Skip to content
Projects
Groups
Snippets
Help
Loading...
Sign in
Toggle navigation
S
strategy_embedding
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
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
rank
strategy_embedding
Commits
56c47d31
Commit
56c47d31
authored
Oct 28, 2020
by
赵威
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
get tractate data
parent
a1c23e8d
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
7 additions
and
7 deletions
+7
-7
spark.py
utils/spark.py
+1
-0
tests.py
word_vector/tests.py
+0
-7
word_to_vec.py
word_vector/word_to_vec.py
+6
-0
No files found.
utils/spark.py
View file @
56c47d31
...
...
@@ -18,6 +18,7 @@ def get_spark(app_name=""):
"spark.sql.extensions"
,
"org.apache.spark.sql.TiExtensions"
)
.
config
(
"spark.tispark.pd.addresses"
,
"172.16.40.170:2379"
)
.
appName
(
app_name
)
.
enableHiveSupport
()
.
getOrCreate
())
spark
.
addPyFile
(
"/srv/apps/strategy_embedding/utils/date.py"
)
ti
=
pti
.
TiContext
(
spark
)
ti
.
tidbMapDatabase
(
"jerry_test"
)
return
spark
...
...
word_vector/tests.py
View file @
56c47d31
# from django.test import TestCase
from
utils.date
import
get_ndays_before_no_minus
from
utils.spark
import
get_spark
,
get_tracate_click_data
# create your tests here.
if
__name__
==
"__main__"
:
spark
=
get_spark
(
"test"
)
click_data
=
get_tracate_click_data
(
spark
,
get_ndays_before_no_minus
(
2
),
get_ndays_before_no_minus
(
1
))
click_data
.
show
(
5
,
False
)
# /opt/spark/bin/spark-submit --master yarn --deploy-mode client --queue root.strategy --driver-memory 16g --executor-memory 1g --executor-cores 1 --num-executors 70 --conf spark.default.parallelism=100 --conf spark.storage.memoryFraction=0.5 --conf spark.shuffle.memoryFraction=0.3 --conf spark.locality.wait=0 --jars /srv/apps/tispark-core-2.1-SNAPSHOT-jar-with-dependencies.jar,/srv/apps/spark-connector_2.11-1.9.0-rc2.jar,/srv/apps/mysql-connector-java-5.1.38.jar /srv/apps/strategy_embedding/word_vector/tests.py
word_vector/word_to_vec.py
View file @
56c47d31
...
...
@@ -4,8 +4,10 @@ import time
from
gensim.models
import
Word2Vec
,
word2vec
from
gm_rpcd.all
import
bind
from
utils.date
import
get_ndays_before_no_minus
from
utils.db
import
get_device_click_tractate_ids
from
utils.es
import
es_scan
from
utils.spark
import
get_spark
,
get_tracate_click_data
base_dir
=
os
.
getcwd
()
print
(
"base_dir: "
+
base_dir
)
...
...
@@ -94,4 +96,8 @@ if __name__ == "__main__":
for
i
in
[
"双眼皮"
,
"隆鼻"
]:
print
(
word_similarity
(
i
))
spark
=
get_spark
(
"test"
)
click_data
=
get_tracate_click_data
(
spark
,
get_ndays_before_no_minus
(
2
),
get_ndays_before_no_minus
(
1
))
click_data
.
show
(
5
,
False
)
print
(
"total cost: {:.2f}mins"
.
format
((
time
.
time
()
-
begin_time
)
/
60
))
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