add multi process predict

predictDiary.py

@@ -89,6 +89,18 @@ def router(device_id):
         predict(user_profile)
 
 
+# 多进程预测
+def multi_predict(predict_list,processes=8):
+    pool = Pool(processes)
+    for device_id in predict_list:
+        start = time.time()
+        pool.apply_async(router, (device_id,))
+        end = time.time()
+        print("该用户{}预测耗时{}秒".format(device_id, (end - start)))
+
+    pool.close()
+    pool.join()
+
 if __name__ == "__main__":
     # TODO 如果耗时小于一分钟，下一次取到的device_id和上一次相同
     while True:
@@ -100,14 +112,29 @@ if __name__ == "__main__":
             time.sleep(58)
         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:
-                    start = time.time()
-                    router(device_id)
-                    end = time.time()
-                    print("该用户预测耗时{}秒".format(end - start))
-                else:
-                    print("该用户不是老用户，不能预测")
+            predict_list = list(set(device_id_list) & set(old_device_id_list))
+            multi_predict(predict_list)
+
+    # while True:
+    #     empty,device_id_list = get_active_users()
+    #     if empty:
+    #         for eachFile in os.listdir("/tmp"):
+    #             if "xlearn" in eachFile:
+    #                 os.remove("/tmp" + "/" + eachFile)
+    #         time.sleep(58)
+    #     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:
+    #                 start = time.time()
+    #                 router(device_id)
+    #                 end = time.time()
+    #                 print("该用户预测耗时{}秒".format(end - start))
+    #             else:
+    #                 print("该用户不是老用户，不能预测")
+
+
+