Fix Mounjaro

fastdatascience · Aug 21, 2024 · ab18f60 · ab18f60
1 parent 489b93b
commit ab18f60
Show file tree

Hide file tree

Showing 4 changed files with 11 additions and 1 deletion.
diff --git a/harvesting_data_from_source/05_combine_data_sources.py b/harvesting_data_from_source/05_combine_data_sources.py
@@ -36,7 +36,7 @@
 
 from nltk.corpus import words
 
-from inclusions import common_english_words_to_include_in_drugs_dictionary, extra_terms_to_exclude_from_drugs_dictionary
+from inclusions import common_english_words_to_include_in_drugs_dictionary, extra_terms_to_exclude_from_drugs_dictionary, extra_mappings
 
 re_num = re.compile(r'^\d+$')
 re_three_digits = re.compile(r'\d\d\d')
@@ -197,6 +197,9 @@ def get_brand_names_nhs(description: str):
         for synonym in synonyms:
             add_synonym(synonym, canonical)
 
+for surface_form, canonical_form in extra_mappings.items():
+    add_synonym(surface_form, canonical_form)
+
 # Remove common English words
 
 print("Finding all drugs that are also in the NLTK list of English words.")

diff --git a/harvesting_data_from_source/inclusions.py b/harvesting_data_from_source/inclusions.py
@@ -347,3 +347,5 @@
     "java tea",
     "kidney tea",
 }
+
+extra_mappings = {"mounjaro": "tirzepatide"}
diff --git a/src/drug_named_entity_recognition/drug_ner_dictionary.pkl.bz2 b/src/drug_named_entity_recognition/drug_ner_dictionary.pkl.bz2
diff --git a/tests/test_drugs_finder.py b/tests/test_drugs_finder.py
@@ -147,3 +147,8 @@ def test_penicillin_streptomycin(self):
         drugs = find_drugs("i bought some Penicillin streptomycin".split(" "), is_include_structure=True)
 
         self.assertEqual(2, len(drugs))  # should be 1?
+
+    def test_mounjaro(self):
+        drugs = find_drugs("i bought some Mounjaro".split(" "), is_include_structure=True)
+
+        self.assertEqual(1, len(drugs))