Commit 482e0d33 authored by 王志伟's avatar 王志伟

统计发现页面的点击率

parent 1189a028
......@@ -782,25 +782,39 @@ object question_count {
//println(param.date)
val partition_date = stat_date.replace("-","")
val question_id=List(212264,212266,212272,212281,212287,212436,212439,212437,212505,212506,212507,212522,212523,212526,212532,212783,212787,212789,212793,212796,213202,213199,213216,213219,213297,213224,213226,213239,213300,213302,213316,213307,213308,213370,213377,213349,213358,213368,213392,213393,213435,213453,213445,213448,213458,213466,213471,213478,213485,213638,213642,213644,213727,213729,213775,213776,213810,213817,213805,213821,213884,213885,213892,213834,213879,214043,214050,214062,214055,214056,214058,214064,214159,214182,214149,214184,214190,214206,214227,214243,214242,214288,214289,214293,214295,214541,214544,214546,214614,214618,214619,214620,214682,214683,214684,214848,214850,214854,214856,214857,214903,214908,214913,214918,214919,214980,214981,214988,214985,215031,215034,215036,215039,215094,215098,215104,215107,215112,215222,215225,215233,215237,215265,215366,215347,215346,215343)
for( a <- question_id ){
val agency_id = sc.sql(
s"""
|SELECT partition_date,count(cl_id)
|FROM online.tl_hdfs_maidian_view
|WHERE partition_date >= '20190101'
|and action='community_home_click_feed_card'
|and params["card_type"]="问题"
|and params['business_id']='212264'
|group by partition_date
|order by partition_date
""".stripMargin
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 <= '20190117'
|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 <= '20190117'
|AND pv_ratio >= 0.95
""".stripMargin
)
println("question_id:",a)
agency_id.show(20)
}
val question_count = sc.sql(
s"""
|SELECT partition_date,count(cl_id)
|FROM online.tl_hdfs_maidian_view ov inner join agency_id
|on ov.cl_id = agency_id.device_id
|WHERE ov.partition_date >= '20190101'
|and ov.action='community_home_click_feed_card'
|and ov.params["card_type"]="问题"
|and ov.cl_id not in (select device_id from blacklist)
|GROUP BY ov.partition_date
|order by ov.partition_date
""".stripMargin
)
question_count.show(30)
}
......
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