Merge branch 'zhao' into 'master'

把esmm 预测后的日记队列数量由500改成1000

See merge request !30

eda/esmm/Model_pipline/feature_engineering.py

@@ -389,10 +389,3 @@ if __name__ == '__main__':
     get_predict(validate_date, value_map, app_list_map, leve2_map, leve3_map)
 
     spark.stop()
-
-
-
-
-
-
-

eda/esmm/Model_pipline/train.py

@@ -378,7 +378,7 @@ def trans(x):
 def set_join(lst):
     l = lst.unique().tolist()
     r = [str(i) for i in l]
-    r =r[:500]
+    r =r[:1000]
     return ','.join(r)
 
 def df_sort(result,queue_name):

train.py

-from dataProcess import *
-from diaryTraining import *
-import time
-from utils import *
-
-
-# 把数据获取、特征转换、模型训练的模型串联在一起
-if __name__ == "__main__":
-    # while True:
-    #     now = datetime.now()
-    #     if (now.hour == 23) and (now.minute == 30):
-    start_train = time.time()
-    data_start_date, data_end_date, validation_date, test_date = get_date()
-    data, test_number, validation_number = feature_en(data_start_date, data_end_date,
-                                                      validation_date,test_date)
-    ffm_transform(data, test_number, validation_number)
-    train()
-    end_train = time.time()
-    print("训练模型耗时{}分".format((end_train-start_train)/60))
-    move_file()
-
-
-
-
-
-
-
-
-