change test file

tensnsorflow/multi_hot.py

@@ -358,6 +358,36 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
         .repartition(100).write.format("tfrecords").save(path=path + "test_nearby/", mode="overwrite")
     print("nearby tfrecord done")
 
+def doris():
+    db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    sql = "select max(stat_date) from esmm_train_data_dwell"
+    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=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.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)
+    df = spark.sql(sql)
+    print(df.count())
+
 
 if __name__ == '__main__':
     sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
@@ -376,8 +406,9 @@ if __name__ == '__main__':
     path = "hdfs:///strategy/esmm/"
     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)
+    # 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)
+    doris()
 
     spark.stop()