Commit 838c47ab authored by 王志伟's avatar 王志伟

新统计

parent 3ca23564
......@@ -48,36 +48,34 @@ object testt {
//机构id
val agency_id = sc.sql(
s"""
|SELECT DISTINCT(cl_id) as device_id
|FROM online.ml_hospital_spam_pv_day
|WHERE partition_date >= '20180402'
|AND partition_date <= '20181203'
|AND pv_ratio >= 0.95
|UNION ALL
|SELECT DISTINCT(cl_id) as device_id
|FROM online.ml_hospital_spam_pv_month
|WHERE partition_date >= '20171101'
|AND partition_date <= '20181203'
|AND pv_ratio >= 0.95
""".stripMargin
)
// agency_id.show()
agency_id.createOrReplaceTempView("agency_id")
// val agency_id = sc.sql(
// s"""
// |SELECT DISTINCT(cl_id) as device_id
// |FROM online.ml_hospital_spam_pv_day
// |WHERE partition_date >= '20180402'
// |AND partition_date <= '20181203'
// |AND pv_ratio >= 0.95
// |UNION ALL
// |SELECT DISTINCT(cl_id) as device_id
// |FROM online.ml_hospital_spam_pv_month
// |WHERE partition_date >= '20171101'
// |AND partition_date <= '20181203'
// |AND pv_ratio >= 0.95
// """.stripMargin
// )
//// agency_id.show()
// agency_id.createOrReplaceTempView("agency_id")
val diary_pv = sc.sql(
s"""
|select ov.partition_date, count(params["business_id"]) as diary_pv
|from online.tl_hdfs_maidian_view ov left join agency_id
|on ov.cl_id = agency_id.device_id
|where ov.action="page_view"
|and ov.params["page_name"]="diary_detail"
|and (ov.params["out"]-ov.params["in"])<7200
|and agency_id.device_id is null
|and ov.partition_date >='20181120'
|and ov.cl_id not in (select distinct(device_id) from blacklist)
|group by ov.partition_date order by ov.partition_date
|select partition_date,count(cl_id)
|from online.tl_hdfs_maidian_view
|where action="page_view"
|and params["page_name"]="diary_detail"
|and params["referrer"]='my_diary'
|and partition_date >='20181120'
|GROUP BY partition_date
|order by partition_date
""".stripMargin
)
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