utkarshg1/fastapi-iris repository overview

⁠Iris Species Prediction App with FastAPI and Scikit-Learn

⁠Overview

This Docker image hosts an Iris Species Prediction web application built with FastAPI and Scikit-Learn. The app allows users to input sepal and petal measurements of iris flowers and returns a prediction of the iris species, along with the associated probabilities for each species. The model is trained using the classic Iris dataset.

⁠Github Repository Link

Github Link - https://github.com/utkarshg1/FastAPI-ML⁠

⁠Demo application link

Demo Link - https://iris-fastapi-meer.onrender.com/⁠

⁠Features

• Web UI: A user-friendly interface built with Jinja2 templates to input iris flower measurements.
• Prediction API: Utilizes a pre-trained Scikit-Learn model to predict the species of iris flowers based on user input.
• Real-Time Inference: Provides the prediction probabilities for each of the three iris species (setosa, versicolor, and virginica).
• FastAPI: An efficient, high-performance, asynchronous web framework for serving the app.
• Dockerized: Fully containerized for easy deployment and scaling.

⁠Technologies Used

• FastAPI: For building the web application and RESTful API.
• Scikit-Learn: For machine learning model training and prediction.
• Jinja2: For HTML templating.
• Docker: For containerizing the application, ensuring portability and consistency across different environments.

⁠How to Use

1. Pull the Image:

   docker pull utkarshg1/fastapi-iris
   

   Copy

2. Run the Container:

   docker run -d -p 8000:8000 utkarshg1/fastapi-iris:latest
   

   Copy

3. Access the Application:
   Open your web browser and go to http://localhost:8000 to start making predictions.

⁠Endpoints

• GET /: Displays the iris prediction form.
• POST /predict: Submits the form data and returns the predicted species along with probabilities.

⁠Environment Variables

• UVICORN_HOST: Set the host for the Uvicorn server (default: 0.0.0.0).
• UVICORN_PORT: Set the port for the Uvicorn server (default: 8000).

⁠Example Usage

1. Input sepal length, sepal width, petal length, and petal width in the form.
2. Click "Predict" to get the predicted species and its associated probabilities.

⁠License

This project is licensed under the Apache License 2.0

⁠Contributing

Feel free to submit issues or pull requests to improve the app.