MaartenGr / MaartenGr/BERTopic
Document Visualization - Point Coordinates
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 7.8k
- Forks
- 920
- Avg merge
- 22h 24m
- Merged PRs (30d)
- 5
Description
Hello,
Thank you for the wonderful work you have done and still do on BERTopic. It's a game-changer in topic analysis trully...
I am running a topic analysis for research purposes and I was wondering the following, is it possible to extract the "coordinates" of each document presented through the 'topic_visualize' function? The reason I am searching for this is because I would like to edit the plot on different data analysis software (e.g. Tableau).
I already tried to extract the 'X, Y' of each point (per topic) by running the 'topic_model.visualize_documents(data_list).to_dict' command, but the final scatter plot is a tad different to the one generated by the script.
Do you have any suggestions on this?
Thank you very much in advance!
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the `topic_visualize` and `topic_model.visualize_documents(data_list)` entry points, then compare their `to_dict` output with the generated scatter plot. Done means the document point coordinates can be extracted reproducibly for use in external analysis software such as Tableau.
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