GitHub - klauslippert/keyword_extraction: extracting keywords (e.g. MeSH terms) from a text using dictionary lookup

keyword extraction

using a simple dictionary lookup approach.

keyword_extraction.py consists of 3 classes:

DictLU_Create_Dict: creates the dictionaries from a lookuplist (Pandas dataframe) to work with
DictLU_Extract_Exact: extract keywords from text by exact matching
DictLU_Extract_Fuzzy: WIP / todo: extracting of keywords by fuzzy matching (e.g. jaccard distance)

see the example jupyter notebook for usage.

Name		Name	Last commit message	Last commit date
Latest commit History 12 Commits
.gitignore		.gitignore
LICENSE		LICENSE
MeSH_dict_english.p		MeSH_dict_english.p
MeSH_dict_french.p		MeSH_dict_french.p
MeSH_dict_german.p		MeSH_dict_german.p
README.md		README.md
example_of_usage_w_MeSH.ipynb		example_of_usage_w_MeSH.ipynb
example_of_usage_w_country_iso_and_TLD_codes.ipynb		example_of_usage_w_country_iso_and_TLD_codes.ipynb
keyword_extraction.py		keyword_extraction.py
setup.py		setup.py