Update smart_breed_matcher.py

smart_breed_matcher.py

@@ -1,4 +1,3 @@
-
 import torch
 import re
 import numpy as np
@@ -81,115 +80,52 @@ 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:
-        """增強版品種相似度計算"""
-        # 基礎相似度計算
+        """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))
-        
-        # 尺寸相似度（加強版）
-        size_similarity = self._calculate_size_similarity_enhanced(
-            breed1_features['size'], 
-            breed2_features['size'],
-            breed2_features['description']  # 加入描述以判斷適應性
-        )
-        
-        # 運動需求相似度（加強版）
-        exercise_similarity = self._calculate_exercise_similarity_enhanced(
-            breed1_features['exercise'],
-            breed2_features['exercise']
-        )
-        
-        # 美容需求相似度
-        grooming_similarity = self._calculate_grooming_similarity(
-            breed1_features['breed_name'],
-            breed2_features['breed_name']
-        )
-        
-        # 其他相似度計算保持不變
+
+        # 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']
         )
-    
-        # 調整權重分配
+
+        # 加權計算
         weights = {
-            'size': 0.20,        # 仍然重要但不過分主導
-            'exercise': 0.20,    # 保持高權重因為這是主要需求
-            'temperament': 0.15, # 保持不變因為性格很重要
-            'grooming': 0.15,    # 保持不變
-            'health': 0.15,      # 提高一點因為這影響長期生活
-            'description': 0.10, # 保持不變
-            'noise': 0.05        # 保持不變因為不是主要考慮因素
+            'description': 0.25,
+            'temperament': 0.20,
+            'exercise': 0.2,
+            'size': 0.05,
+            'health': 0.15,
+            'noise': 0.15
         }
-        
+
         final_similarity = (
-            size_similarity * weights['size'] +
-            exercise_similarity * weights['exercise'] +
-            grooming_similarity * weights['grooming'] +
-            temperament_similarity * weights['temperament'] +
             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
 
 
@@ -254,80 +190,6 @@ class SmartBreedMatcher:
             'bonus_score': round(bonus_score, 4),
             'scores': {k: round(v, 4) for k, v in scores.items()}
         }
-
-    def _calculate_size_similarity_enhanced(self, size1: str, size2: str, description: str) -> float:
-        """增強版尺寸相似度計算"""
-        # 更細緻的尺寸映射
-        size_map = {
-            'Tiny': 0,
-            'Small': 1,
-            'Small-Medium': 2,
-            'Medium': 3,
-            'Medium-Large': 4,
-            'Large': 5,
-            'Giant': 6
-        }
-        
-        # 轉換尺寸到數值
-        value1 = size_map.get(self._normalize_size(size1), 3)  # 預設為 Medium
-        value2 = size_map.get(self._normalize_size(size2), 3)
-        
-        # 計算基礎相似度
-        base_similarity = 1.0 - (abs(value1 - value2) / 6.0)
-        
-        # 根據用戶需求的尺寸偏好調整分數
-        if size2 in ['Small', 'Tiny']:
-            base_similarity *= 0.5  # 顯著降低小型犬的分數
-        elif size2 == 'Giant':
-            base_similarity *= 0.6  # 顯著降低巨型犬的分數
-        elif size2 in ['Medium', 'Medium-Large']:
-            base_similarity *= 1.2  # 提高中型和中大型犬的分數
-        
-        # 考慮適應性
-        if 'apartment' in description.lower() and size2 in ['Large', 'Giant']:
-            base_similarity *= 0.8  # 降低大型犬在公寓的適應性分數
-        
-        return min(1.0, base_similarity)  # 確保不超過1.0
-    
-    def _normalize_size(self, size: str) -> str:
-        """標準化尺寸分類"""
-        size = size.lower()
-        if 'tiny' in size:
-            return 'Tiny'
-        elif 'small' in size:
-            return 'Small'
-        elif 'medium' in size and 'large' in size:
-            return 'Medium-Large'
-        elif 'medium' in size:
-            return 'Medium'
-        elif 'giant' in size:
-            return 'Giant'
-        elif 'large' in size:
-            return 'Large'
-        return 'Medium'  # 預設
-    
-    def _calculate_exercise_similarity_enhanced(self, exercise1: str, exercise2: str) -> float:
-        """增強版運動需求相似度計算"""
-        exercise_map = {
-            'Low': 1,
-            'Moderate': 2,
-            'High': 3,
-            'Very High': 4
-        }
-        
-        value1 = exercise_map.get(exercise1, 2)
-        value2 = exercise_map.get(exercise2, 2)
-        
-        # 基礎相似度
-        base_similarity = 1.0 - abs(value1 - value2) / 3.0
-        
-        # 根據用戶需求調整
-        if exercise2 in ['High', 'Very High']:
-            base_similarity *= 1.2  # 提高高運動量品種的分數
-        elif exercise2 == 'Low':
-            base_similarity *= 0.7  # 降低低運動量品種的分數
-        
-        return min(1.0, base_similarity)
     
     def _calculate_grooming_similarity(self, breed1: str, breed2: str) -> float:
         """計算美容需求相似度"""