Skip to content
Projects
Groups
Snippets
Help
Loading...
Sign in
Toggle navigation
F
ffm-baseline
Project
Project
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
ML
ffm-baseline
Commits
0671e724
Commit
0671e724
authored
Apr 12, 2019
by
王志伟
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
查找无点击老用户
parent
26fc2796
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
77 additions
and
64 deletions
+77
-64
temp_count.scala
eda/feededa/src/main/scala/com/gmei/temp_count.scala
+77
-64
No files found.
eda/feededa/src/main/scala/com/gmei/temp_count.scala
View file @
0671e724
...
...
@@ -901,76 +901,89 @@ object find_reason {
old_clk_device
.
createOrReplaceTempView
(
"old_clk_device"
)
//2.当天新用户中的点击用户数
val
new_clk_count
=
sc
.
sql
(
//1.1无点击的老用户
val
old_noclk_device
=
sc
.
sql
(
s
"""
|select '${stat_date}' as stat_date,count(distinct(oc.device_id)) as new_clk_count
|from all_clk_diary_card oc inner join device_id_new
|on oc.device_id = device_id_new.device_id
|select device_id
|from device_id_old
|except
|select device_id
|from old_clk_device
"""
.
stripMargin
)
//2.1 有点击的新用户
val
new_clk_device
=
sc
.
sql
(
s
"""
|select distinct(oc.device_id) as device_id
|from all_clk_diary_card oc inner join device_id_new
|on oc.device_id = device_id_new.device_id
"""
.
stripMargin
)
new_clk_device
.
createOrReplaceTempView
(
"new_clk_device"
)
old_noclk_device
.
show
()
//3.当天老用户数
val
old_count
=
sc
.
sql
(
s
"""
|select '${stat_date}' as stat_date,count(distinct(dio.device_id)) as old_count
|from device_id_old dio left join agency_id
|on dio.device_id = agency_id.device_id
|where agency_id.device_id is null
"""
.
stripMargin
)
//4.当天新用户数
val
new_count
=
sc
.
sql
(
s
"""
|select '${stat_date}' as stat_date,count(distinct(din.device_id)) as new_count
|from device_id_new din left join agency_id
|on din.device_id = agency_id.device_id
|where agency_id.device_id is null
"""
.
stripMargin
)
//5.有点击老用户的曝光数
val
exp_clkold_count
=
sc
.
sql
(
s
"""
|select '${stat_date}' as stat_date,count(dp.device_id) as imp_clkold_count
|from data_feed_exposure_precise dp inner join old_clk_device
|on dp.device_id = old_clk_device.device_id
|where stat_date='${stat_date}'
|group by stat_date
"""
.
stripMargin
)
//6.有点击新用户的曝光数
val
exp_clknew_count
=
sc
.
sql
(
s
"""
|select '${stat_date}' as stat_date,count(dp.device_id) as imp_clknew_count
|from data_feed_exposure_precise dp inner join new_clk_device
|on dp.device_id = new_clk_device.device_id
|where stat_date='${stat_date}'
|group by stat_date
"""
.
stripMargin
)
val
result
=
old_clk_count
.
join
(
new_clk_count
,
"stat_date"
)
.
join
(
old_count
,
"stat_date"
)
.
join
(
new_count
,
"stat_date"
)
.
join
(
exp_clkold_count
,
"stat_date"
)
.
join
(
exp_clknew_count
,
"stat_date"
)
GmeiConfig
.
writeToJDBCTable
(
result
,
"device_clk_imp_reason"
,
SaveMode
.
Append
)
//2.当天新用户中的点击用户数
// val new_clk_count = sc.sql(
// s"""
// |select '${stat_date}' as stat_date,count(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
// """.stripMargin
// )
////2.1 有点击的新用户
// val new_clk_device = sc.sql(
// s"""
// |select distinct(oc.device_id) as device_id
// |from all_clk_diary_card oc inner join device_id_new
// |on oc.device_id = device_id_new.device_id
// """.stripMargin
// )
// new_clk_device.createOrReplaceTempView("new_clk_device")
//
//
// //3.当天老用户数
//
// val old_count = sc.sql(
// s"""
// |select '${stat_date}' as stat_date,count(distinct(dio.device_id)) as old_count
// |from device_id_old dio left join agency_id
// |on dio.device_id = agency_id.device_id
// |where agency_id.device_id is null
// """.stripMargin
// )
//
// //4.当天新用户数
// val new_count = sc.sql(
// s"""
// |select '${stat_date}' as stat_date,count(distinct(din.device_id)) as new_count
// |from device_id_new din left join agency_id
// |on din.device_id = agency_id.device_id
// |where agency_id.device_id is null
// """.stripMargin
// )
//
// //5.有点击老用户的曝光数
// val exp_clkold_count = sc.sql(
// s"""
// |select '${stat_date}' as stat_date,count(dp.device_id) as imp_clkold_count
// |from data_feed_exposure_precise dp inner join old_clk_device
// |on dp.device_id = old_clk_device.device_id
// |where stat_date='${stat_date}'
// |group by stat_date
// """.stripMargin
// )
//
// //6.有点击新用户的曝光数
// val exp_clknew_count = sc.sql(
// s"""
// |select '${stat_date}' as stat_date,count(dp.device_id) as imp_clknew_count
// |from data_feed_exposure_precise dp inner join new_clk_device
// |on dp.device_id = new_clk_device.device_id
// |where stat_date='${stat_date}'
// |group by stat_date
// """.stripMargin
// )
//
// val result = old_clk_count.join(new_clk_count,"stat_date")
// .join(old_count,"stat_date")
// .join(new_count,"stat_date")
// .join(exp_clkold_count,"stat_date")
// .join(exp_clknew_count,"stat_date")
//
// GmeiConfig.writeToJDBCTable(result, "device_clk_imp_reason", SaveMode.Append)
}
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment