修改特征工程里的训练集和预测集

eda/esmm/Model_pipline/feature_engineering.py

@@ -243,7 +243,7 @@ def feature_engineer():
 
     # TODO 上线后把下面train fliter 删除，因为最近一天的数据也要作为训练集
 
-    train = rdd.map(
+    train = rdd.filter(lambda x: x[0] != validate_date).map(
         lambda x: (x[1], x[2], x[3], x[4], x[5], x[6], x[7], x[8], x[9],
                    x[10], x[11], x[12], x[13], x[14], x[15],x[16],x[17],x[18]))
     f = time.time()
@@ -299,7 +299,8 @@ 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"
+          "left join jerry_test.search_doris doris on e.device_id = doris.device_id and e.stat_date = doris.get_date " \
+          "limit 200000"
 
     features = ["ucity_id", "ccity_name", "device_type", "manufacturer",
                 "channel", "top", "time", "hospital_id",