Merge branch 'master' of git.wanmeizhensuo.com:ML/ffm-baseline

update comment

local/test_supervisor.py

@@ -100,15 +100,13 @@ def get_active_users():
     device_id_df = con_sql(sql)
     if device_id_df.empty:
         print("当下这一分钟没有活跃用户，不需要预测")
-        # 为了debug supervisor，修改了下面的return参数
-        return 1,[1,2]
+        return True,None
     else:
         device_id_list = device_id_df[0].values.tolist()
         # 对device_id 进行去重
         device_id_list = list(set(device_id_list))
         print("成功获取当下一分钟内活跃用户")
-        # 为了debug supervisor，修改了下面的return参数
-        return "0",device_id_list
+        return False,device_id_list
 
 def fetch_user_profile(device_id):
 
@@ -181,12 +179,14 @@ def predict(user_profile):
 
     ffm_model = xl.create_ffm()
     ffm_model.setTest(instance_file_path)
+
     ffm_model.setSigmoid()
+
     ffm_model.predict(DIRECTORY_PATH + "model_{0}-{1}_lr{2}_lambda{3}.out".format(DATA_START_DATE,
                                                                                   DATA_END_DATE, lr, l2_lambda),
                       DIRECTORY_PATH + "result/{0}_output.txt".format(user_profile['device_id']))
     print("预测结束")
-    predict_save_to_local(user_profile, instance)
+    # predict_save_to_local(user_profile, instance)
 def router(device_id):
     user_profile, not_exist = fetch_user_profile(device_id)
 
@@ -198,18 +198,23 @@ def router(device_id):
 if __name__ == "__main__":
     while True:
         start = time.time()
-        get_active_users()
-        # empty,device_id_list = get_active_users()
-        # if empty==1:
-        #     time.sleep(30)
-        # else:
-
-            # old_device_id_list = pd.read_csv(DIRECTORY_PATH + "data_set_device_id.csv")["device_id"].values.tolist()
-            # for device_id in device_id_list:
-            #     if device_id in old_device_id_list:
-            #         router(device_id)
-            #     else:
-            #         print("该用户不是老用户，不能预测")
+        empty,device_id_list = get_active_users()
+        if empty==True:
+            time.sleep(30)
+        else:
+            old_device_id_list = pd.read_csv(DIRECTORY_PATH + "data_set_device_id.csv")["device_id"].values.tolist()
+            for device_id in device_id_list:
+                if device_id in old_device_id_list:
+                    # router(device_id)
+                    user_profile, not_exist = fetch_user_profile(device_id)
+
+                    if not_exist == 1:
+                        print('Sorry, we don\'t have you.')
+                    else:
+                        predict(user_profile)
+
+                else:
+                    print("该用户不是老用户，不能预测")
             # end = time.time()
             # time_cost = (end - start)
             # print("耗时{}秒".format(time_cost))

predictDiary.py

@@ -88,8 +88,7 @@ def predict_save_to_redis(user_profile, instance):
 
 def router(device_id):
     user_profile, not_exist = fetch_user_profile(device_id)
-
-    if not_exist==1:
+    if not_exist==True:
         print('Sorry, we don\'t have you.')
     else:
         predict(user_profile)
@@ -100,7 +99,7 @@ if __name__ == "__main__":
     while True:
         start = time.time()
         empty,device_id_list = get_active_users()
-        if empty==1:
+        if empty==True:
             time.sleep(60)
         else:
             old_device_id_list = pd.read_csv(DIRECTORY_PATH + "data_set_device_id.csv")["device_id"].values.tolist()

userProfile.py

@@ -14,15 +14,13 @@ def get_active_users():
     device_id_df = con_sql(sql)
     if device_id_df.empty:
         print("当下这一分钟没有活跃用户，不需要预测")
-        # 为了debug supervisor，修改了下面的return参数
-        return 1,[1,2]
+        return True,None
     else:
         device_id_list = device_id_df[0].values.tolist()
         # 对device_id 进行去重
         device_id_list = list(set(device_id_list))
         print("成功获取当下一分钟内活跃用户")
-        # 为了debug supervisor，修改了下面的return参数
-        return "0",device_id_list
+        return False,device_id_list
 
 
 def fetch_user_profile(device_id):
@@ -30,13 +28,11 @@ def fetch_user_profile(device_id):
         user_profile = con_sql(sql)
         if user_profile.empty:
             print("没有获取到该用户对应的city_id")
-            # 为了debug supervisor，修改了下面的return参数
-            return {1:2}, 1
+            return None,True
         else:
             user_profile = user_profile.rename(columns={0:"device_id",1:"city_id"})
             print("成功获取该用户对应的city_id")
             user_profile_dict = {}
             for i in user_profile.columns:
                 user_profile_dict[i] = user_profile.loc[0, i]
-                # 为了debug supervisor，修改了下面的return参数
-            return user_profile_dict, "0"
+            return user_profile_dict, False