This PR includes all require code and utils to conduct one of several semantic clustering approaches, namely:
strict hierarchical clustering
strict hierarchical clustering with proportional cluster sizes
fuzzy hierarchical clustering
hierarchical clustering via climbing an agglomerative clustering's dendrogram
hierarchical clustering using centroids of parent-level clusters
meta-clustering (in combination with community detection algorithm, not implemented here).
Single clustering outputs are created from make_taxonomy.py, which multiple clustering outputs (and the associated meta_cluster object) are created using make_taxonomies.py (which does not have argparse properties). See README in pipeline/semantic_taxonomy for more details.
Pipelines for embeddings generation are also included in this PR.
Fixes #9
Checklist:
[X] I have refactored my code out from notebooks/
[X] I have checked the code runs
[X] I have tested the code
[X] I have run pre-commit and addressed any issues not automatically fixed
[X] I have merged any new changes from dev
[X] I have documented the code
[X] Major functions have docstrings
[X] Appropriate information has been added to READMEs
Semantic Taxonomy
Description
This PR includes all require code and utils to conduct one of several semantic clustering approaches, namely:
Single clustering outputs are created from
make_taxonomy.py, which multiple clustering outputs (and the associated meta_cluster object) are created usingmake_taxonomies.py(which does not have argparse properties). See README inpipeline/semantic_taxonomyfor more details.Pipelines for embeddings generation are also included in this PR.
Fixes #9
Checklist:
notebooks/pre-commitand addressed any issues not automatically fixeddevREADMEs