esmm pre data on activate user

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

@@ -55,7 +55,7 @@ object Recommendation_strategy_all {
       val partition_date = stat_date.replace("-","")
       val decive_id_oldUser = sc.sql(
         s"""
-           |select distinct(device_id) as decive_id
+           |select distinct(device_id) as device_id
            |from online.ml_device_day_active_status
            |where active_type = '4'
            |and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
@@ -75,7 +75,7 @@ object Recommendation_strategy_all {
         s"""
            |select '${stat_date}' as stat_date, count(cid_id) as clk_count_oldUser_Contrast
            |from data_feed_click jd inner join device_id_old
-           |on jd.device_id = device_id_old.decive_id
+           |on jd.device_id = device_id_old.device_id
            |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
            |and jd.device_id regexp'1$$'
            |and jd.device_id not in (select device_id from bl_device_list)
@@ -88,7 +88,7 @@ object Recommendation_strategy_all {
         s"""
            |select '${stat_date}' as stat_date, count(cid_id) as imp_count_oldUser_Contrast
            |from data_feed_exposure je inner join device_id_old
-           |on je.device_id = device_id_old.decive_id
+           |on je.device_id = device_id_old.device_id
            |where je.cid_type = 'diary'
            |and je.device_id regexp'1$$'
            |and je.device_id not in (select device_id from bl_device_list)
@@ -101,7 +101,7 @@ object Recommendation_strategy_all {
         s"""
            |select '${stat_date}' as stat_date, count(cid_id) as clk_count_oldUser_all
            |from data_feed_click jd inner join device_id_old
-           |on jd.device_id = device_id_old.decive_id
+           |on jd.device_id = device_id_old.device_id
            |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
            |and jd.device_id not in (select device_id from bl_device_list)
            |and jd.device_id not in (select device_id from blacklist)
@@ -113,7 +113,7 @@ object Recommendation_strategy_all {
         s"""
            |select '${stat_date}' as stat_date, count(cid_id) as imp_count_oldUser_all
            |from data_feed_exposure je inner join device_id_old
-           |on je.device_id = device_id_old.decive_id
+           |on je.device_id = device_id_old.device_id
            |where je.cid_type = 'diary'
            |and je.device_id not in (select device_id from bl_device_list)
            |and je.device_id not in (select device_id from blacklist)
@@ -167,7 +167,7 @@ object Recommendation_strategy_all {
         s"""
            |select '${stat_date}' as stat_date, count(distinct(je.device_id)) as device_num_1_hit
            |from data_feed_exposure je inner join device_id_old
-           |on je.device_id = device_id_old.decive_id
+           |on je.device_id = device_id_old.device_id
            |where je.cid_type = 'diary'
            |and je.device_id regexp'1$$'
            |and je.device_id not in (select device_id from bl_device_list)
@@ -298,10 +298,6 @@ object Recommendation_strategy_all {
       GmeiConfig.writeToJDBCTable(result2, "strategy_other", SaveMode.Append)
 
 
-
-
-
-
 //统计新用户点击率
       val devicee_id_newUser = sc.sql(
         s"""

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

@@ -279,8 +279,6 @@ object diary_exposure {
       val final_cid_city = diary_id_temp.join(df_cid_city,Seq("diary_id"),"left_outer")
       final_cid_city.show()
       val df1=final_cid_city.groupBy("name").count().orderBy(desc("count"))
-      df1.show(400)
-
 
 //3.5星以上日记本的id
       val diary_id_temp2 = sc.sql(
@@ -315,7 +313,6 @@ object diary_exposure {
       val final_cid_city2 = diary_id_temp2.join(df_cid_city2,Seq("diary_id"),"left_outer")
       final_cid_city2.show()
       val df2 =final_cid_city2.groupBy("name").count().orderBy(desc("count"))
-      df2.show(400)
 
       val df3 =df1.join(df2,Seq("name"),"left_outer")
       df3.show(400)