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
2779038d
Commit
2779038d
authored
Nov 09, 2018
by
王志伟
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
new file
parent
aaa1888e
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
124 additions
and
0 deletions
+124
-0
Recommendation_strategy_all.scala
...src/main/scala/com/gmei/Recommendation_strategy_all.scala
+124
-0
Recommendation_strategy_all.py
eda/gray_stat/Recommendation_strategy_all.py
+0
-0
No files found.
eda/feededa/src/main/scala/com/gmei/Recommendation_strategy_all.scala
0 → 100644
View file @
2779038d
//#该文件统计ffm\node2vec\搜索推荐三个策略merge后的全量用户的ctr
//#device_id尾号为1的用户为对照组
//#且去除每天新用户
package
com.gmei
import
java.io.Serializable
import
com.gmei.WeafareStat.
{
defaultParams
,
parser
}
import
org.apache.spark.sql.
{
SaveMode
,
TiContext
}
import
org.apache.log4j.
{
Level
,
Logger
}
import
scopt.OptionParser
import
com.gmei.lib.AbstractParams
object
Recommendation_strategy_all
{
Logger
.
getLogger
(
"org.apache.spark"
).
setLevel
(
Level
.
WARN
)
Logger
.
getLogger
(
"org.apache.eclipse.jetty.server"
).
setLevel
(
Level
.
OFF
)
case
class
Params
(
env
:
String
=
"dev"
,
date
:
String
=
"2018-08-01"
)
extends
AbstractParams
[
Params
]
with
Serializable
val
defaultParams
=
Params
()
val
parser
=
new
OptionParser
[
Params
](
"Feed_EDA"
)
{
head
(
"WeafareStat"
)
opt
[
String
](
"env"
)
.
text
(
s
"the databases environment you used"
)
.
action
((
x
,
c
)
=>
c
.
copy
(
env
=
x
))
opt
[
String
]
(
"date"
)
.
text
(
s
"the date you used"
)
.
action
((
x
,
c
)
=>
c
.
copy
(
date
=
x
))
note
(
"""
|For example, the following command runs this app on a tidb dataset:
|
| spark-submit --class com.gmei.WeafareStat ./target/scala-2.11/feededa-assembly-0.1.jar \
"""
.
stripMargin
+
s
"| --env ${defaultParams.env}"
)
}
def
main
(
args
:
Array
[
String
])
:
Unit
=
{
parser
.
parse
(
args
,
defaultParams
).
map
{
param
=>
GmeiConfig
.
setup
(
param
.
env
)
val
spark_env
=
GmeiConfig
.
getSparkSession
()
val
sc
=
spark_env
.
_2
val
ti
=
new
TiContext
(
sc
)
ti
.
tidbMapTable
(
dbName
=
"jerry_prod"
,
tableName
=
"diary_video"
)
ti
.
tidbMapTable
(
dbName
=
"jerry_prod"
,
tableName
=
"data_feed_click"
)
ti
.
tidbMapTable
(
dbName
=
"jerry_prod"
,
tableName
=
"blacklist"
)
ti
.
tidbMapTable
(
dbName
=
"jerry_test"
,
tableName
=
"bl_device_list"
)
ti
.
tidbMapTable
(
dbName
=
"jerry_prod"
,
tableName
=
"data_feed_exposure"
)
import
sc.implicits._
// val stat_date = GmeiConfig.getMinusNDate(1)
println
(
param
.
date
)
val
partition_date
=
param
.
date
.
replace
(
"-"
,
""
)
val
decive_id_oldUser
=
sc
.
sql
(
s
"""
|select distinct(device_id) as decive_id
|from online.ml_device_day_active_status
|where active_type = '4'
|and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
| ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
| ,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
| ,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
| ,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
| ,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
| ,'promotion_shike','promotion_julang_jl03')
|and partition_date ='${partition_date}'
"""
.
stripMargin
)
decive_id_oldUser
.
show
()
decive_id_oldUser
.
createOrReplaceTempView
(
"device_id_old"
)
val
strategies
=
Seq
(
"1$"
,
"^1$"
)
for
(
strategy
<-
strategies
){
val
clk_count_oldUser
=
sc
.
sql
(
s
"""
|select '${param.date}' as stat_date, count(cid_id) as get_clk_count_old
|from data_feed_click jd inner join device_id_old
|on jd.device_id = device_id_old.decive_id
|where (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
|and jd.device_id regexp'${strategy}'
|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 ='${param.date}'
"""
.
stripMargin
)
val
imp_count_oldUser
=
sc
.
sql
(
s
"""
|select '${param.date}' as stat_date, count(cid_id) as get_imp_count_old
|from data_feed_exposure je inner join device_id_old
|on je.device_id = device_id_old.decive_id
|where je.cid_type = 'diary'
|and je.device_id regexp'${strategy}'
|and je.device_id not in (select device_id from bl_device_list)
|and je.device_id not in (select device_id from blacklist)
|and je.stat_date ='${param.date}'
"""
.
stripMargin
)
val
result
=
clk_count_oldUser
.
join
(
imp_count_oldUser
,
"stat_date"
)
result
.
show
()
}
}
}
}
eda/gray_stat/Recommendation_strategy_all.py
0 → 100644
View file @
2779038d
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