Update smart_breed_matcher.py

smart_breed_matcher.py

@@ -81,33 +81,81 @@ class SmartBreedMatcher:
         return sorted(similarities, key=lambda x: x[1], reverse=True)[:top_n]
 
 
+    # def _calculate_breed_similarity(self, breed1_features: Dict, breed2_features: Dict) -> float:
+    #     """計算兩個品種之間的相似度，包含健康和噪音因素"""
+    #     # 計算描述文本的相似度
+    #     desc1_embedding = self._get_cached_embedding(breed1_features['description'])
+    #     desc2_embedding = self._get_cached_embedding(breed2_features['description'])
+    #     description_similarity = float(util.pytorch_cos_sim(desc1_embedding, desc2_embedding))
+
+    #     # 基本特徵相似度
+    #     size_similarity = 1.0 if breed1_features['size'] == breed2_features['size'] else 0.5
+    #     exercise_similarity = 1.0 if breed1_features['exercise'] == breed2_features['exercise'] else 0.5
+
+    #     # 性格相似度
+    #     temp1_embedding = self._get_cached_embedding(breed1_features['temperament'])
+    #     temp2_embedding = self._get_cached_embedding(breed2_features['temperament'])
+    #     temperament_similarity = float(util.pytorch_cos_sim(temp1_embedding, temp2_embedding))
+
+    #     # 健康分數相似度
+    #     health_score1 = self._calculate_health_score(breed1_features['breed_name'])
+    #     health_score2 = self._calculate_health_score(breed2_features['breed_name'])
+    #     health_similarity = 1.0 - abs(health_score1 - health_score2)
+
+    #     # 噪音水平相似度
+    #     noise_similarity = self._calculate_noise_similarity(
+    #         breed1_features['breed_name'],
+    #         breed2_features['breed_name']
+    #     )
+
+    #     # 加權計算
+    #     weights = {
+    #         'description': 0.25,
+    #         'temperament': 0.20,
+    #         'exercise': 0.2,
+    #         'size': 0.05,
+    #         'health': 0.15,
+    #         'noise': 0.15
+    #     }
+
+    #     final_similarity = (
+    #         description_similarity * weights['description'] +
+    #         temperament_similarity * weights['temperament'] +
+    #         exercise_similarity * weights['exercise'] +
+    #         size_similarity * weights['size'] +
+    #         health_similarity * weights['health'] +
+    #         noise_similarity * weights['noise']
+    #     )
+
+    #     return final_similarity
+
     def _calculate_breed_similarity(self, breed1_features: Dict, breed2_features: Dict) -> float:
         """計算兩個品種之間的相似度，包含健康和噪音因素"""
         # 計算描述文本的相似度
         desc1_embedding = self._get_cached_embedding(breed1_features['description'])
         desc2_embedding = self._get_cached_embedding(breed2_features['description'])
         description_similarity = float(util.pytorch_cos_sim(desc1_embedding, desc2_embedding))
-
-        # 基本特徵相似度
-        size_similarity = 1.0 if breed1_features['size'] == breed2_features['size'] else 0.5
-        exercise_similarity = 1.0 if breed1_features['exercise'] == breed2_features['exercise'] else 0.5
-
+    
+        # 使用新的精細計算方法
+        size_similarity = self._calculate_size_similarity(breed1_features['size'], breed2_features['size'])
+        exercise_similarity = self._calculate_exercise_similarity(breed1_features['exercise'], breed2_features['exercise'])
+    
         # 性格相似度
         temp1_embedding = self._get_cached_embedding(breed1_features['temperament'])
         temp2_embedding = self._get_cached_embedding(breed2_features['temperament'])
         temperament_similarity = float(util.pytorch_cos_sim(temp1_embedding, temp2_embedding))
-
+    
         # 健康分數相似度
         health_score1 = self._calculate_health_score(breed1_features['breed_name'])
         health_score2 = self._calculate_health_score(breed2_features['breed_name'])
         health_similarity = 1.0 - abs(health_score1 - health_score2)
-
+    
         # 噪音水平相似度
         noise_similarity = self._calculate_noise_similarity(
             breed1_features['breed_name'],
             breed2_features['breed_name']
         )
-
+    
         # 加權計算
         weights = {
             'description': 0.25,
@@ -117,7 +165,7 @@ class SmartBreedMatcher:
             'health': 0.15,
             'noise': 0.15
         }
-
+    
         final_similarity = (
             description_similarity * weights['description'] +
             temperament_similarity * weights['temperament'] +
@@ -126,7 +174,7 @@ class SmartBreedMatcher:
             health_similarity * weights['health'] +
             noise_similarity * weights['noise']
         )
-
+    
         return final_similarity
 
 
@@ -192,6 +240,24 @@ class SmartBreedMatcher:
             'scores': {k: round(v, 4) for k, v in scores.items()}
         }
 
+    def _calculate_size_similarity(self, size1: str, size2: str) -> float:
+        size_map = {'Small': 1, 'Medium': 2, 'Large': 3, 'Giant': 4}
+        value1 = size_map.get(size1, 2)  # 預設為 'Medium'
+        value2 = size_map.get(size2, 2)  # 預設為 'Medium'
+    
+        # 計算相似度
+        size_similarity = 1.0 - abs(value1 - value2) / 3
+        return max(0.0, size_similarity)  # 確保相似度在 [0, 1] 範圍內
+    
+    def _calculate_exercise_similarity(self, exercise1: str, exercise2: str) -> float:
+        exercise_map = {'Low': 1, 'Moderate': 2, 'High': 3, 'Very High': 4}
+        value1 = exercise_map.get(exercise1, 2)  # 預設為 'Moderate'
+        value2 = exercise_map.get(exercise2, 2)  # 預設為 'Moderate'
+    
+        # 計算相似度
+        exercise_similarity = 1.0 - abs(value1 - value2) / 3
+        return max(0.0, exercise_similarity)  # 確保相似度在 [0, 1] 範圍內
+
     def _calculate_health_score(self, breed_name: str) -> float:
         """計算品種的健康分數"""
         if breed_name not in breed_health_info: