增加特征

eda/esmm/Model_pipline/feature.py

@@ -37,7 +37,7 @@ def get_data():
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
     sql = "select e.y,e.z,e.stat_date,e.ucity_id,feat.level2_ids,e.ccity_name,u.device_type,u.manufacturer," \
           "u.channel,c.top,e.device_id,cut.time,dl.app_list,e.diary_service_id,feat.level3_ids,feat.level2," \
-          "wiki.tag,question.tag,search.tag,budan.tag,order.tag,sixin.tag,cart.tag " \
+          "wiki.tag,question.tag,search.tag,budan.tag " \
           "from {} e left join user_feature u on e.device_id = u.device_id " \
           "left join cid_type_top c on e.device_id = c.device_id " \
           "left join cid_time_cut cut on e.cid_id = cut.cid " \
@@ -47,11 +47,13 @@ def get_data():
           "left join question_tag question on e.device_id = question.device_id " \
           "left join search_tag search on e.device_id = search.device_id " \
           "left join budan_tag budan on e.device_id = budan.device_id " \
-          "left join order_tag order on e.device_id = order.device_id " \
-          "left join sixin_tag sixin on e.device_id = sixin.device_id " \
-          "left join cart_tag cart on e.device_id = cart.device_id " \
           "where e.stat_date >= '{}'".format(train_data_set, start)
 
+    # , order.tag, sixin.tag, cart.tag
+    # "left join order_tag order on e.device_id = order.device_id " \
+    # "left join sixin_tag sixin on e.device_id = sixin.device_id " \
+    # "left join cart_tag cart on e.device_id = cart.device_id "
+
     df = con_sql(db, sql)
     # print(df.shape)
     df = df.rename(columns={0: "y", 1: "z", 2: "stat_date", 3: "ucity_id", 4: "clevel2_id", 5: "ccity_name",