change test file

tensnsorflow/feature_engineering.py

@@ -182,7 +182,6 @@ def feature_engineer():
           "where e.stat_date >= '{}'".format(start)
 
     df = spark.sql(sql)
-    df.show(2)
 
     df = df.drop_duplicates(["ucity_id", "level2_ids", "ccity_name", "device_type", "manufacturer",
                              "channel", "top", "time", "stat_date", "app_list", "hospital_id", "level3_ids",
@@ -256,9 +255,8 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
           "left join jerry_test.order_tag ot on e.device_id = ot.device_id " \
           "left join jerry_test.sixin_tag sixin on e.device_id = sixin.device_id " \
           "left join jerry_test.cart_tag cart on e.device_id = cart.device_id " \
-          "left join jerry_test.train_Knowledge_network_data k on feat.level2 = k.level2_id " \
-          "limit 5000"
-# TODO 把上面的limit 5000删除
+          "left join jerry_test.train_Knowledge_network_data k on feat.level2 = k.level2_id"
+
     features = ["ucity_id", "ccity_name", "device_type", "manufacturer",
                 "channel", "top", "time", "hospital_id",
                 "treatment_method", "price_min", "price_max", "treatment_time", "maintain_time", "recover_time"]

tensnsorflow/train_multi.py

@@ -375,7 +375,6 @@ def get_filename(dir_in):
     proc = subprocess.Popen(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
     s_output, s_err = proc.communicate()
     all_dart_dirs = s_output.split()
-    print(all_dart_dirs)
     a = []
     for i in all_dart_dirs:
         b = str(i).split("/")[4]