{"id":22141172,"url":"https://github.com/marta-barea/visnir-waxtype-classification-ml","last_synced_at":"2026-02-13T15:38:30.440Z","repository":{"id":78391592,"uuid":"484359084","full_name":"Marta-Barea/visnir-waxtype-classification-ml","owner":"Marta-Barea","description":"Spectroscopic data processing approaches for petroleum wax discrimination","archived":false,"fork":false,"pushed_at":"2024-11-20T17:37:56.000Z","size":2016,"stargazers_count":2,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-11-20T18:27:36.904Z","etag":null,"topics":["cheminformatics","chemistry","chemoinformatics","machine-learning","petroleum","r","vis-nir-spectroscopy"],"latest_commit_sha":null,"homepage":"","language":"R","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Marta-Barea.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":"2022-04-22T08:40:08.000Z","updated_at":"2024-11-20T17:38:00.000Z","dependencies_parsed_at":"2024-11-06T03:34:40.539Z","dependency_job_id":"6a513961-9ef4-4e9c-ad8d-40e1fe947027","html_url":"https://github.com/Marta-Barea/visnir-waxtype-classification-ml","commit_stats":null,"previous_names":["marta-barea/visnir-waxtype-classification-ml"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Marta-Barea%2Fvisnir-waxtype-classification-ml","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Marta-Barea%2Fvisnir-waxtype-classification-ml/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Marta-Barea%2Fvisnir-waxtype-classification-ml/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Marta-Barea%2Fvisnir-waxtype-classification-ml/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Marta-Barea","download_url":"https://codeload.github.com/Marta-Barea/visnir-waxtype-classification-ml/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":227629031,"owners_count":17796054,"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":["cheminformatics","chemistry","chemoinformatics","machine-learning","petroleum","r","vis-nir-spectroscopy"],"created_at":"2024-12-01T21:10:57.293Z","updated_at":"2026-02-13T15:38:25.406Z","avatar_url":"https://github.com/Marta-Barea.png","language":"R","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Rapid Classification of Petroleum Waxes: A Vis-NIR Spectroscopy and Machine Learning Approach\n\n## Description\n\nThis repository contains the source code for all data processing and the application of machine learning algorithms used in the article \"Rapid Classification of Petroleum Waxes: A Vis-NIR Spectroscopy and Machine Learning Approach\".\n\n---\n\n## 📂 Repository Structure\n\n- `spectra/`: Folder containing the spectra data.\n- `supervised algorithms/`: Source code for all the supervised machine learning models and experiments.\n- `unsupervised algorithms/`: Source code related to unsupervised learning techniques and clustering.\n- `App/`: A Shiny application to demonstrate and visualize the findings.\n\n## 🛠️ **System Requirements**\n\n### Software\n- **R version 4.2.0** \n- RStudio (optional but recommended)\n\n### Packages\n\n- **prospectr (version 0.2.3)**: Used for calculating the first derivative for each sample spectrum with the `savitzkyGolay` function.\n- **stats (version 4.1.2)**: Utilized for HCA with the `hclust` function, PCA with the `prcomp` function, and one-way ANOVA with the `aov` function.\n- **cluster (version 2.1.2)**: Linkage method selection for the HCA established using the `agnes` function.\n- **factoextra (version 1.0.7)**: Used for visualizing HCA results with the `fviz_dend` function and for extracting and visualizing the PCA result with the `fviz_eig` function.\n- **ggplot2 (version 3.3.5)**: Employed for plotting the scores and loadings of the PCA with the `ggplot` function and generating the spectralprint radar chart.\n- **caret (version 6.0-90)**: Utilized for developing the SVM and RF models.\n- **graphics (version 4.1.2)**: The `filled.contour` function was used to generate the contour plot for the SVM model.\n- **ggiraphExtra (version 0.3.0)**: Assisted in generating the spectralprint radar chart.\n- **shiny (version 1.7.1)**: Utilized for developing the web application.\n\n## ⚙️ How to Use This Repository\n\n### Clone the Repository\n\n```bash\ngit clone https://github.com/Marta-Barea/visnir-waxtype-classification-ml\ncd visnir-waxtype-classification-ml\n```\n\n### Running the Shiny Application\n1. Place `app.R`, `svm.rds`, `svr.rds`and `test_data.xlsx` in the same folder.\n2. In your R console, run: \n   \n  ```R \n   shiny::runApp(\"app.R\")\n```\n\n3. Use the web interface to:\n- 📁 **Upload** `.csv` or `.xlsx` data files.\n- 🛠️ **Preprocess** data using advanced filtering techniques.\n- 🤖 **Predict** wax type with AI.\n\n---\n\n### 📂 **Example Dataset**\nA sample dataset (`test_data.xlsx`) is included for demonstration purposes. It contains Vis-NIR spectral readings and hydroprocessing grades for various wax samples.\n\n\n---\n\n### 🤝 **Contributors**\n- **University of Cádiz (AGR-291 Research Group)**\n  - Specializing in hydrocarbon characterization and spectroscopy.\n\n---\n\n### 📜 **License**\nThis project is licensed under the GNU GENERAL PUBLIC License. See `LICENSE` for details.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmarta-barea%2Fvisnir-waxtype-classification-ml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmarta-barea%2Fvisnir-waxtype-classification-ml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmarta-barea%2Fvisnir-waxtype-classification-ml/lists"}