A simple lightweight API built with Flask for deploying a machine learning model trained on the Iris flower dataset. This project demonstrates how to integrate and serve ML models through a RESTful API, deployed on PythonAnywhere for easy access.
- Predicts species of Iris flowers: setosa, versicolor, and virginica.
- RESTful endpoints for submitting sepal and petal measurements.
- Lightweight implementation suitable for quick prototyping.
The classification model used in this API is not optimized for maximum accuracy. The hyperparameters were left in a sub-optimal state intentionally, as the focus of this project is to demonstrate how a model can be deployed and served via a RESTful API, rather than achieving high performance. This conscious decision allows users to explore how changes in model configuration impact accuracy and other evaluation metrics.
The API is hosted in https://elecomexp.pythonanywhere.com/, making it accessible from any device with an internet connection.
- Clone the repository.
- Set up the virtual environment with Python 3.10.
- Install the requiered dependencies
- Run the Flask app locally or deploy it on PythonAnywhere.