Skip to content

F
ffm-baseline
Commit e249d07a authored by 王志伟's avatar 王志伟
Browse files
Options

更改action

parent 596782ff
Show whitespace changes
Inline Side-by-side
Showing with 8 additions and 113 deletions
eda/feededa/src/main/scala/com/gmei/Search_keywords_count.scala
View file @ e249d07a
......@@ -50,7 +50,7 @@ object Search_keywords_count {
s"""
|select params['query'] as search_keywords
|from online.tl_hdfs_maidian_view
|where action = 'search_result_click_search'
|where action = 'do_search'
|and partition_date ='${partition_date}'
""".stripMargin
)
......@@ -59,7 +59,7 @@ object Search_keywords_count {
s"""
|select '${stat_date}' as stat_date,count(params['query']) as search_num
|from online.tl_hdfs_maidian_view
|where action = 'search_result_click_search'
|where action = 'do_search'
|and partition_date ='${partition_date}'
""".stripMargin
)
......
eda/feededa/src/main/scala/com/gmei/strategy_other.scala
View file @ e249d07a
......@@ -187,7 +187,7 @@ object strategy_other {
//使用信息熵描述推荐系统对长尾优质物品(日记本)的挖掘能力
//使用基尼系数描述推荐系统对日记本推荐是否具有马太效应
object evaluation_indicator_ {
object evaluation_indicator {
Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
......@@ -226,121 +226,16 @@ object evaluation_indicator_ {
//val stat_date = GmeiConfig.getMinusNDate(1)
//println(param.date)
val partition_date = param.date.replace("-","")
val devicee_id_oldUser = sc.sql(
val diary_id = sc.sql(
s"""
|select distinct(device_id) as device_id
|from online.ml_device_day_active_status
|where active_type = '4'
|and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
| ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
| ,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
| ,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
| ,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
| ,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
| ,'promotion_shike','promotion_julang_jl03')
|and partition_date ='${partition_date}'
|select native_queue as diary_id
|from doris_prod.device_diary_queue
""".stripMargin
)
devicee_id_oldUser.show()
devicee_id_oldUser.createOrReplaceTempView("device_id_old")
diary_id.show()
//device_id尾号1有点击用户日记本点击数
val clk_active_1 = sc.sql(
s"""
|select '${param.date}' as stat_date, count(jd.cid_id) as clk_active_1
|from data_feed_click jd inner join device_id_old
|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$$'
|and jd.device_id not in (select device_id from bl_device_list)
|and jd.device_id not in (select device_id from blacklist)
|and jd.stat_date ='${param.date}'
""".stripMargin
)
//device_id尾号1有点击用户日记本曝光数
val imp_active_1 = sc.sql(
s"""
|select '${param.date}' as stat_date, count(je.cid_id) as imp_active_1
|from data_feed_exposure je inner join device_id_old
|on je.device_id = device_id_old.device_id
|where je.cid_type = 'diary'
|and je.device_id in (select distinct(device_id) from data_feed_click where device_id regexp '1$$' and stat_date = '${param.date}')
|and je.device_id not in (select device_id from bl_device_list)
|and je.device_id not in (select device_id from blacklist)
|and je.stat_date ='${param.date}'
""".stripMargin
)
//device_id尾号1点击日记本用户数
val clk_diary_device = sc.sql(
s"""
|select '${param.date}' as stat_date, count(distinct(jd.device_id)) as clk_diary_device
|from data_feed_click jd inner join device_id_old
|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)
|and jd.device_id not in (select device_id from blacklist)
|and jd.stat_date ='${param.date}'
""".stripMargin
)
//所有有点击用户日记本点击数
val clk_active_all = sc.sql(
s"""
|select '${param.date}' as stat_date, count(jd.cid_id) as clk_active_all
|from data_feed_click jd inner join device_id_old
|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)
|and jd.stat_date ='${param.date}'
""".stripMargin
)
//所有有点击用户日记本曝光数
val imp_active_all = sc.sql(
s"""
|select '${param.date}' as stat_date, count(je.cid_id) as imp_active_all
|from data_feed_exposure je inner join device_id_old
|on je.device_id = device_id_old.device_id
|where je.cid_type = 'diary'
|and je.device_id in (select distinct(device_id) from data_feed_click where stat_date = '${param.date}')
|and je.device_id not in (select device_id from bl_device_list)
|and je.device_id not in (select device_id from blacklist)
|and je.stat_date ='${param.date}'
""".stripMargin
)
//策略命中用户点击日记本用户数
val clk_diary_device_cover = sc.sql(
s"""
|select '${param.date}' as stat_date,count(distinct(device_id)) as clk_diary_device_cover
|from merge_queue_table
|where device_id in (select distinct(device_id) from data_feed_click where stat_date = '${param.date}')
""".stripMargin
)
//策略命中用户总数
val device_all_cover = sc.sql(
s"""
|select '${param.date}' as stat_date,count(distinct(device_id)) as device_all_cover
|from merge_queue_table
""".stripMargin
)
val result = clk_active_1.join(imp_active_1,"stat_date")
.join(clk_active_all,"stat_date")
.join(imp_active_all,"stat_date")
.join(clk_diary_device,"stat_date")
.join(clk_diary_device_cover,"stat_date")
.join(device_all_cover,"stat_date")
result.show()
GmeiConfig.writeToJDBCTable(result, "strategy_other", SaveMode.Append)
GmeiConfig.writeToJDBCTable(diary_id, "dairy_id_queue", SaveMode.Append)
}
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment