修改配置文件文件路径

dataProcess.py

@@ -69,7 +69,7 @@ def ffm_transform(data, test_number, validation_number):
     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=4)
+    data = ffm_train.fit_transform(data, y='y',n=50000,processes=8)
     with open(DIRECTORY_PATH+"train/ffm.pkl", "wb") as f:
         pickle.dump(ffm_train, f)
 

diaryTraining.py

@@ -8,7 +8,7 @@ def train():
     ffm_model.setTrain(DIRECTORY_PATH + "train_ffm_data.csv")
     ffm_model.setValidate(DIRECTORY_PATH + "validation_ffm_data.csv")
     # log保存路径，如果不加这个参数，日志默认保存在/temp路径下，不符合规范
-    param = {'task': 'binary', 'lr': lr, 'lambda': l2_lambda, 'metric': 'auc',"log":"/data2/models/result"}
+    param = {'task': 'binary', 'lr': lr, 'lambda': l2_lambda, 'metric': 'auc',"log":DIRECTORY_PATH+"result"}
 
     ffm_model.fit(param, DIRECTORY_PATH + "train/model.out")
 

train.py

@@ -17,9 +17,9 @@ if __name__ == "__main__":
     train()
     end_train = time.time()
     print("训练模型耗时{}分".format((end_train-start_train)/60))
-    # move_file()
+    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

@@ -9,6 +9,7 @@ from sklearn.metrics import auc
 from multiprocessing import Pool
 import os
 import signal
+from config import *
 
 
 def get_date():
@@ -50,7 +51,7 @@ def con_sql(sql):
 def move_file():
     import os
     for eachFile in os.listdir("/data2/models/train"):
-        os.rename("/data2/models/train" + "/" + eachFile,"/data2/models/" + eachFile)
+        os.rename(DIRECTORY_PATH+"train" + "/" + eachFile,DIRECTORY_PATH + eachFile)
     print("成功将文件剪切到对应路径")