esmm 测试项目增加知识图谱特征

eda/feededa/src/main/scala/com/gmei/EsmmData.scala

@@ -688,10 +688,14 @@ object GetDiaryPortrait {
 //      diary_tag.show()
 //      println(diary_tag.count())
       diary_tag.createOrReplaceTempView("t")
-      val result = 
+      val result = sc.sql(
+        s"""
+           |select diary_id,level1_ids,level2_ids,level3_ids,split(level2_ids,",")[0] as level2 from t
+         """.stripMargin
+      )
       val jdbc = "jdbc:mysql://10.66.157.22:4000/jerry_test?user=root&password=3SYz54LS9#^9sBvC&rewriteBatchedStatements=true"
 
-      GmeiConfig.writeToJDBCTable(jdbc,diary_tag,"diary_feat",SaveMode.Overwrite)
+      GmeiConfig.writeToJDBCTable(jdbc,result,"pre_test",SaveMode.Overwrite)
 
 
       sc.stop()

tensnsorflow/es/feature.py

@@ -42,13 +42,11 @@ def get_data():
     db = pymysql.connect(host='10.66.157.22', 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," \
-          "k.treatment_method,k.price_min,k.price_max,k.treatment_time,k.maintain_time,k.recover_time " \
           "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 " \
           "left join device_app_list dl on e.device_id = dl.device_id " \
           "left join diary_feat feat on e.cid_id = feat.diary_id " \
-          "left join train_Knowledge_network_data k on SUBSTRING_INDEX(feat.level2_ids,",",1) = k.level2_id " \
           "where e.stat_date >= '{}'".format(train_data_set,start)
     df = con_sql(db, sql)
     # print(df.shape)
@@ -58,7 +56,7 @@ def get_data():
                             15:"method",16:"min",17:"max",18:"treatment_time",19:"maintain_time",20:"recover_time"})
     print("esmm data ok")
 
-    print(df[["method","min","max","treatment_time","maintain_time","recover_time"]].head(6))
+    # print(df["method","min","max","treatment_time","maintain_time","recover_time"].head(6))
     print(df.count(axis = 1))
 
     service_id = tuple(df["service_id"].unique())