seanpedrickcase/topic_modelling at 90553eb1d87ca48a5c17e65dd88980b50ce1d0c9

topic_modelling / funcs

Ctrl+K

3 contributors

History: 37 commits

seanpedrickcase

App now retains original index following cleaning to allow for referring back to original data

90553eb 11 months ago

__init__.py

0 Bytes

first commit over 1 year ago
anonymiser.py

10.6 kB

App now retains original index following cleaning to allow for referring back to original data 11 months ago
auth.py

1.88 kB

Only aggregate topics not 'other', allowed for minimum sentence length, default max_topics now will auto aggregate topics. Added Cognito Auth functionality (boto3 with AWS). about 1 year ago
bertopic_vis_documents.py

47.6 kB

Can split passages into sentences. Improved embedding, LLM representation models, improved zero shot capabilities about 1 year ago
clean_funcs.py

4.86 kB

Only aggregate topics not 'other', allowed for minimum sentence length, default max_topics now will auto aggregate topics. Added Cognito Auth functionality (boto3 with AWS). about 1 year ago
embeddings.py

3.37 kB

App now retains original index following cleaning to allow for referring back to original data 11 months ago
helper_functions.py

18.3 kB

App now retains original index following cleaning to allow for referring back to original data 11 months ago
presidio_analyzer_custom.py

4.18 kB

Added clean data options, improved re-representation options and visualisation. General format changes over 1 year ago
prompts.py

6.24 kB

Updated packages. Improve hierarchy vis. Better models - mixedbread and phi3. Now option to split texts into sentences before modelling. about 1 year ago
representation_model.py

7.83 kB

Removed some requirements from Dockerfile for AWS deployment to reduce container size about 1 year ago
topic_core_funcs.py

38.4 kB

App now retains original index following cleaning to allow for referring back to original data 11 months ago