change preidct and training argument

diaryTraining.py

@@ -9,8 +9,8 @@ def train():
     ffm_model = xl.create_ffm()
     ffm_model.setTrain(DIRECTORY_PATH + "train{0}-{1}.csv".format(DATA_START_DATE, VALIDATION_DATE))
     ffm_model.setValidate(DIRECTORY_PATH + "validation{0}.csv".format(VALIDATION_DATE))
-
-    param = {'task': 'binary', 'lr': lr, 'lambda': l2_lambda, 'metric': 'auc'}
+    # 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"}
 
     ffm_model.fit(param, DIRECTORY_PATH + "model_lr{}_lambda{}.out".format(lr, l2_lambda))
 

predictDiary.py

@@ -52,7 +52,9 @@ def predict(user_profile):
     ffm_model = xl.create_ffm()
     ffm_model.setTest(instance_file_path)
     ffm_model.setSigmoid()
-    ffm_model.predict(DIRECTORY_PATH + "model_lr{}_lambda{}.out".format(lr, l2_lambda),
+    #日志保存路径，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 = {"log": "/data2/models/result"}
+    ffm_model.predict(param,DIRECTORY_PATH + "model_lr{}_lambda{}.out".format(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)

processData.py

@@ -77,7 +77,7 @@ 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=6)
+    data = ffm_train.fit_transform(data, y='y',n=50000,processes=5)
     with open(DIRECTORY_PATH+"ffm_{0}_{1}.pkl".format(DATA_START_DATE,DATA_END_DATE), "wb") as f:
         pickle.dump(ffm_train, f)