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
a5881d91
Commit
a5881d91
authored
Nov 05, 2020
by
赵威
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
get feature data
parent
223dcbc2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
128 additions
and
3 deletions
+128
-3
get_tractate_data.py
dssm/get_tractate_data.py
+126
-2
tractate.py
word_vector/tractate.py
+2
-1
No files found.
dssm/get_tractate_data.py
View file @
a5881d91
...
...
@@ -35,7 +35,7 @@ def get_spark(app_name=""):
"org.apache.spark.sql.TiExtensions"
)
.
config
(
"spark.tispark.pd.addresses"
,
"172.16.40.170:2379"
)
.
appName
(
app_name
)
.
enableHiveSupport
()
.
getOrCreate
()
sc
=
spark
.
sparkContext
sc
.
setLogLevel
(
"
WARN
"
)
sc
.
setLogLevel
(
"
ERROR
"
)
# sc.addPyFile("/srv/apps/strategy_embedding/utils/date.py")
ti
=
pti
.
TiContext
(
spark
)
ti
.
tidbMapDatabase
(
"jerry_test"
)
...
...
@@ -45,7 +45,7 @@ def get_spark(app_name=""):
def
get_click_data
(
spark
,
card_type
,
start
,
end
):
reg
=
r"""^\\d+$"""
sql
=
"""
SELECT DISTINCT t1.cl_id device_id, cast(t1.business_id as int) card_id,t1.partition_date
,t1.time_stamp
SELECT DISTINCT t1.cl_id device_id, cast(t1.business_id as int) card_id,t1.partition_date
FROM
(select partition_date,cl_id,business_id,action,page_name,page_stay,time_stamp
from online.bl_hdfs_maidian_updates
...
...
@@ -236,6 +236,127 @@ def get_exposure_data(spark, card_type, start, end):
"""
.
format
(
reg
,
card_type
,
end
,
start
,
end
,
end
,
end
,
end
,
end
,
start
,
end
))
def
get_card_feature_df
(
spark
,
card_type
,
yesterday
):
reg
=
r"""^\\d+$"""
sql
=
"""
SELECT CAST(card_id as INT) as card_id,
partition_date,
is_pure_author,
is_have_pure_reply,
is_have_reply,
CAST(card_feature.content_level as FLOAT) as content_level,
topic_seven_click_num,
topic_thirty_click_num,
topic_num,
seven_transform_num,
thirty_transform_num,
favor_num,
favor_pure_num,
vote_num,
vote_display_num,
reply_num,
reply_pure_num,
one_click_num,
three_click_num,
seven_click_num,
fifteen_click_num,
thirty_click_num,
sixty_click_num,
ninety_click_num,
history_click_num,
one_precise_exposure_num,
three_precise_exposure_num,
seven_precise_exposure_num,
fifteen_precise_exposure_num,
thirty_precise_exposure_num,
sixty_precise_exposure_num,
ninety_precise_exposure_num,
history_precise_exposure_num,
one_vote_user_num,
three_vote_user_num,
seven_vote_user_num,
fifteen_vote_user_num,
thirty_vote_user_num,
sixty_vote_user_num,
ninety_vote_user_num,
history_vote_user_num,
one_reply_user_num,
three_reply_user_num,
seven_reply_user_num,
fifteen_reply_user_num,
thirty_reply_user_num,
sixty_reply_user_num,
ninety_reply_user_num,
history_reply_user_num,
one_browse_user_num,
three_browse_user_num,
seven_browse_user_num,
fifteen_browse_user_num,
thirty_browse_user_num,
sixty_browse_user_num,
ninety_browse_user_num,
history_browse_user_num,
one_reply_num,
three_reply_num,
seven_reply_num,
fifteen_reply_num,
thirty_reply_num,
sixty_reply_num,
ninety_reply_num,
history_reply_num,
one_ctr,
three_ctr,
seven_ctr,
fifteen_ctr,
thirty_ctr,
sixty_ctr,
ninety_ctr,
history_ctr,
one_vote_pure_rate,
three_vote_pure_rate,
seven_vote_pure_rate,
fifteen_vote_pure_rate,
thirty_vote_pure_rate,
sixty_vote_pure_rate,
ninety_vote_pure_rate,
history_vote_pure_rate,
one_reply_pure_rate,
three_reply_pure_rate,
seven_reply_pure_rate,
fifteen_reply_pure_rate,
thirty_reply_pure_rate,
sixty_reply_pure_rate,
ninety_reply_pure_rate,
history_reply_pure_rate,
CAST(IFNULL(content2.goodclick_7, 0.0) AS DOUBLE) AS goodclick_7,
CAST(IFNULL(content2.goodclick_14, 0.0) AS DOUBLE) AS goodclick_14,
CAST(IFNULL(content2.goodclick_30, 0.0) AS DOUBLE) AS goodclick_30,
CAST(IFNULL(content2.goodclick_60, 0.0) AS DOUBLE) AS goodclick_60,
CAST(IFNULL(content2.goodclick_90, 0.0) AS DOUBLE) AS goodclick_90,
content_tag3.smart_rank_score smart_rank_score,
IFNULL(content_tag3.first_demands, "") AS card_first_demands,
IFNULL(content_tag3.second_demands, "") AS card_second_demands,
IFNULL(content_tag3.first_solutions, "") AS card_first_solutions,
IFNULL(content_tag3.second_solutions, "") AS card_second_solutions,
IFNULL(content_tag3.first_positions, "") AS card_first_positions,
IFNULL(content_tag3.second_positions, "") AS card_second_positions,
IFNULL(content_tag3.projects, "") AS card_projects
FROM
online.al_community_forecast_character_day_v3 card_feature
JOIN content_tag3
ON card_feature.card_id = content_tag3.id
LEFT JOIN
(select * from online.al_community_detail_page_goodclick_ctr
where page_name = '{}'
) AS content2
ON card_feature.card_id = content2.business_id
where partition_date = '{}'
and card_content_type = '{}'
and card_id rlike '{}'
"""
.
format
(
card_type
,
yesterday
,
card_type
,
reg
)
return
spark
.
sql
(
sql
)
if
__name__
==
"__main__"
:
spark
=
get_spark
(
"dssm_tractate_data"
)
card_type
=
"user_post"
...
...
@@ -247,4 +368,7 @@ if __name__ == "__main__":
exposure_df
=
get_exposure_data
(
spark
,
card_type
,
start
,
end
)
exposure_df
.
show
(
5
,
False
)
tractate_feature_df
=
get_card_feature_df
(
spark
,
card_type
,
end
)
tractate_feature_df
.
show
(
5
,
False
)
# 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/dssm/get_tractate_data.py
word_vector/tractate.py
View file @
a5881d91
...
...
@@ -35,7 +35,8 @@ 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
()
# sc = spark.sparkContext
sc
=
spark
.
sparkContext
sc
.
setLogLevel
(
"ERROR"
)
# sc.addPyFile("/srv/apps/strategy_embedding/utils/date.py")
ti
=
pti
.
TiContext
(
spark
)
ti
.
tidbMapDatabase
(
"jerry_test"
)
...
...
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