{"id":26507531,"url":"https://github.com/gangula-karthik/mlops-assignment","last_synced_at":"2026-04-07T23:31:03.597Z","repository":{"id":282748099,"uuid":"926950904","full_name":"gangula-karthik/MLOps-Assignment","owner":"gangula-karthik","description":"An end-to-end MLOps journey from car prices to wheat predictions, all powered by FastAPI, MLflow, and a dash of cloud magic!","archived":false,"fork":false,"pushed_at":"2025-12-14T16:34:15.000Z","size":16996,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-01-03T20:42:28.950Z","etag":null,"topics":["dagshub","google-cloud-run","mlflow","mlops","nextjs","pycaret","vercel"],"latest_commit_sha":null,"homepage":"https://ml-ops-assignment.vercel.app","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/gangula-karthik.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":"2025-02-04T06:19:54.000Z","updated_at":"2025-12-14T16:34:25.000Z","dependencies_parsed_at":"2025-03-16T19:05:05.251Z","dependency_job_id":null,"html_url":"https://github.com/gangula-karthik/MLOps-Assignment","commit_stats":null,"previous_names":["gangula-karthik/mlops-assignment"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/gangula-karthik/MLOps-Assignment","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gangula-karthik%2FMLOps-Assignment","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gangula-karthik%2FMLOps-Assignment/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gangula-karthik%2FMLOps-Assignment/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gangula-karthik%2FMLOps-Assignment/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gangula-karthik","download_url":"https://codeload.github.com/gangula-karthik/MLOps-Assignment/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gangula-karthik%2FMLOps-Assignment/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31533823,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-07T16:28:08.000Z","status":"ssl_error","status_checked_at":"2026-04-07T16:28:06.951Z","response_time":105,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["dagshub","google-cloud-run","mlflow","mlops","nextjs","pycaret","vercel"],"created_at":"2025-03-20T23:29:06.694Z","updated_at":"2026-04-07T23:31:03.581Z","avatar_url":"https://github.com/gangula-karthik.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# IT3385 - MLOps Assignment\n\nThis assignment was completed by Gangula Karthik, Choy Wei Jun and Gabriel Loh. It covers 3 end-to-end machine learning tasks with practical MLOps concepts used alongside the modelling process. To try out the website visit: https://ml-ops-assignment.vercel.app/\n\n![Screenshot](/assets/Screenshot%202025-02-28%20at%203.11.22 PM.png)\n\n## Important Links\n\n- Youtube video link: https://youtu.be/3A7-HXlz9pw\n- MLFlow remote tracking server: https://dagshub.com/gangula-karthik/MLOps-Assignment.mlflow/\n- DVC Tracking (configured on CLI to host in s3 bucket): https://dagshub.com/gangula-karthik/MLOps-Assignment?filter=dvc \n- Frontend: https://ml-ops-assignment.vercel.app/\n- Backend Documentation: https://mlops-assignment-734580083911.us-central1.run.app/docs\n\n\n## Technologies and Libraries Used\n\nThe folder structure was setup using cookiecutter\n\n```\ncookiecutter https://github.com/mihail911/e2eml-cookiecutter\n```\n\n```\n📦 Project Root  \n├── 📂 assets/         # Stores static files like images, PDFs, and other resources  \n├── 📂 backend/        # Contains all backend-related code, including APIs, models, and logic  \n│   ├── backend_car_price.py  \n│   ├── housepricingmodel_karthik_api.py  \n│   ├── wheatseeds_gabriel_api.py  \n│   ├── main.py        # Entry point for backend services  \n│   ├── best_cb_model.pkl  # Serialized ML model for car price prediction  \n│   ├── wheat_classifier_pipeline.pkl  # Serialized ML model for wheat classification  \n│   ├── logs.log       # Log file for backend operations  \n│   ├── requirements.txt  # Backend dependencies  \n│   ├── __init__.py  \n│   ├── *.pyc          # Compiled Python files  \n│   └── ...  \n│  \n├── 📂 conf/           # Configuration files for the project (e.g., environment settings)  \n│   ├── config.yaml    # Example: Configuration for ML models, paths, or API keys  \n│   ├── logging.conf   # Example: Logging configuration  \n│   └── ...  \n│  \n├── 📂 frontend/       # Stores frontend code (if applicable, e.g., React, HTML, CSS)  \n│   ├── src/          # Source code for frontend  \n|   |   ├── app/      # all the routes and frontend code\n|   |   ├── components/      # all the components for the individual sections\n│   ├── public/       # Static assets for frontend  \n│   ├── package.json  # Frontend dependencies (if using Node.js)  \n│  \n├── 📂 notebooks/      # Jupyter notebooks for data exploration, visualization, and analysis  \n│  \n├── .gitignore        # Specifies files and folders to ignore in version control  \n├── Dockerfile        # Defines how to containerize the project  \n├── LICENSE           # License file for the project  \n├── mlflow.db         # SQLite database for MLflow experiment tracking  \n├── mlruns.db         # Stores metadata for MLflow runs  \n├── poetry.lock       # Poetry lockfile for dependency management  \n├── pyproject.toml    # Poetry project file defining dependencies and project settings  \n└── README.md         # Main project documentation  \n```\n\nThis is the DVC Setup that was done: \n\n```\nS3 endpoint url: https://dagshub.com/gangula-karthik/MLOps-Assignment.s3\n\ndvc remote add origin s3://dvc\ndvc remote modify origin endpointurl https://dagshub.com/gangula-karthik/MLOps-Assignment.s3\n\ndvc remote modify origin --local access_key_id \u003cKEY\u003e\ndvc remote modify origin --local secret_access_key \u003cKEY\u003e\n```\n\nSetting Up the frontend\n```\ncd frontend/\nnpm i\nnpm run dev\n```\n\nSetting up the backend\n```\npoetry install\npoetry shell\ncd backend\npoetry run python main.py\n```\n\n**Backend**\n- Python\n- Pycaret: An automated machine learning library used to streamline the model development process for all three machine learning tasks.\n- FastAPI: A modern, fast (high-performance) web framework for building APIs with Python 3.7+ based on standard Python type hints.\n- Pydantic: A data validation and settings management library using Python type annotations, facilitating data parsing and validation for easier error handling and enforcement of type constraints.\n- MLflow: Utilized for tracking experiments, including parameter logging, metrics, and model versioning, to enhance model management and reproducibility.\n- DVC: Data Version Control was used to track and manage datasets and their versions, ensuring consistency across all stages of the project.\n- HYDRA: Employed for managing and configuring the application's environment, making it easier to switch between different setups without changing the codebase.\n- POETRY: Used for dependency management and packaging of project, ensuring that all necessary libraries are installed and maintained correctly.\n\n**Frontend**\n- Next.js: A React framework for building user interfaces, optimized for a smoother developer experience and high-performance applications.\n- HeroUI, ShadCN, and tailwindcss\n\n## Individual Contributions\n\nKarthik: \n- worked on housing price prediction\n- setup shared environment using poetry\n- setup dvc + aws s3 on the data folder\n- setup remote mlflow tracking server on dagshub\n- integrated different backends together using fastapi router\n- deployed frontend (on vercel) and backend (google cloud run)\n\nWei Jun: \n- worked on car sales prediction\n\nGabriel Loh: \n- worked on wheat type prediction\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgangula-karthik%2Fmlops-assignment","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgangula-karthik%2Fmlops-assignment","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgangula-karthik%2Fmlops-assignment/lists"}