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
58ad143d
Commit
58ad143d
authored
Nov 23, 2018
by
高雅喆
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add esmm data
parent
e249d07a
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
107 additions
and
0 deletions
+107
-0
EsmmData.scala
eda/feededa/src/main/scala/com/gmei/EsmmData.scala
+107
-0
No files found.
eda/feededa/src/main/scala/com/gmei/EsmmData.scala
0 → 100644
View file @
58ad143d
package
com.gmei
import
java.io.Serializable
import
org.apache.spark.sql.
{
SaveMode
,
TiContext
}
import
org.apache.log4j.
{
Level
,
Logger
}
import
scopt.OptionParser
import
com.gmei.lib.AbstractParams
object
EsmmData
{
Logger
.
getLogger
(
"org.apache.spark"
).
setLevel
(
Level
.
WARN
)
Logger
.
getLogger
(
"org.apache.eclipse.jetty.server"
).
setLevel
(
Level
.
OFF
)
case
class
Params
(
env
:
String
=
"dev"
)
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
))
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 ${defaultParams.env}"
)
}
def
main
(
args
:
Array
[
String
])
:
Unit
=
{
parser
.
parse
(
args
,
defaultParams
).
map
{
param
=>
GmeiConfig
.
setup
(
param
.
env
)
val
spark_env
=
GmeiConfig
.
getSparkSession
()
val
sc
=
spark_env
.
_2
val
ti
=
new
TiContext
(
sc
)
ti
.
tidbMapTable
(
dbName
=
"eagle"
,
tableName
=
"src_mimas_prod_api_diary_tags"
)
ti
.
tidbMapTable
(
dbName
=
"jerry_prod"
,
tableName
=
"data_feed_click"
)
ti
.
tidbMapTable
(
dbName
=
"jerry_prod"
,
tableName
=
"data_feed_exposure"
)
import
sc.implicits._
val
stat_date
=
GmeiConfig
.
getMinusNDate
(
14
)
println
(
stat_date
)
val
imp_data
=
sc
.
sql
(
s
"""
|select stat_date,device_id,city_id as ucity_id,
| cid_id,diary_service_id
|from data_feed_exposure
|where cid_type = 'diary'
|and stat_date >'${stat_date}'
"""
.
stripMargin
)
imp_data
.
show
()
imp_data
.
createOrReplaceTempView
(
"imp_data"
)
val
clk_data
=
sc
.
sql
(
s
"""
|select stat_date,device_id,city_id as ucity_id,
| cid_id,diary_service_id
|from data_feed_click
|where cid_type = 'diary'
|and stat_date >'${stat_date}'
"""
.
stripMargin
)
clk_data
.
show
()
clk_data
.
createOrReplaceTempView
(
"clk_data"
)
val
stat_date_not
=
GmeiConfig
.
getMinusNDate
(
14
).
replace
(
"-"
,
""
)
val
cvr_data
=
sc
.
sql
(
s
"""
|select
| from_unixtime(unix_timestamp('${stat_date_not}' ,'yyyyMMdd'), 'yyyy-MM-dd') as stat_date,
| cl_id as device_id,city_id as ucity_id,
| params["referrer_id"] as cid_id,params["business_id"] as diary_service_id
|from online.tl_hdfs_maidian_view
|where action='page_view'
|and partition_date >'${stat_date_not}'
|and params['page_name'] = 'welfare_detail'
|and params['referrer'] = 'diary_detail'
"""
.
stripMargin
)
cvr_data
.
show
()
cvr_data
.
createOrReplaceTempView
(
"cvr_data"
)
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