change test file

tensnsorflow/multi_hot.py

@@ -157,7 +157,7 @@ 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=3)).strftime("%Y-%m-%d")
     print(start)
 
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC')
@@ -289,8 +289,7 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
           "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.knowledge k on feat.level2 = k.level2_id " \
-          "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(date)
+          "left join jerry_test.search_doris doris on e.device_id = doris.device_id and e.stat_date = doris.get_date"
 
     features = ["ucity_id", "ccity_name", "device_type", "manufacturer",
                 "channel", "top", "time", "hospital_id",
@@ -300,8 +299,6 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
 
     df = spark.sql(sql)
     df = df.drop_duplicates(["ucity_id", "device_id", "cid_id"])
-    print("pre")
-    print(df.count())
 
     df = df.na.fill(dict(zip(features, features)))
     f = time.time()
@@ -409,9 +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)
-    doris()
+    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)
+
 
     spark.stop()