Skip to content

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.

Main functionalities

  • 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

ML model training

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
  • Dotenv

Sample photos

alt text alt text

Link to repository