Skip to content

F
ffm-baseline
Commit 838c47ab authored by 王志伟's avatar 王志伟
Browse files
Options

新统计

parent 3ca23564
Hide whitespace changes
Inline Side-by-side
Showing with 25 additions and 27 deletions
eda/feededa/src/main/scala/com/gmei/testt.scala
View file @ 838c47ab
...@@ -48,36 +48,34 @@ object testt { ...@@ -48,36 +48,34 @@ object testt {
//机构id //机构id
val agency_id = sc.sql( // val agency_id = sc.sql(
s""" // s"""
|SELECT DISTINCT(cl_id) as device_id // |SELECT DISTINCT(cl_id) as device_id
|FROM online.ml_hospital_spam_pv_day // |FROM online.ml_hospital_spam_pv_day
|WHERE partition_date >= '20180402' // |WHERE partition_date >= '20180402'
|AND partition_date <= '20181203' // |AND partition_date <= '20181203'
|AND pv_ratio >= 0.95 // |AND pv_ratio >= 0.95
|UNION ALL // |UNION ALL
|SELECT DISTINCT(cl_id) as device_id // |SELECT DISTINCT(cl_id) as device_id
|FROM online.ml_hospital_spam_pv_month // |FROM online.ml_hospital_spam_pv_month
|WHERE partition_date >= '20171101' // |WHERE partition_date >= '20171101'
|AND partition_date <= '20181203' // |AND partition_date <= '20181203'
|AND pv_ratio >= 0.95 // |AND pv_ratio >= 0.95
""".stripMargin // """.stripMargin
) // )
// agency_id.show() //// agency_id.show()
agency_id.createOrReplaceTempView("agency_id") // agency_id.createOrReplaceTempView("agency_id")
val diary_pv = sc.sql( val diary_pv = sc.sql(
s""" s"""
|select ov.partition_date, count(params["business_id"]) as diary_pv |select partition_date,count(cl_id)
|from online.tl_hdfs_maidian_view ov left join agency_id |from online.tl_hdfs_maidian_view
|on ov.cl_id = agency_id.device_id |where action="page_view"
|where ov.action="page_view" |and params["page_name"]="diary_detail"
|and ov.params["page_name"]="diary_detail" |and params["referrer"]='my_diary'
|and (ov.params["out"]-ov.params["in"])<7200 |and partition_date >='20181120'
|and agency_id.device_id is null |GROUP BY partition_date
|and ov.partition_date >='20181120' |order by partition_date
|and ov.cl_id not in (select distinct(device_id) from blacklist)
|group by ov.partition_date order by ov.partition_date
""".stripMargin """.stripMargin
) )
diary_pv.show() diary_pv.show()
......
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