{"id":32700368,"url":"https://github.com/iffat336/automl","last_synced_at":"2026-05-06T10:32:11.460Z","repository":{"id":321994176,"uuid":"1087831161","full_name":"iffat336/AutoML","owner":"iffat336","description":"AutoML-driven health prediction system showcasing automated model selection, visual analytics, and explainable AI.","archived":false,"fork":false,"pushed_at":"2025-11-01T20:58:57.000Z","size":568,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-11-01T22:21:02.814Z","etag":null,"topics":["artificial-intelligence","data-science","healthcare","kaggle","machine-learning","paycart"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/iffat336.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-11-01T18:24:01.000Z","updated_at":"2025-11-01T20:59:00.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/iffat336/AutoML","commit_stats":null,"previous_names":["iffat336/automl"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/iffat336/AutoML","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iffat336%2FAutoML","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iffat336%2FAutoML/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iffat336%2FAutoML/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iffat336%2FAutoML/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iffat336","download_url":"https://codeload.github.com/iffat336/AutoML/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iffat336%2FAutoML/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":282216044,"owners_count":26633413,"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":"2025-11-01T02:00:06.759Z","response_time":61,"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":["artificial-intelligence","data-science","healthcare","kaggle","machine-learning","paycart"],"created_at":"2025-11-01T23:00:36.786Z","updated_at":"2025-11-01T23:01:40.091Z","avatar_url":"https://github.com/iffat336.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🧠 AutoML Health Prediction\n\n**Author:** Iffat Nazir  \n**Repository:** [AutoML by Iffat336](https://github.com/iffat336/AutoML)  \n**License:** MIT License  \n**Last Updated:** November 2025  \n\n---\n\n## 🌿 Overview\n\n**AutoML Health Prediction** is a research-driven project that demonstrates how **Automated Machine Learning (AutoML)** can be leveraged to predict health risks efficiently and transparently.  \nBy integrating **PyCaret**, an open-source low-code machine learning library, this notebook automates the entire machine learning pipeline — from data preprocessing to model evaluation — without compromising explainability or accuracy.\n\nThis project was created as part of **Iffat Nazir’s data science portfolio**, focusing on health analytics and intelligent automation.  \nIt is ideal for **students, data science enthusiasts, and researchers** interested in applying AI to healthcare datasets.\n\n---\n\n## 🎯 Objectives\n\n- Build an **AutoML pipeline** to predict disease likelihood using health indicators.  \n- Compare multiple ML algorithms automatically for best accuracy.  \n- Generate **interactive visualizations** and **explainable AI insights**.  \n- Showcase professional workflow for GitHub \u0026 Kaggle portfolios.  \n\n---\n\n## 🧩 Key Features\n\n✅ Fully automated model training using **PyCaret**  \n✅ Preprocessing: handling missing values, encoding, normalization  \n✅ Comparative model leaderboard for accuracy, F1-score, etc.  \n✅ **Visualization suite:** correlation heatmaps, confusion matrix, ROC curve  \n✅ Feature importance and SHAP-based interpretability  \n✅ Modular notebook structure — easy to adapt for new datasets  \n✅ Designed to look human, documented like a professional project  \n\n---\n\n## 🧠 Tech Stack\n\n| Component | Tool/Library |\n|------------|--------------|\n| Language | Python 3.10+ |\n| Framework | PyCaret |\n| Data Manipulation | pandas, numpy |\n| Visualization | seaborn, matplotlib |\n| Environment | Jupyter Notebook |\n| Deployment | GitHub, Kaggle |\n\n---\n\n## 🩺 Data Description\n\nYou can use **any open-source health dataset** such as:\n- [Heart Disease Dataset (Kaggle)](https://www.kaggle.com/datasets/ronitf/heart-disease-uci)\n- [Cardiovascular Risk Dataset](https://www.kaggle.com/datasets/sulianova/cardiovascular-disease-dataset)\n- Or your own clinical data (if anonymized)\n\nThe dataset typically includes features like:\n- `age`, `sex`, `blood_pressure`, `cholesterol`, `glucose`, `smoking`, `exercise`, etc.  \nand a target variable like:\n- `disease` or `cardio` (1 = disease present, 0 = healthy)\n\n---\n\n## ⚙️ Installation \u0026 Setup\n\nClone this repository:\n```bash\ngit clone https://github.com/iffat336/AutoML.git\ncd AutoML\n\nInstall dependencies:\n\npip install -r requirements.txt\n\n\nRun the notebook:\n\njupyter notebook AutoML_Health_Prediction.ipynb\n📊 Results \u0026 Visuals\n\nThe notebook generates several insightful plots automatically:\n\nCorrelation Heatmap (Feature relationships)\n\nModel Leaderboard (Accuracy comparison)\n\nConfusion Matrix (Prediction quality)\n\nROC Curve (Model discrimination power)\n\nFeature Importance Plot (Key health predictors)\n\nAll visuals are saved in the /visuals folder.\n\n🧬 Insights \u0026 Interpretability\n\nAutoML ranked multiple models, and the top-performing one achieved X% accuracy (update with your result).\nFeature importance analysis revealed that variables like blood pressure, cholesterol, and BMI were strong predictors of disease risk.\nSHAP values further confirmed the explainability of the model outputs — ensuring trustworthy AI for healthcare.\n\n💡 How to Use\n\nReplace the dataset path in the notebook with your CSV file.\n\nRun all cells sequentially.\n\nReview the output — you’ll get:\n\nBest model summary\n\nEvaluation metrics\n\nVisuals saved automatically\n\n📘 Folder Structure\nAutoML/\n│\n├── AutoML_Health_Prediction.ipynb     # Main Jupyter Notebook\n├── README.md                          # Project Documentation\n├── LICENSE                            # Open-source License (MIT)\n├── requirements.txt                   # Python dependencies\n├── visuals/                           # Saved plots and charts\n└── data/                              # Input datasets (optional)\n\n🧑‍🔬 Author’s Note\n\nThis project is part of my ongoing journey to merge Artificial Intelligence and Health Sciences.\nThe goal is to create intelligent, data-driven solutions that can empower preventive care, fitness tracking, and early disease detection — forming the foundation for my future app idea, Healix.\n\nIf you find this useful, ⭐️ star the repo and follow for future updates.\n\n🧠 Future Improvements\n\nIntegrate with Streamlit for real-time web app visualization\n\nAdd deep learning models (TensorFlow, PyTorch)\n\nExpand dataset diversity (nutrition, activity tracking)\n\nDeploy trained models as APIs\n\n🤝 Contributions\n\nContributions are welcome!\nIf you’d like to improve visuals, add datasets, or optimize models:\n\nFork this repository\n\nCreate a new branch\n\nCommit your changes\n\nOpen a Pull Request\n\n📜 License\n\nDistributed under the MIT License.\nSee LICENSE file for more details.\n\n🌟 Acknowledgements\n\nSpecial thanks to:\n\nKaggle Datasets Community for providing open data\n\nPyCaret Developers for simplifying AutoML\n\nGitHub for empowering open-source research\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiffat336%2Fautoml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fiffat336%2Fautoml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiffat336%2Fautoml/lists"}