/Zindi_Hackathon_Project

Solution for the Umojahack hackathon with MLOps using Sklearn and MLFlow and deployment using Flask

Primary LanguageJupyter NotebookMIT LicenseMIT

Zindi_Hackathon_Project

This Repo is a more advanced implementation of our work in the UmojaHack Hackathon (Largest Inter-University Hackathon in Africa organized by Zindi) using Sklearn for data preprocessing and for model engineering, and MLFlow for model monitoring, registring, orchestration, and deployed as an API locally using Flask.

Usage

Run the 'main.py' script to load the model and to train and to log the main metrics, you can change the model to one of the models existing in the 'models.py' script and rerun the 'main.py' script with one of those models.

Deployment

run the 'server.py' script to execute the API microservice server, and run 'inference.py' script to call the API and get the model predictions for our inference dataset

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

License

MIT