change test fliw

eda/esmm/Model_pipline/feature_engineering.py

@@ -139,7 +139,7 @@ def feature_engineer():
     validate_date = con_sql(db, sql)[0].values.tolist()[0]
     print("validate_date:" + validate_date)
     temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
-    start = (temp - datetime.timedelta(days=100)).strftime("%Y-%m-%d")
+    start = (temp - datetime.timedelta(days=6)).strftime("%Y-%m-%d")
     print(start)
 
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC')
@@ -337,7 +337,7 @@ if __name__ == '__main__':
     local_path = "/home/gmuser/esmm/"
 
     validate_date, value_map, app_list_map, leve2_map, leve3_map = feature_engineer()
-    get_predict(validate_date, value_map, app_list_map, leve2_map, leve3_map)
+    # get_predict(validate_date, value_map, app_list_map, leve2_map, leve3_map)
 
     spark.stop()
 

eda/esmm/Model_pipline/train.py

@@ -348,19 +348,19 @@ def main(_):
     elif FLAGS.task_type == 'export':
         print("Not Implemented, Do It Yourself!")
 
-def get_filename(dir_in):
-    pre_path = "hdfs://172.16.32.4:8020"
-    args = "hdfs dfs -ls " + dir_in + " | awk '{print $8}'"
-    proc = subprocess.Popen(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
-    s_output, s_err = proc.communicate()
-    all_dart_dirs = s_output.split()
-    a = []
-    for i in all_dart_dirs:
-        b = str(i).split("/")[4]
-        if b[:4] == "part":
-            tmp = pre_path + str(i)[2:-1]
-            a.append(tmp)
-    return a
+# def get_filename(dir_in):
+#     pre_path = "hdfs://172.16.32.4:8020"
+#     args = "hdfs dfs -ls " + dir_in + " | awk '{print $8}'"
+#     proc = subprocess.Popen(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
+#     s_output, s_err = proc.communicate()
+#     all_dart_dirs = s_output.split()
+#     a = []
+#     for i in all_dart_dirs:
+#         b = str(i).split("/")[4]
+#         if b[:4] == "part":
+#             tmp = pre_path + str(i)[2:-1]
+#             a.append(tmp)
+#     return a
 
 if __name__ == "__main__":
     b = time.time()