MaartenGr / MaartenGr/BERTopic

Additional labeling in visualize_documents

Open
#1,579 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
7.8k
Forks
920
Avg merge
22h 24m
Merged PRs (30d)
5

Description

I am doing some EDA on a corpus and was wondering if it was possible to make another layer of labeling for the individual documents. When you call ```visualize_documents``` the dots are plotted and color coded based on their respective topic, i was wondering if there was a way I could potentially alter the shape of the of the dot based on a factor, say for example I have a list of authors. I'd love to just use the BERTopic plotting mainly because I'm lazy 😅, but if its not possible at the moment I can recreate my own plots.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start at the visualize_documents entry point and trace how document points are plotted and color-coded by topic. Check whether the plotting interface already accepts document-level metadata, then determine how an author or other factor could select marker shapes. Done means callers can provide such a factor and the resulting visualization uses distinct shapes while preserving topic colors.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
data-visualization, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.