fixes for wweia categories

algo.py

@@ -142,7 +142,11 @@ class Algo:
                     'confidence_score': None, 
                     'similar_words': None,
                     'is_food': False,
-                    'food_nonfood_score': 1.0
+                    'food_nonfood_score': 1.0,
+                    'wweia_category': 'Non-Food Item',
+                    'water_content': None,
+                    'dry_matter_content': None,
+                    'leakage': None
                 }
                 break
 
@@ -358,7 +362,7 @@ class Algo:
                 results_batch.append(mapping)
         
             # Store results in batches
-            if len(results_batch) >= 1000:
+            if len(results_batch) == 1:
                 store_results_batch(self.db_cursor, self.db_conn, self.run_key, results_batch)
                 results_batch = []
 

db/db_utils.py

@@ -183,38 +183,32 @@ def store_result_to_db(cursor, conn, run_key, result):
         return False
 
 def store_results_batch(cursor, conn, run_key, results_batch):
-    try:
-        cursor.executemany('''
-            INSERT INTO results (run_key, run_row, date, input_word, dictionary_word, is_food, wweia_category, dry_matter_content, leakage, weight, weight_metric_tonnes, donor, similarity_score, food_nonfood_score, distance, ef, mt_lb_mile, baseline_emissions, leakage_emissions, project_emissions, total_emissions_reduction)
-            VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
-        ''', [
-            (
-                run_key,
-                result['run_row'],
-                result['date'], 
-                result['input_word'], 
-                result['dictionary_word'], 
-                result['is_food'], 
-                result['wweia_category'], 
-                result['dry_matter_content'],
-                result['leakage'],
-                result['weight'],
-                result['weight_metric_tonnes'],
-                result['donor'],
-                result['similarity_score'], 
-                result['food_nonfood_score'],
-                result['distance'],
-                result['ef'], 
-                result['mt_lb_mile'], 
-                result['baseline_emissions'], 
-                result['leakage_emissions'],
-                result['project_emissions'],  
-                result['total_emissions_reduction']
-            ) for result in results_batch
-        ])
-        conn.commit()
-    except Exception as e:
-        logging.info(f" - Error storing results to db: {e}")
-        conn.rollback()
-        return False
-    return True
+    cursor.executemany('''
+        INSERT INTO results (run_key, run_row, date, input_word, dictionary_word, is_food, wweia_category, dry_matter_content, leakage, weight, weight_metric_tonnes, donor, similarity_score, food_nonfood_score, distance, ef, mt_lb_mile, baseline_emissions, leakage_emissions, project_emissions, total_emissions_reduction)
+        VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
+    ''', [
+        (
+            run_key,
+            result['run_row'],
+            result['date'], 
+            result['input_word'], 
+            result['dictionary_word'], 
+            result['is_food'], 
+            result['wweia_category'], 
+            result['dry_matter_content'],
+            result['leakage'],
+            result['weight'],
+            result['weight_metric_tonnes'],
+            result['donor'],
+            result['similarity_score'], 
+            result['food_nonfood_score'],
+            result['distance'],
+            result['ef'], 
+            result['mt_lb_mile'], 
+            result['baseline_emissions'], 
+            result['leakage_emissions'],
+            result['project_emissions'],  
+            result['total_emissions_reduction']
+        ) for result in results_batch
+    ])
+    conn.commit()

run.py

@@ -40,6 +40,9 @@ if __name__ == "__main__":
 
     input_data = input_data[last_row_num:]
 
+    # limit to 100 rows
+    # input_data = input_data[:100]
+
     # profiler = cProfile.Profile()
     # profiler.enable()