Halfmarathon Estimator App
Date of creation: 2024-10-20
Project description:
The aim of the project was to create an application that would use a regression algorithm to train models and would be able to predict (based on previously trained data) the time in which a user would run a half marathon - by providing specific data.
Project description:
- allowing the user to enter data freely (without any appropriate conversion of the record) -> the LLM model used extracts data from the user into a JSON structure and prepares it for use by the regression model,
- simple functionality allows for the final estimation of the time to run a half marathon - using the trained best regression model,
- the LLM model is connected to Langfuse to track the model's life cycle.
To train the AI model I used PyCaret tools and I have included the implementation in a notebook ready for download:
Download Notebook: Model training
Skills:
- Python,
- PyCaret,
- Machine Learning,
- Langfuse,
- OpenAI,
- Streamlit,
- Pandas,
- Instructor,
- Pydantic,
- Langfuse,
- Dotenv.
Sample photos:
The application has been deployed on the Streamlit Community App and is available for public use.
Link to repository: https://github.com/kasjansmigielski/halfmarathon_estimator_app
Link to app: https://halfmarathon-estimator.streamlit.app/