更新xgboost模型预测过程中各阶段的耗时统计

src/core/recommender.py

@@ -25,6 +25,18 @@ from ydl_ai_recommender.src.utils.log import create_logger
 
 logger = create_logger(__name__, 'service_xgb.log', is_rotating=True)
 
+
+def cost_time(desc):
+    def the_func_cost_time(func):
+        def fun(*args,**kwargs):
+            t = time.perf_counter()
+            result = func(*args, **kwargs)
+            logger.info('函数:{},{} 耗时:{} ms'.format(str(func.__name__), desc, round((time.perf_counter()-t)*1000, 2)))
+            return result
+        return fun
+    return the_func_cost_time
+
+
 class Recommender():
 
     def __init__(self) -> None:
@@ -266,20 +278,22 @@ class RecommendByXgboost(Recommender):
         self.model = xgb.XGBClassifier(objective='binary:logistic', nthread=-1, **self.params)
         self.model.load_model(os.path.join(get_project_path(), 'model_data/xgb_model.bin'))
 
+    @cost_time(desc='')
+    def recall_data(self, user_id, size=0, is_merge=True):
+        return self.recommender.recommend(user_id, size=size, is_merge=True)
+
+    @cost_time(desc='模型推荐整个流程')
     def recommend(self, user_id, size=0, is_merge=True):
 
         s_u_profile_time = time.time()
         user_profile = self.get_user_profile(user_id)
         if not user_profile:
             return self._recommend_top(size)
-        recall_start = time.time()
-        # recommend_result = self.recommender.recommend(user_id, size=size, is_merge=True)
-        recommend_result = None
-        logger.info('recall call time:{}ms'.format(int((time.time()-recall_start)*1000)))
 
+        # recommend_result = self.recall_data(user_id, size=size, is_merge=True)
+        recommend_result = None
         data_time = time.time()
-        predit_data = self.trans_feature_data(user_id, recommend_result)
-        logger.info('data_time: {}ms'.format(int((time.time()-data_time)*1000)))
+        predit_data = self.trans_feature_data(user_id, user_profile, recommend_result)
         doctor_ids = predit_data.pop('doctor_id')
         doctor_ids = doctor_ids.to_numpy()
 
@@ -290,13 +304,14 @@ class RecommendByXgboost(Recommender):
         result_dict = sorted(result_dict.items(), key=lambda x:x[1], reverse=True)
         recommend_data = [{
             'counselor': int(c_id),
-            'score': float(proba),
+            'score': round(float(proba), 4),
             'from': 'similar_users {}'.format(user_id),
         } for (c_id, proba) in result_dict[0:50]]
         return recommend_data
 
-    def trans_feature_data(self, user_id, counselor_data):
-        user_feature_data = self.trans_user_feature_data(user_id)
+    @cost_time(desc='')
+    def trans_feature_data(self, user_id, user_profile, counselor_data):
+        user_feature_data = self.trans_user_feature_data(user_id, user_profile)
         counselor_feature_data = self.trans_counselor_feature_data(counselor_data)
         counselor_num = len(counselor_feature_data)
 
@@ -307,9 +322,9 @@ class RecommendByXgboost(Recommender):
         predit_feature_data = pd.concat([user_feature_data_dataframe, counselor_feature_data], axis=1)
         return predit_feature_data
 
-    def trans_user_feature_data(self, user_id):
+    def trans_user_feature_data(self, user_id, user_profile):
+        if not user_profile:
             user_profile = self.get_user_profile(user_id)
-
         from_login_encoder = self.get_encoder_from_dict('ffrom_login', user_profile['ffrom_login'])
         user_login_city_encoder = self.get_encoder_from_dict('user_login_city', user_profile['user_login_city'])
 
@@ -327,6 +342,7 @@ class RecommendByXgboost(Recommender):
         # return counselor_profiles
         return self.all_counselors
 
+    @cost_time(desc='获取用户画像')
     def get_user_profile(self, user_id):
         if user_id == '0':
             return []
@@ -347,7 +363,6 @@ class RecommendByXgboost(Recommender):
         try:
             get_profile_time = time.time()
             response = requests.request('POST', self.dmp_url, headers=headers, json=payload)
-            logger.info('get user profile cost: {}ms'.format(int((time.time()-get_profile_time)*1000)))
             resp = response.json()
             return resp['data']['objects'][0]
         except Exception as e:
@@ -398,11 +413,11 @@ if __name__ == '__main__':
     print()
     s_time = time.time()
     recommender = RecommendByXgboost()
-    recommender.recommend('12047')
+    recommender.recommend('3251227')
     print('all cost time: '.format(time.time()-s_time), recommender.recommend('12047'))
 
     # print()
     # print()
     # s_time = time.time()
-    # recommender.recommend('30004410')
+    # recommender.recommend('37298')
     # print('all cost time: '.format(time.time() - s_time), recommender.recommend('12047'))
\ No newline at end of file