Skip to content

Find Friends App

Data of creation: 2024-10-09

Project description

The aim of the project was to create an application that would enable the use of a clustering model to match a user to the appropriate group from a loaded data set (data comes from an anonymized survey) - based on data provided by the user.

Main functionalities

  • The user filters basic data, such as: age, education, gender, favorite animals, or favorite places - corresponding to their preferences
  • Then the previously trained clustering model creates the appropriate number of clusters for the survey data and matches the user's preferences to the matching group
  • Finally, using LLM, adequate cluster descriptions are generated

ML model training

I used Scikit-learn tools and I have included the implementation in a notebook ready for download:

Download Notebook: Model training

Clusters naming

I used the LLM model and I have included the implementation in a notebook ready for dowlonad:

Download Notebook: Clusters naming

Skills

  • Python
  • Langfuse
  • OpenAI
  • Streamlit
  • Scikit-learn
  • Plotly
  • PyCaret (Clustering)
  • NumPy
  • Matplotlib

Sample photos

alt text alt text

Application testing

The application has been deployed on the Streamlit Community App and is available for public use.

Link to repository

Go to application