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
dddaef01
Commit
dddaef01
authored
6 years ago
by
张彦钊
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
change test file
parent
ef64e1b8
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
19 additions
and
16 deletions
+19
-16
multi.py
tensnsorflow/multi.py
+19
-16
No files found.
tensnsorflow/multi.py
View file @
dddaef01
...
...
@@ -198,25 +198,28 @@ def con_sql(db,sql):
def
test
():
# sql = "select stat_date,cid_id from esmm_train_data e where stat_date = '{}' limit 60".format("2019-04-25")
# df = spark.createDataFrame(spark.sql(sql).rdd.map(lambda x:(x[0],x[1])).zipWithIndex()
# .map(lambda x:(x[1],x[0][0],x[0][1]))).toDF("ind","k","v")
# df.show(6)
# # df.write.csv('/recommend/tr', mode='overwrite', header=True)
# df = df.toPandas()
from
hdfs
import
InsecureClient
from
hdfs.ext.dataframe
import
read_dataframe
from
hdfs.ext.dataframe
import
write_dataframe
sql
=
"select stat_date,cid_id from esmm_train_data e where stat_date = '{}' limit 60"
.
format
(
"2019-04-25"
)
df
=
spark
.
createDataFrame
(
spark
.
sql
(
sql
)
.
rdd
.
map
(
lambda
x
:(
x
[
0
],
x
[
1
]))
.
zipWithIndex
()
.
map
(
lambda
x
:(
x
[
1
],
x
[
0
][
0
],
x
[
0
][
1
])))
.
toDF
(
"ind"
,
"k"
,
"v"
)
df
.
show
(
6
)
df
.
write
.
csv
(
'/recommend/tr'
,
mode
=
'overwrite'
,
header
=
True
)
df
.
write
.
format
(
"avro"
)
.
mode
(
"overwrite"
)
.
save
(
"/recommend/tr/avro.csv"
)
client
=
InsecureClient
(
'http://nvwa01:50070'
)
# write_dataframe(client, '/recommend/va/a.csv', df)
df
=
read_dataframe
(
client
,
"/recommend/va/a.csv"
)
print
(
df
.
head
())
#
# from hdfs import InsecureClient
# from hdfs.ext.dataframe import read_dataframe
# from hdfs.ext.dataframe import write_dataframe
#
#
# client = InsecureClient('http://nvwa01:50070')
# # write_dataframe(client, '/recommend/va/a.csv', df)
#
# df = read_dataframe(client,"/recommend/va/a.csv")
#
#
# print(df.head())
# spark.sql("use online")
# spark.sql("ADD JAR /srv/apps/brickhouse-0.7.1-SNAPSHOT.jar")
...
...
This diff is collapsed.
Click to expand it.
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