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
91caf4cd
Commit
91caf4cd
authored
Mar 07, 2019
by
张彦钊
Browse files
Options
Browse Files
Download
Plain Diff
Merge branch 'master' of git.wanmeizhensuo.com:ML/ffm-baseline
修改训练集开始日期
parents
92d02e7f
0fc26443
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
137 additions
and
23 deletions
+137
-23
find_bug.scala
eda/feededa/src/main/scala/com/gmei/find_bug.scala
+2
-2
temp_count.scala
eda/feededa/src/main/scala/com/gmei/temp_count.scala
+130
-21
testt.scala
eda/feededa/src/main/scala/com/gmei/testt.scala
+5
-0
No files found.
eda/feededa/src/main/scala/com/gmei/find_bug.scala
View file @
91caf4cd
...
@@ -499,4 +499,5 @@ object CTR_precise {
...
@@ -499,4 +499,5 @@ object CTR_precise {
}
}
}
}
\ No newline at end of file
eda/feededa/src/main/scala/com/gmei/temp_count.scala
View file @
91caf4cd
...
@@ -218,34 +218,145 @@ object Repeated_content_recommendation {
...
@@ -218,34 +218,145 @@ object Repeated_content_recommendation {
ti
.
tidbMapTable
(
dbName
=
"jerry_prod"
,
tableName
=
"merge_queue_table"
)
ti
.
tidbMapTable
(
dbName
=
"jerry_prod"
,
tableName
=
"merge_queue_table"
)
val
stat_date
=
GmeiConfig
.
getMinusNDate
(
1
)
//
val stat_date = GmeiConfig.getMinusNDate(1)
//
val stat_date = param.date
val
stat_date
=
param
.
date
val
partition_date
=
stat_date
.
replace
(
"-"
,
""
)
val
partition_date
=
stat_date
.
replace
(
"-"
,
""
)
val
exp_diary
=
sc
.
sql
(
val
agency_id
=
sc
.
sql
(
s
"""
s
"""
|select concat_ws('|',device_id,cid_id)
|SELECT DISTINCT(cl_id) as device_id
|from data_feed_exposure
|FROM online.ml_hospital_spam_pv_day
|where cid_type = 'diary'
|WHERE partition_date >= '20180402'
|and device_id not in (select device_id from blacklist)
|AND partition_date <= '${partition_date}'
|and stat_date ='${stat_date}'
|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 <= '${partition_date}'
|AND pv_ratio >= 0.95
|UNION ALL
|select distinct(device_id)
|from blacklist
"""
.
stripMargin
)
agency_id
.
createOrReplaceTempView
(
"agency_id"
)
val
device_id_oldUser
=
sc
.
sql
(
s
"""
|select distinct(om.device_id) as device_id
|from online.ml_device_day_active_status om left join agency_id
|on om.device_id = agency_id.device_id
|where om.active_type = '4'
|and om.first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
| ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
| ,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
| ,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
| ,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
| ,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
| ,'promotion_shike','promotion_julang_jl03','','unknown')
|and om.partition_date ='${partition_date}'
|and agency_id.device_id is null
"""
.
stripMargin
)
device_id_oldUser
.
createOrReplaceTempView
(
"device_id_old"
)
device_id_oldUser
.
show
()
val
device_id_newUser
=
sc
.
sql
(
s
"""
|select distinct(om.device_id) as device_id
|from online.ml_device_day_active_status om left join agency_id
|on om.device_id = agency_id.device_id
|where om.active_type != '4'
|and om.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','','unknown')
|and om.partition_date ='${partition_date}'
|and agency_id.device_id is null
"""
.
stripMargin
"""
.
stripMargin
)
)
exp_diary
.
show
()
device_id_newUser
.
createOrReplaceTempView
(
"device_id_new"
)
val
get_result
=
exp_diary
.
rdd
.
map
((
_
,
1
)).
reduceByKey
(
_
+
_
)
device_id_newUser
.
show
()
val
exp_diary_new
=
sc
.
sql
(
s
"""
|select concat_ws('|',de.device_id,de.cid_id)
|from data_feed_exposure de inner join device_id_new
|on de.device_id=device_id_new.device_id
|where de.cid_type = 'diary'
|and de.stat_date ='${stat_date}'
"""
.
stripMargin
)
val
get_result_new
=
exp_diary_new
.
rdd
.
map
((
_
,
1
)).
reduceByKey
(
_
+
_
)
.
sortBy
(
_
.
_2
,
false
)
.
sortBy
(
_
.
_2
,
false
)
val
more_than2
=
get_result
.
filter
(
_
.
_2
>=
2
).
map
(
_
.
_2
).
reduce
((
x
,
y
)
=>
x
+
y
)
val
more_than2_new
=
get_result_new
.
filter
(
_
.
