Merge branch 'master' of git.wanmeizhensuo.com:ML/ffm-baseline

修改模型训练参数num_epochs

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

@@ -756,7 +756,7 @@ object find_reason {
 
       val all_clk = sc.sql(
         s"""
-           |select '${stat_date}' as stat_date,ov.cl_id as device_id
+           |select ov.cl_id as device_id
            |from online.tl_hdfs_maidian_view ov left join agency_id
            |on ov.cl_id = agency_id.device_id
            |where ov.action = 'on_click_diary_card'
@@ -771,10 +771,9 @@ object find_reason {
       //1.当天老用户中的点击用户数
       val old_clk_count = sc.sql(
         s"""
-           |select '${stat_date}' as stat_date,count(oc.device_id) as old_clk_count
+           |select '${stat_date}' as stat_date,count(distinct(oc.device_id)) as old_clk_count
            |from all_clk_diary_card oc inner join device_id_old
            |on oc.device_id = device_id_old.device_id
-           |group by stat_date
        """.stripMargin
       )
       old_clk_count.show()
@@ -793,10 +792,9 @@ object find_reason {
       //2.当天新用户中的点击用户数
       val new_clk_count = sc.sql(
         s"""
-           |select '${stat_date}' as stat_date,count(oc.device_id) as new_clk_count
+           |select '${stat_date}' as stat_date,count(distinct(oc.device_id)) as new_clk_count
            |from all_clk_diary_card oc inner join device_id_new
            |on oc.device_id = device_id_new.device_id
-           |group by stat_date
        """.stripMargin
       )
 //2.1 有点击的新用户
@@ -815,8 +813,9 @@ object find_reason {
       val old_count = sc.sql(
         s"""
            |select '${stat_date}' as stat_date,count(distinct(dio.device_id)) as old_count
-           |from device_id_old dio inner join agency_id
+           |from device_id_old dio left join agency_id
            |on dio.device_id = agency_id.device_id
+           |where agency_id.device_id is null
        """.stripMargin
       )
 
@@ -824,8 +823,9 @@ object find_reason {
       val new_count = sc.sql(
         s"""
            |select '${stat_date}' as stat_date,count(distinct(din.device_id)) as new_count
-           |from device_id_new din inner join agency_id
+           |from device_id_new din left join agency_id
            |on din.device_id = agency_id.device_id
+           |where agency_id.device_id is null
        """.stripMargin
       )