change test file

tensnsorflow/multi_hot.py

@@ -366,25 +366,28 @@ def doris():
     temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
     start = (temp - datetime.timedelta(days=3)).strftime("%Y-%m-%d")
     print(start)
-    sql = "select e.y,e.z,e.stat_date,e.ucity_id,doris.search_tag2,doris.search_tag3 " \
-          "from jerry_test.esmm_train_data_dwell e " \
-          "left join jerry_test.search_doris doris on e.device_id = doris.device_id " \
-          "and e.stat_date = doris.get_date " \
-          "where e.stat_date >= '{}'".format(start)
-
-    df = spark.sql(sql)
-    print(df.count())
-    sql = "select y,z,stat_date,ucity_id from jerry_test.esmm_train_data_dwell " \
-          "where stat_date >= '{}'".format(start)
-
-    df = spark.sql(sql)
-    print(df.count())
+    # sql = "select e.y,e.z,e.stat_date,e.ucity_id,doris.search_tag2,doris.search_tag3 " \
+    #       "from jerry_test.esmm_train_data_dwell e " \
+    #       "left join jerry_test.search_doris doris on e.device_id = doris.device_id " \
+    #       "and e.stat_date = doris.get_date " \
+    #       "where e.stat_date >= '{}'".format(start)
+    #
+    # df = spark.sql(sql)
+    # print(df.count())
+    # sql = "select y,z,stat_date,ucity_id from jerry_test.esmm_train_data_dwell " \
+    #       "where stat_date >= '{}'".format(start)
+    #
+    # df = spark.sql(sql)
+    # print(df.count())
 
     sql = "select e.y,e.z,e.label,e.ucity_id,doris.search_tag2,doris.search_tag3 " \
           "from jerry_test.esmm_pre_data e " \
           "left join jerry_test.search_doris doris on e.device_id = doris.device_id " \
-          "and e.stat_date = doris.get_date " \
-          "where doris.get_date = '{}'".format(validate_date)
+          "and e.stat_date = doris.get_date"
+    df = spark.sql(sql)
+    print(df.count())
+
+    sql = "select y,z from jerry_test.esmm_pre_data"
     df = spark.sql(sql)
     print(df.count())