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
f7324e6a
Commit
f7324e6a
authored
Jan 04, 2019
by
高雅喆
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add device duration
parent
7c856a21
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
101 additions
and
0 deletions
+101
-0
EsmmData.scala
eda/feededa/src/main/scala/com/gmei/EsmmData.scala
+101
-0
No files found.
eda/feededa/src/main/scala/com/gmei/EsmmData.scala
View file @
f7324e6a
...
@@ -699,6 +699,107 @@ object GetLevelCount {
...
@@ -699,6 +699,107 @@ object GetLevelCount {
)
)
level1_name
.
show
()
level1_name
.
show
()
sc
.
stop
()
}
}
}
object
GetDeviceDuration
{
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
=
GmeiConfig
.
getMinusNDate
(
1
)
)
extends
AbstractParams
[
Params
]
with
Serializable
val
defaultParams
=
Params
()
val
parser
=
new
OptionParser
[
Params
](
"Feed_EDA"
)
{
head
(
"EsmmData"
)
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.EsmmData ./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
=
"data_feed_click"
)
import
sc.implicits._
val
stat_date
=
param
.
date
val
uid_duration
=
sc
.
sql
(
s
"""
|select a.device_id,coalesce(a.start_time,a.ndiary_in,0) in_time,coalesce(a.end_time,a.ndiary_out,0) out_time,
|explode(split(b.level1_ids,';')) level1_id
|from data_feed_click a
|left join diary_feat b on a.cid_id = b.diary_id
|where a.stat_date > '2018-12-12'
"""
.
stripMargin
)
uid_duration
.
show
()
val
uid_duration_last
=
sc
.
sql
(
s
"""
|select d.device_id,
|sum(if(d.level1_id=0,sum_duration,0)) as 'kongbai',
|sum(if(d.level1_id=1,sum_duration,0)) as 'yanbu',
|sum(if(d.level1_id=10,sum_duration,0)) as 'simi',
|sum(if(d.level1_id=1024,sum_duration,0)) as 'zitizhifang',
|sum(if(d.level1_id=1080,sum_duration,0)) as 'banyongjiu',
|sum(if(d.level1_id=11,sum_duration,0)) as 'yachi',
|sum(if(d.level1_id=12,sum_duration,0)) as 'kouchun',
|sum(if(d.level1_id=13,sum_duration,0)) as 'erbu',
|sum(if(d.level1_id=2,sum_duration,0)) as 'bibu',
|sum(if(d.level1_id=2053,sum_duration,0)) as 'remen',
|sum(if(d.level1_id=2054,sum_duration,0)) as 'banyongjiuzhuang',
|sum(if(d.level1_id=2212,sum_duration,0)) as 'jiankangguanli',
|sum(if(d.level1_id=2214,sum_duration,0)) as 'qita',
|sum(if(d.level1_id=3,sum_duration,0)) as 'lunkuo',
|sum(if(d.level1_id=4,sum_duration,0)) as 'shoushen',
|sum(if(d.level1_id=5,sum_duration,0)) as 'pifu',
|sum(if(d.level1_id=6933,sum_duration,0)) as 'shenghuo',
|sum(if(d.level1_id=7,sum_duration,0)) as 'xiongbu',
|sum(if(d.level1_id=9,sum_duration,0)) as 'maofa',
|sum(if(d.level1_id=922,sum_duration,0)) as 'kangshuai',
|sum(if(d.level1_id=929,sum_duration,0)) as 'shili',
|sum(if(d.level1_id=971,sum_duration,0)) as 'chanhouxiufu',
|sum(if(d.level1_id=992,sum_duration,0)) as 'zhushe'
|from
| (select c.device_id,c.level1_id,sum(c.duration) as sum_duration from
| (select a.device_id,
| coalesce(a.end_time,a.ndiary_out,0)-coalesce(a.start_time,a.ndiary_in,0) as duration,
| explode(split(b.level1_ids,';')) level1_id
| from data_feed_click a
| left join diary_feat b on a.cid_id = b.diary_id where a.stat_date > '2018-12-12') c
| group by c.device_id,c.level1_id) d
|group by d.device_id
"""
.
stripMargin
)
uid_duration_last
.
show
()
sc
.
stop
()
sc
.
stop
()
}
}
...
...
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