Leveraging BERT and c-TF-IDF to create easily interpretable topics.
active 2025-03-28 → 2026-08-02 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 493 days from 2025-03-28 to 2026-08-02. Pushes: 33 total, peak 6 in a day. Pull requests: 29 total, peak 3 in a day. Issues: 25 total, peak 2 in a day. Comments: 117 total, peak 13 in a day. Stars: 427 total, peak 6 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| MaartenGr | 107 | 33 | 14 | 53 |
| shuanglovesdata | 11 | 0 | 0 | 8 |
| saikumaru | 11 | 0 | 1 | 5 |
| afuetterer | 10 | 0 | 3 | 7 |
| raffaem | 4 | 0 | 0 | 0 |
| carobs9 | 4 | 0 | 0 | 3 |
| betatim | 3 | 0 | 1 | 2 |
| 6801318d8d | 3 | 0 | 0 | 1 |
| makramab | 3 | 0 | 0 | 3 |
| Jason990407 | 3 | 0 | 0 | 2 |
| mzeres | 3 | 0 | 0 | 2 |
| keyuchen21 | 3 | 0 | 0 | 2 |
| rhys-thompson-deel | 2 | 0 | 0 | 2 |
| andrebittar-ko | 2 | 0 | 0 | 2 |
| NJAHNAVI2907 | 2 | 0 | 0 | 1 |
| huisman | 2 | 0 | 2 | 0 |
| luismavs | 2 | 0 | 0 | 2 |
| jemather | 2 | 0 | 0 | 1 |
| angelonazzaro | 2 | 0 | 2 | 0 |
| Quadrophonia | 2 | 0 | 0 | 2 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#1575luxurystorecc12026-05-07 06:22Adding custom topic aspect after training
- Issue comment#2460afuetterer2026-04-25 20:15Switch documentation from `mkdocs-material` to `zensical`
- Pull request#2480sebastianbreguel2026-04-07 21:00
- Issue#2475raffaem2026-03-08 17:26find_topics(topic) crashes if topic is a 1-element list
- Issue#2475raffaem2026-03-08 17:26find_topics(topic) crashes if topic is a 1-element list
- Issue comment#2108MMHHRR2026-02-05 11:02UnicodeEncodeError: 'ascii' codec can't encode characters in position 18-20: ordinal not in range(128)
- Issue comment#2468MaartenGr2026-01-19 15:18German Language Issues: Umlaut Removal and Compound Word Truncation in c-TF-IDF
- Pull request#2467MaartenGr2026-01-03 09:33
- Pull request#2461afuetterer2025-12-17 08:12
- Issue comment#2461MaartenGr2025-12-17 08:12Enable ruff rule `PD`
- Issue comment#2454MaartenGr2025-12-03 16:07Make `SklearnEmbedder` return a dense array
- Issue comment#2423okkymabruri2025-11-30 01:42BadRequestError: Error code: 400 - {'error': {'message': "Unsupported parameter: 'stop' is not supported with this model.", 'type': 'invalid_request_error', 'param': 'stop', 'code': 'unsupported_parameter'}}
- Issue#2458Iyeleon2025-11-16 02:35Allow option to show heatmap annotation
- Issue comment#2451MaartenGr2025-11-11 12:14Update topic mapping when all documents match zero-shot topics
- Pull request#2455khanhkhanhlele2025-11-06 11:18
- Pull request#2451huisman2025-10-29 20:49
- Issue comment#1966bertagrim2025-10-26 19:41Getting probabilities for all topics given a document from loaded model
- Issue comment#2448MaartenGr2025-10-25 07:33Fix incorrect label in zero-shot svg in documentation
- Issue comment#2447MaartenGr2025-10-25 07:31Topic names not set to zero-shot topic when `fit_transform` results in only zero-shot topics
- Pull request#2448huisman2025-10-25 07:14
- Issue comment#2446MaartenGr2025-10-25 07:04Update installation instructions for cuML with BERTopic.
- Issue comment#2429NJAHNAVI29072025-10-23 09:32MLflow Autologging Integration for BERTopic
- Issue comment#2445afuetterer2025-10-23 08:58ci: switch to uv based project installation
- Issue comment#2445afuetterer2025-10-23 08:58ci: switch to uv based project installation
- Issue comment#2082afuetterer2025-10-23 08:42ci: speed up by using uv to install python packages
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 427 stars here means stars gained during the window, not the repo's star count.