修改配置文件文件路径

dataProcess.py

@@ -68,8 +68,7 @@ def ffm_transform(data, test_number, validation_number):
     print("Start ffm transform")
     start = time.time()
     ffm_train = multiFFMFormatPandas()
-    # 服务器内存空闲的时候，可以下面的4改成6。4比较稳定，如果服务器内存被其他程序占用较多的时候，用6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=8)
+    data = ffm_train.fit_transform(data, y='y',n=50000,processes=20)
     with open(DIRECTORY_PATH+"train/ffm.pkl", "wb") as f:
         pickle.dump(ffm_train, f)
 

train.py

@@ -19,7 +19,7 @@ if __name__ == "__main__":
     print("训练模型耗时{}分".format((end_train-start_train)/60))
     move_file()
     #TODO 如果用自己写的keepProcess文件守护进程，下面在这个函数里删掉重新启动进程那行代码，因为可能会多启动一次进程
-    restart_process()
+    # restart_process()
 
 
 

utils.py

@@ -18,9 +18,12 @@ def get_date():
     month = now.month
     day = now.day
     date = datetime(year,month,day)
-    data_start_date = (date - timedelta(days=3)).strftime("%Y-%m-%d")
-    data_end_date = (date - timedelta(days=1)).strftime("%Y-%m-%d")
-    validation_date = (date - timedelta(days=2)).strftime("%Y-%m-%d")
+    data_start_date = "2018-07-15"
+    data_end_date = "2018-08-30"
+    validation_date = "2018-08-29"
+    # data_start_date = (date - timedelta(days=3)).strftime("%Y-%m-%d")
+    # data_end_date = (date - timedelta(days=1)).strftime("%Y-%m-%d")
+    # validation_date = (date - timedelta(days=2)).strftime("%Y-%m-%d")
     # 验证集和测试集的日期必须相差一天，否则切割数据集时会报错
     test_date = data_end_date
     print("data_start_date,data_end_date,validation_date,test_date：")
@@ -50,7 +53,7 @@ def con_sql(sql):
 
 def move_file():
     import os
-    for eachFile in os.listdir("/data2/models/train"):
+    for eachFile in os.listdir(DIRECTORY_PATH+"train"):
         os.rename(DIRECTORY_PATH+"train" + "/" + eachFile,DIRECTORY_PATH + eachFile)
     print("成功将文件剪切到对应路径")