Merge pull request #46 from ccb-hms/development

Optimize filter_mappings()

.github/workflows/python-app.yml

@@ -26,7 +26,6 @@ jobs:
     - name: show python path
       run: |
         python -c "import sys; print('\n'.join(sys.path))"
-        echo $PYTHONPATH
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip

text2term/onto_cache.py

@@ -3,8 +3,8 @@
 import text2term
 import owlready2
 import pandas as pd
-from .term import OntologyTermType
-from .mapper import Mapper
+from text2term.term import OntologyTermType
+from text2term.mapper import Mapper
 from shutil import rmtree
 
 CACHE_FOLDER = "cache"

text2term/t2t.py

@@ -265,13 +265,11 @@ def _add_tags_to_df(df, tags):
 
 
 def _filter_mappings(mappings_df, min_score):
-    new_df = pd.DataFrame(columns=mappings_df.columns)
-    for index, row in mappings_df.iterrows():
-        if row['Mapping Score'] >= min_score:
-            new_df.loc[len(new_df.index)] = row
+    if mappings_df.empty:
+        return mappings_df
+    new_df = mappings_df.loc[mappings_df["Mapping Score"] >= min_score]
     return new_df
 
-
 def _add_unmapped_terms(mappings_df, tags, source_terms, source_terms_ids):
     if mappings_df.size == 0:
         mapped = []

text2term/term_collector.py

@@ -48,7 +48,7 @@ def get_ontology_terms(self, base_iris=(), exclude_deprecated=False, term_type=O
         return ontology_terms
 
     def filter_terms(self, onto_terms, iris=(), excl_deprecated=False, term_type=OntologyTermType.ANY):
-        return filter_terms(onto_terms, iris, exclude_deprecated, term_type)
+        return filter_terms(onto_terms, iris, excl_deprecated, term_type)
 
     def _get_ontology_signature(self, ontology):
         signature = list(ontology.classes())