make math terms dict more readable

handler.py

@@ -259,15 +259,18 @@ class FocusingQuestionModel:
 
 def load_math_terms():
     math_terms = []
+    math_terms_dict = {}
     for term in MATH_WORDS:
         if term in MATH_PREFIXES:
+            math_terms_dict[f"(^|[^a-zA-Z]){term}(s|es)?([^a-zA-Z]|$)"] = term
             math_terms.append(f"(^|[^a-zA-Z]){term}(s|es)?([^a-zA-Z]|$)")
         else:
+            math_terms_dict[f"(^|[^a-zA-Z]){term}([^a-zA-Z]|$)"] = term
             math_terms.append(f"(^|[^a-zA-Z]){term}([^a-zA-Z]|$)")
-    return math_terms
+    return math_terms, math_terms_dict
 
 def run_math_density(transcript):
-    math_terms = load_math_terms()
+    math_terms, math_terms_dict = load_math_terms()
     for i, utt in enumerate(transcript.utterances): 
         found_math_terms = set()
         text = utt.get_clean_text(remove_punct=False)
@@ -275,7 +278,7 @@ def run_math_density(transcript):
         for term in math_terms:
             count = len(re.findall(term, text))
             if count > 0:
-                found_math_terms.add(term)
+                found_math_terms.add(math_terms_dict[term])
             num_math_terms += count
         utt.num_math_terms = num_math_terms
         utt.math_terms = list(found_math_terms)