Merge pull request #58 from ccb-hms/development

Updated dependencies

.github/workflows/github_test.yml

@@ -1,8 +1,8 @@
 # This workflow will install Python dependencies, run tests and lint with a single version of Python
 # For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
 
-name: Tests
-run-name: Unit Testing on ${{ github.event_name }}
+name: CI Tests
+run-name: CI Testing on ${{ github.event_name }}
 
 on:
   push:

README.md

@@ -14,6 +14,8 @@
    <a href="https://doi.org/10.48550/arXiv.2407.02626">
         <img alt="arXiv preprint" src="https://img.shields.io/badge/DOI-arXiv:2407.02626-orange" />
    </a>
+   <img alt="PyPI Installs" src="https://img.shields.io/pypi/dm/text2term?label=pypi%20installs&color=D3CB40">
+   <img alt="Total Downloads" src="https://img.shields.io/pepy/dt/text2term?label=downloads&color=D10000">
 </div>
 
 ## Installation

requirements.txt

@@ -1,16 +1,16 @@
-Owlready2~=0.44
+owlready2~=0.46
 argparse~=1.4.0
-pandas~=2.0.3
-numpy~=1.24.2
-gensim~=4.3.0
-scipy~=1.10.1
-scikit-learn~=1.2.1
-setuptools~=68.2.2
-requests~=2.31.0
+pandas~=2.2.2
+numpy~=1.26.4
+gensim~=4.3.2
+scipy~=1.12.0
+scikit-learn~=1.5.1
+setuptools~=70.2.0
+requests~=2.32.3
 tqdm~=4.66.1
-sparse_dot_topn~=0.3.4
-bioregistry~=0.10.6
+sparse-dot-topn~=1.1.3
+bioregistry~=0.11.10
 nltk~=3.8.1
-rapidfuzz~=2.13.7
+rapidfuzz~=3.9.4
 shortuuid~=1.0.11
-myst_parser~=2.0.0
+myst-parser~=2.0.0

setup.py

@@ -1,7 +1,7 @@
 from setuptools import setup, find_packages
 from text2term.config import VERSION
 
-description = 'A tool for mapping free-text descriptions of (biomedical) entities to controlled terms in ontologies'
+description = 'a tool for mapping free-text descriptions of entities to ontology terms'
 long_description = open('README.md').read()
 
 with open('requirements.txt') as f:
@@ -24,9 +24,13 @@
         'Development Status :: 4 - Beta',
         'License :: OSI Approved :: MIT License',
         'Operating System :: OS Independent',
+        'Environment :: Console',
         'Programming Language :: Python',
         'Programming Language :: Python :: 3',
         'Programming Language :: Python :: 3.9',
+        'Programming Language :: Python :: 3.10',
+        'Programming Language :: Python :: 3.11',
+        'Programming Language :: Python :: 3.12',
         'Topic :: Scientific/Engineering'
     ],
     python_requires=">=3.9",

text2term/__main__.py

@@ -4,7 +4,6 @@
 from t2t import map_terms, cache_ontology
 from onto_cache import cache_exists
 from mapper import Mapper
-from term import OntologyTermType
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description='A tool for mapping free-text descriptions of (biomedical) '
@@ -25,7 +24,7 @@
                              "that contains the terms to map, optionally followed by the name of the column that "
                              "contains identifiers for the terms (eg 'my_terms,my_term_ids')")
     parser.add_argument("-sep", "--separator", required=False, type=str, default=',',
-                        help="Specifies the cell separator to be used when reading a non-comma-separated tabular file")
+                        help="Specifies the cell separator to be used when reading a table")
     parser.add_argument("-top", "--top_mappings", required=False, type=int, default=3,
                         help="Maximum number of top-ranked mappings returned per source term (default=3)")
     parser.add_argument("-min", "--min_score", required=False, type=float, default=0.5,
@@ -38,9 +37,9 @@
     parser.add_argument("-g", "--save_term_graphs", required=False, default=False, action="store_true",
                         help="Save vis.js graphs representing the neighborhood of each ontology term (default=False)")
     parser.add_argument("-c", "--store_in_cache", required=False, type=str, default="",
-                        help="Store the target ontology into local cache under acronym")
+                        help="Cache the target ontology using the name given here")
     parser.add_argument("-type", "--term_type", required=False, type=str, default="class",
-                        help="Define whether to return ontology classes, properties, or both")
+                        help="Define whether to map to ontology classes, properties, or both")
     parser.add_argument('-u', "--incl_unmapped", required=False, default=False, action="store_true",
                         help="Include all unmapped terms in the output")
 

text2term/config.py

@@ -1 +1 @@
-VERSION = "4.1.4"
+VERSION = "4.2.0"

text2term/syntactic_mapper.py

@@ -79,32 +79,31 @@ def compare_levenshtein(self, s1, s2):
         Calculates the normalized Levenshtein distance between s1 and s2.
         :return similarity between s1 and s2 as a float between 0 and 1
         """
-        similarity = rapidfuzz.string_metric.normalized_levenshtein(s1, s2)/100
+        similarity = rapidfuzz.distance.Levenshtein.normalized_similarity(s1, s2)
         return similarity
 
     def compare_jaro(self, s1, s2):
         """
         Calculates the Jaro similarity between s1 and s2.
         :return similarity between s1 and s2 as a float between 0 and 1
         """
-        similarity = rapidfuzz.string_metric.jaro_similarity(s1, s2)/100
+        similarity = rapidfuzz.distance.Jaro.normalized_similarity(s1, s2)
         return similarity
 
     def compare_jarowinkler(self, s1, s2):
         """
         Calculates the Jaro-Winkler similarity between s1 and s2.
         :return similarity between s1 and s2 as a float between 0 and 1
         """
-        similarity = rapidfuzz.string_metric.jaro_winkler_similarity(s1, s2)/100
+        similarity = rapidfuzz.distance.Jaro.normalized_similarity(s1, s2)
         return similarity
 
     def compare_indel(self, s1, s2):
         """
         Calculates the normalized Indel distance between s1 and s2.
-        See: https://maxbachmann.github.io/RapidFuzz/Usage/fuzz.html#ratio
         :return similarity between s1 and s2 as a float between 0 and 1
         """
-        similarity = rapidfuzz.fuzz.ratio(s1, s2)/100
+        similarity = rapidfuzz.distance.Indel.normalized_similarity(s1, s2)
         return similarity
 
     def compare_fuzzy_ratio(self, s1, s2):