MaartenGr/BERTopic

Custom labels for get_topic_tree

Open

#2,123 opened on Aug 17, 2024

View on GitHub
 (2 comments) (0 reactions) (0 assignees)Python (634 forks)batch import
good first issue

Repository metrics

Stars
 (5,074 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

Discussed in https://github.com/MaartenGr/BERTopic/discussions/2122

Originally posted by clfkenny August 17, 2024 Hi there, I noticed the visualize_hierarchy method has a custom_labels parameter. Is there anything similar to this for the get_topic_tree method? I use the LLM generated labels as the custom labels so the hierarchy tree is much easier to interpret. Thanks!

This seems like a good first issue for someone wanting to contribute to this repository. It has a very similar structure to the visualize_hierarchy functionality, so I believe it should be straightforward to implement. Unfortunately, I have a large backlog and cannot prioritize this, so if anyone wants to help out then that would be great!

Contributor guide

Research direction
Add a `custom labels` parameter to the `get topic tree` method, mirroring the implementation in `visualize hierarchy`. This involves modifying the method signature to accept an optional list of labels, and using those labels instead of the default topic representations when building the tree structure.
Tech stack
python
Domain
machine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonBERTopic
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
90