_2
>=
2
).
map
(
_
.
_2
).
reduce
((
x
,
y
)
=>
x
+
y
)
println
(
more_than2
)
println
(
more_than2_new
)
val
all
=
get_result
.
map
(
_
.
_2
).
reduce
((
x
,
y
)
=>
x
+
y
)
val
all_new
=
get_result_new
.
map
(
_
.
_2
).
reduce
((
x
,
y
)
=>
x
+
y
)
println
(
all
)
println
(
all_new
)
val
repeated_rate
=
more_than2
/
all
.
toDouble
val
repeated_rate_new
=
more_than2_new
/
all_new
.
toDouble
println
(
repeated_rate
)
println
(
repeated_rate_new
)
val
test
=
List
((
stat_date
,
repeated_rate
))
val
df
=
sc
.
createDataFrame
(
test
)
val
exp_diary_old
=
sc
.
sql
(
s
"""
|select concat_ws('|',de.device_id,de.cid_id)
|from data_feed_exposure de inner join device_id_old
|on de.device_id=device_id_old.device_id
|where de.cid_type = 'diary'
|and de.stat_date ='${stat_date}'
"""
.
stripMargin
)
val
get_result_old
=
exp_diary_old
.
rdd
.
map
((
_
,
1
)).
reduceByKey
(
_
+
_
)
.
sortBy
(
_
.
_2
,
false
)
val
more_than2_old
=
get_result_old
.
filter
(
_
.
_2
>=
2
).
map
(
_
.
_2
).
reduce
((
x
,
y
)
=>
x
+
y
)
println
(
more_than2_old
)
val
all_old
=
get_result_old
.
map
(
_
.
_2
).
reduce
((
x
,
y
)
=>
x
+
y
)
println
(
all_old
)
val
repeated_rate_old
=
more_than2_old
/
all_old
.
toDouble
println
(
repeated_rate_old
)
val
result2
=
List
((
stat_date
,
more_than2_old
,
all_old
,
more_than2_new
,
all_new
))
val
df2
=
sc
.
createDataFrame
(
result2
).
toDF
(
"stat_date"
,
"old_rep_count"
,
"old_imp_all"
,
"new_rep_count"
,
"new_imp_all"
)
GmeiConfig
.
writeToJDBCTable
(
df
,
table
=
"Repeated_evaluation_indicator"
,
SaveMode
.
Append
)
GmeiConfig
.
writeToJDBCTable
(
df2
,
table
=
"Repeated_evaluation_indicator"
,
SaveMode
.
Append
)
// val exp_diary_old = sc.sql(
// s"""
// |select concat_ws('|',de.device_id,de.cid_id)
// |from data_feed_exposure de inner join device_id_old
// |where de.cid_type = 'diary'
// |and de.stat_date ='${stat_date}'
// """.stripMargin
// )
// val get_result_old =exp_diary_old.rdd.map((_, 1)).reduceByKey(_ + _)
// .sortBy(_._2,false)
//
// val more_than2_old=get_result_old.filter(_._2 >=2).map(_._2).reduce((x,y)=>x+y)
// println(more_than2_old)
// val all_old =get_result_old.map(_._2).reduce((x,y)=>x+y)
// println(all_old)
// val repeated_rate_old= more_than2_old / all_old.toDouble
// println(repeated_rate_old)
//
//
// val result2=List((stat_date,more_than2_old,all_old))
// val df2 = sc.createDataFrame(result2).toDF("stat_date","old_rep_count","old_imp_all")
//
// GmeiConfig.writeToJDBCTable(df2, table = "Repeated_evaluation_indicator_old", SaveMode.Append)
// val temp=get_result.collect()
// val temp=get_result.collect()
...
@@ -260,8 +371,6 @@ object Repeated_content_recommendation {
...
@@ -260,8 +371,6 @@ object Repeated_content_recommendation {
}
}
object
Repeated_content_recommendation_moreday
{
object
Repeated_content_recommendation_moreday
{
Logger
.
getLogger
(
"org.apache.spark"
).
setLevel
(
Level
.
WARN
)
Logger
.
getLogger
(
"org.apache.spark"
).
setLevel
(
Level
.
WARN
)
...
...
eda/feededa/src/main/scala/com/gmei/testt.scala
View file @
91caf4cd
...
@@ -408,6 +408,11 @@ object testt {
...
@@ -408,6 +408,11 @@ object testt {
object
diary_clk_card
{
object
diary_clk_card
{
Logger
.
getLogger
(
"org.apache.spark"
).
setLevel
(
Level
.
WARN
)
Logger
.
getLogger
(
"org.apache.spark"
).
setLevel
(
Level
.
WARN
)
...
...
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