updates for heterogeneous mixture

algo.py

@@ -43,19 +43,18 @@ class Algo:
         #     if slow_mapping['similarity_score'] > mapping['similarity_score']:
         #         mapping = slow_mapping
 
-        if mapping['similarity_score'] < similarity_threshold and len(input_word.split(' ')) > 1:
-            print(" - Attempting reverse mapping")
-            reversed_input_word = ' '.join(input_word.split(' ')[::-1])
-            reversed_mapping = self.similarity_fast.find_most_similar_word(reversed_input_word)
-            if reversed_mapping['similarity_score'] > mapping['similarity_score']:
-                reversed_mapping.update(
-                    {
-                        'input_word': input_word, 
-                        'cleaned_word': mapping['cleaned_word']
-                    }
-                )
-                mapping = reversed_mapping
-        
+        # if mapping['similarity_score'] < similarity_threshold and len(input_word.split(' ')) > 1:
+        #     print(" - Attempting reverse mapping")
+        #     reversed_input_word = ' '.join(input_word.split(' ')[::-1])
+        #     reversed_mapping = self.similarity_fast.find_most_similar_word(reversed_input_word)
+        #     if reversed_mapping['similarity_score'] > mapping['similarity_score']:
+        #         reversed_mapping.update(
+        #             {
+        #                 'input_word': input_word, 
+        #                 'cleaned_word': mapping['cleaned_word']
+        #             }
+        #         )
+        #         mapping = reversed_mapping
 
         # check if the cleaned_word is a substring of the matching_word
         is_substring = mapping['cleaned_word'] in mapping['matching_word']
@@ -147,27 +146,36 @@ class Algo:
                 'food_nonfood_score': None
             }
 
-        self.db_cursor.execute(
-            f"SELECT DISTINCT wweia_category FROM dictionary WHERE description IN ({','.join(['%s']*len(dictionary_words))})",
-            dictionary_words
-        )
-        wweia_categories = self.db_cursor.fetchall()
-        wweia_categories = [x[0] for x in wweia_categories]
-        print("categories -> ", wweia_categories)
-        mixture = "Heterogeneous Mixture"
-        if len(set(wweia_categories)) == 1:
-            mixture = "Homogenous Mixture"
-        
+        # check if "Heterogenous" is in the wweia category of any of the mappings
+        # otherwise we find the mapping with the lowest DMC value, and return that as the dictionary word, dmc, wc, and leakage values
+        heterogenous_exists = False
+        most_conservative_mapping = None
+        for mapping in mappings:
+            if mapping['wweia_category'] == "Heterogenous":
+                heterogenous_exists = True
+                break
+            else:
+                if most_conservative_mapping is None or mapping['dry_matter_content'] < most_conservative_mapping['dry_matter_content']:
+                    most_conservative_mapping = mapping
+
+        dictionary_word = 'Hetereogenous Mixture'
+        if most_conservative_mapping is not None:
+            dictionary_word = f"{most_conservative_mapping['dictionary_word']} (Lowest DMC)"
+
         return {
             'input_word': input_word, 
             'cleaned_word': None, 
-            'matching_word': mixture, 
-            'dictionary_word': mixture,
+            'matching_word': dictionary_word, 
+            'dictionary_word': dictionary_word,
             'similarity_score': None, 
             'confidence_score': None,
             'similar_words': None,
             'is_food': True,
             'food_nonfood_score': 1.0,
+            'wweia_category': most_conservative_mapping['wweia_category'],
+            'water_content': most_conservative_mapping['water_content'],
+            'dry_matter_content': most_conservative_mapping['dry_matter_content'],
+            'leakage': most_conservative_mapping['leakage']
         }
 
     def handle_single_item(self, input_word):