v0.7 (MaartenGr#87)

Highlights:  

* (semi-)supervised topic modeling
* Added Spacy, Gensim, USE (TFHub)
* Use a different backend for document embeddings and word embeddings
* Create your own backends with `bertopic.backend.BaseEmbedder`
* Calculate and visualize topics per class

Fixes:

* Fixed issues with Torch req
* Prevent saving term frequency matrix in CTFIDF class
* Fixed DTM not working when reducing topics (MaartenGr#96)
* Moved visualization dependencies to base BERTopic
* `pip install bertopic[visualization]` becomes `pip install bertopic`
* Allow precomputed embeddings in bertopic.find_topics() (MaartenGr#79)

Fix typo (MaartenGr#69)

v0.5 (MaartenGr#46)

* Add Flair to allow for more (custom) token/document embeddings
* Option to use custom UMAP, HDBSCAN, and CountVectorizer
* Added low_memory parameter to reduce memory during computation
* Improved verbosity (shows progress bar)
* Improved testing
* Use the newest version of sentence-transformers as it speeds ups encoding significantly
* Return the figure of visualize_topics()
* Expose all parameters with a single function: get_params()
* Option to disable the saving of embedding_model, should reduce BERTopic size significantly
* Add FAQ page

Fixed embedding parameter not working (MaartenGr#36)

Fix language bug (MaartenGr#34)

Update documentation

Bugfix topic reduction (MaartenGr#15)

* Fix topic reduction not accounting for linked mappings
* Return nr_topics + 1 (= outlier group)

Update README.md

Added probability distributions (MaartenGr#9)

* Add topic probabilities (MaartenGr#8)
* Added visualization of topic probabilities
* Update documentation
* Remove logging for topic reduction

Fixed ngram + added stopwords (MaartenGr#6, MaartenGr#5)

* Fixed ngram and added stopwords
* Update pypi version