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
c497c73b
Commit
c497c73b
authored
Nov 27, 2018
by
王志伟
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
将统计合并为1个文件
parent
e249d07a
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
107 additions
and
6 deletions
+107
-6
Recommendation_strategy_all.scala
...src/main/scala/com/gmei/Recommendation_strategy_all.scala
+104
-3
strategy_other.scala
eda/feededa/src/main/scala/com/gmei/strategy_other.scala
+3
-3
No files found.
eda/feededa/src/main/scala/com/gmei/Recommendation_strategy_all.scala
View file @
c497c73b
...
...
@@ -158,14 +158,115 @@ object Recommendation_strategy_all {
val
result
=
clk_count_oldUser_Contrast
.
join
(
imp_count_oldUser_Contrast
,
"stat_date"
)
val
result
1
=
clk_count_oldUser_Contrast
.
join
(
imp_count_oldUser_Contrast
,
"stat_date"
)
.
join
(
clk_count_oldUser_all
,
"stat_date"
)
.
join
(
imp_count_oldUser_all
,
"stat_date"
)
.
join
(
clk_count_oldUser_Cover
,
"stat_date"
)
.
join
(
imp_count_oldUser_Cover
,
"stat_date"
)
result
.
show
()
result1
.
show
()
GmeiConfig
.
writeToJDBCTable
(
result1
,
"Recommendation_strategy_temp"
,
SaveMode
.
Append
)
//device_id尾号1有点击用户日记本点击数
val
clk_active_1
=
sc
.
sql
(
s
"""
|select '${stat_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$$'
|and jd.device_id not in (select device_id from bl_device_list)
|and jd.device_id not in (select device_id from blacklist)
|and jd.stat_date ='${stat_date}'
"""
.
stripMargin
)
//device_id尾号1有点击用户日记本曝光数
val
imp_active_1
=
sc
.
sql
(
s
"""
|select '${stat_date}' as stat_date, count(je.cid_id) as imp_active_1
|from data_feed_exposure je inner join device_id_old
|on je.device_id = device_id_old.device_id
|where je.cid_type = 'diary'
|and je.device_id in (select distinct(device_id) from data_feed_click where device_id regexp '1$$' and stat_date = '${param.date}')
|and je.device_id not in (select device_id from bl_device_list)
|and je.device_id not in (select device_id from blacklist)
|and je.stat_date ='${stat_date}'
"""
.
stripMargin
)
//device_id尾号1点击日记本用户数
val
clk_diary_device
=
sc
.
sql
(
s
"""
|select '${stat_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 ='${stat_date}'
"""
.
stripMargin
)
//所有有点击用户日记本点击数
val
clk_active_all
=
sc
.
sql
(
s
"""
|select '${stat_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 ='${stat_date}'
"""
.
stripMargin
)
//所有有点击用户日记本曝光数
val
imp_active_all
=
sc
.
sql
(
s
"""
|select '${stat_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 = '${stat_date}')
|and je.device_id not in (select device_id from bl_device_list)
|and je.device_id not in (select device_id from blacklist)
|and je.stat_date ='${stat_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 '${stat_date}' as stat_date,count(distinct(device_id)) as clk_diary_device_cover
|from merge_queue_table
|where device_id in (select distinct(device_id) from data_feed_click where stat_date = '${stat_date}')
"""
.
stripMargin
)
//策略命中用户总数
val
device_all_cover
=
sc
.
sql
(
s
"""
|select '${stat_date}' as stat_date,count(distinct(device_id)) as device_all_cover
|from merge_queue_table
"""
.
stripMargin
)
val
result2
=
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"
)
result2
.
show
()
GmeiConfig
.
writeToJDBCTable
(
result2
,
"strategy_other"
,
SaveMode
.
Append
)
GmeiConfig
.
writeToJDBCTable
(
result
,
"Recommendation_strategy_temp"
,
SaveMode
.
Append
)
}
...
...
eda/feededa/src/main/scala/com/gmei/strategy_other.scala
View file @
c497c73b
...
...
@@ -162,15 +162,15 @@ object strategy_other {
val
result
=
clk_active_1
.
join
(
imp_active_1
,
"stat_date"
)
val
result
2
=
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
()
result
2
.
show
()
GmeiConfig
.
writeToJDBCTable
(
result
,
"strategy_other"
,
SaveMode
.
Append
)
GmeiConfig
.
writeToJDBCTable
(
result
2
,
"strategy_other"
,
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