add print

diaryQueueUpdate.py

@@ -233,10 +233,10 @@ if __name__ == "__main__":
         print("累计预测用户总数：{}".format(total_number))
         if device_city_list != []:
             for device_city in device_city_list:
-                start = time.time()
+                # start = time.time()
                 multi_proecess_update(device_city[0], device_city[1], data_set_cid, total_video_id)
-                end = time.time()
-                print("更新该用户队列耗时{}秒".format((end - start)))
+                # end = time.time()
+                # print("更新该用户队列耗时{}秒".format((end - start)))
 
 
 

processData.py

@@ -68,7 +68,8 @@ def ffm_transform(data, test_number, validation_number):
     print("Start ffm transform")
     start = time.time()
     ffm_train = multiFFMFormatPandas()
-    data = ffm_train.fit_transform(data, y='y',n=50000,processes=8)
+    # 服务器内存空闲的时候，可以下面的6改成8。6比较稳定，如果服务器内存占用较多的时候，用8可能因为分配不到内存，脚本挂掉。
+    data = ffm_train.fit_transform(data, y='y',n=50000,processes=6)
     with open(DIRECTORY_PATH+"train/ffm.pkl", "wb") as f:
         pickle.dump(ffm_train, f)
 

train.py

@@ -29,3 +29,4 @@ if __name__ == "__main__":
 
 
 
+

utils.py

@@ -8,6 +8,7 @@ import pandas as pd
 from sklearn import metrics
 from sklearn.metrics import auc
 from multiprocessing import Pool
+import os
 
 
 def get_date():
@@ -46,6 +47,13 @@ def con_sql(sql):
     return df
 
 
+def move_file():
+    for eachFile in os.listdir("/data2/"):
+        if "xlearn" in eachFile:
+            os.remove("/tmp" + "/" + eachFile)
+
+
+
 # 把数据写到redis里
 # TODO 生产环境的redis地址没有提供，下面的地址是测试环境的，需要改成生产环境地址
 def add_data_to_redis(key, val):