io/badge/Bayesian%20Optimization-orange)\n![Machine Learning](https://img.shields.io/badge/Machine%20Learning-yellow?logo=machine-learning\u0026logoColor=white)\n![Statistics](https://img.shields.io/badge/Statistics-lightgrey?logo=chart-bar\u0026logoColor=white)\n![License](https://img.shields.io/badge/license-MIT-green)\n\n# Predicting the Average Charring Rate of Mass Timber Using Data-Driven Methods for Structural Calculations\n\nMLCharring is a collection of data-driven models developed to predict the charring rate of timber in fire scenarios, providing assistance for structural engineering calculations. The dataset, [VAQT](https://zenodo.org/records/14238389) , aggregates timber furnace tests conducted in an ISO 834 fire environment, offering a robust foundation for training advanced statistical and machine learning models. These models are designed to accurately estimate the average charring rate of mass timber, supporting fire-safe and efficient structural design practices in the built environment. \n\n--- \n## Setting up VAQT on your local machine\n\nFollow these steps to set up the VAQT dataset:\n\n1. [Download VAQT](https://zenodo.org/records/14238389) from Zenodo. \n2. Install Microsoft Access or migrate to open database platform (e.g., PostgreSQL, MySQL)\n3. Open the `Timber Charring fe` file. \n4. Navigate to the `External Data` tab and select:\n     - `New Data Source` -\u003e `From Database` -\u003e `Access`.\n5. Choose `Link to data source...` and select the `Timber Charring be` file.\n6. In the dialog box,  press `SELECT ALL` and then click `OK`.\n7. **VAQT is now linked and ready to usee**\n\n---\n## Running models locally\n\n1. Ensure Python is installed and set up a virtual environment. Guidance can be found here:\n   - [Python Installation Guide](https://www.python.org/downloads/)\n   - [Virtual Environments Guide](https://docs.python.org/3/tutorial/venv.html)\n2. Run `pip install -r requirements.txt` to install all dependencies. \n3. Ensure the model `statistical_model.pkl` is in the same directory as `ml_charring_statistical.py`.\n4. Execute the script using:\n   ```bash\n   python ml_charring_statistical.py\n   ```\n6. Provide the input dataset to the model. \n7. The terminal will output the predicted charring rates(s):\n   ```bash\n   Charring Rate: [0.71605273]\n   ``` \n\nIf you encounter any problems, please create an issue directly in this repository or email [myself](rikamin95@gmail.com) or [Prof. Guillermo Rein](g.rein@imperial.ac.uk).\n\n---\n\n### Additional Resources:\n- [Publication DOI](https://doi.org/10.1007/s10694-024-01593-x)\n- [Hazelab - Imperial College London](https://www.imperial.ac.uk/hazelab)\n--- \n### To Do (when i have some more time):\n* Update VAQT compatability to open databases \n* Upload deep learning models (currently on my own server)\n* Implement MLOps for containerization and deployment (Docker and Kubernetes)\n---\n### Citation\n```text\n@article{Amin2024,\n   author = {Amin, Rikesh and Yaxin, Mo and Richter, Franz and Kurzer, Christoph and Werther, Norman and Rein, Guillermo},\n   title = {Predicting the Average Charring Rate of Mass Timber Using Data-Driven Methods for Structural Calculations},\n   journal = {Fire Technology},\n   ISSN = {1572-8099},\n   DOI = {10.1007/s10694-024-01593-x},\n   url = {https://doi.org/10.1007/s10694-024-01593-x},\n   year = {2024},\n   type = {Journal Article}\n}\n```\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frikeshamin%2Fmlcharring","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frikeshamin%2Fmlcharring","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frikeshamin%2Fmlcharring/lists"}