Spaces:

seanpedrickcase
/

topic_modelling

Running

3 contributors

Reduce outliers now more efficient and relabels with correct vectoriser. Default topic labels now tidier. Hiearchical topics outputs more useful for joining to df afterwards. Switched low resource reduction algorithm to UMAP as default is not good.

e1c1f68 5 months ago

__init__.py

0 Bytes

first commit 5 months ago
anonymiser.py

10.2 kB

Added clean data options, improved re-representation options and visualisation. General format changes 5 months ago
bertopic_vis_documents.py

47.2 kB

Reduce outliers now more efficient and relabels with correct vectoriser. Default topic labels now tidier. Hiearchical topics outputs more useful for joining to df afterwards. Switched low resource reduction algorithm to UMAP as default is not good. 5 months ago
clean_funcs.py

5.03 kB

Reduce outliers now more efficient and relabels with correct vectoriser. Default topic labels now tidier. Hiearchical topics outputs more useful for joining to df afterwards. Switched low resource reduction algorithm to UMAP as default is not good. 5 months ago
embeddings.py

2.54 kB

Hopefully now LLM download from hub should work 5 months ago
helper_functions.py

9.91 kB

Should now parse custom regex correctly. Will now wipe previously created embeddings if 'low resource mode' option switched. 5 months ago
presidio_analyzer_custom.py

4.18 kB

Added clean data options, improved re-representation options and visualisation. General format changes 5 months ago
prompts.py

4.86 kB

Model export changed to safetensors. Improved representational model function. Got zero shot topic modelling working 5 months ago
representation_model.py

6.74 kB

Hopefully now LLM download from hub should work 5 months ago
topic_core_funcs.py

25.1 kB

Reduce outliers now more efficient and relabels with correct vectoriser. Default topic labels now tidier. Hiearchical topics outputs more useful for joining to df afterwards. Switched low resource reduction algorithm to UMAP as default is not good. 5 months ago