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
518ddf1f
Commit
518ddf1f
authored
Jul 08, 2020
by
赵威
Browse files
Options
Browse Files
Download
Plain Diff
Merge branch 'offic' into 'master'
update field See merge request
!61
parents
35e4d3f4
f1b95d7e
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
37 additions
and
22 deletions
+37
-22
tag3_update_user_portrait_offline.py
eda/smart_rank/tag3_update_user_portrait_offline.py
+37
-22
No files found.
eda/smart_rank/tag3_update_user_portrait_offline.py
View file @
518ddf1f
...
@@ -91,17 +91,18 @@ def update_tag3_user_portrait_by_event(cl_id):
...
@@ -91,17 +91,18 @@ def update_tag3_user_portrait_by_event(cl_id):
list
(
second_demands_dict
.
keys
())
+
list
(
first_positions_dict
.
keys
())
+
list
(
second_positions_dict
.
keys
())
+
list
(
second_demands_dict
.
keys
())
+
list
(
first_positions_dict
.
keys
())
+
list
(
second_positions_dict
.
keys
())
+
list
(
projects_dict
.
keys
()))
list
(
projects_dict
.
keys
()))
for
e
in
events
:
# TODO
first_solutions
=
","
.
join
(
first_solutions_dict
.
get
(
e
,
[]))
# for e in events:
second_solutions
=
","
.
join
(
second_solutions_dict
.
get
(
e
,
[]))
# first_solutions = ",".join(first_solutions_dict.get(e, []))
first_demands
=
","
.
join
(
first_demands_dict
.
get
(
e
,
[]))
# second_solutions = ",".join(second_solutions_dict.get(e, []))
second_demands
=
","
.
join
(
second_demands_dict
.
get
(
e
,
[]))
# first_demands = ",".join(first_demands_dict.get(e, []))
first_positions
=
","
.
join
(
first_positions_dict
.
get
(
e
,
[]))
# second_demands = ",".join(second_demands_dict.get(e, []))
second_positions
=
","
.
join
(
second_positions_dict
.
get
(
e
,
[]))
# first_positions = ",".join(first_positions_dict.get(e, []))
projects
=
","
.
join
(
projects_dict
.
get
(
e
,
[]))
# second_positions = ",".join(second_positions_dict.get(e, []))
# projects = ",".join(projects_dict.get(e, []))
write_user_portrait_by_event
(
cl_id
,
first_solutions
,
second_solutions
,
first_demands
,
second_demands
,
first_positions
,
second_positions
,
projects
,
e
)
# write_user_portrait_by_event(cl_id, first_solutions, second_solutions, first_demands, second_demands, first_positions,
# second_positions, projects, e)
return
cl_id
return
cl_id
...
@@ -140,6 +141,18 @@ def update_tag3_user_portrait(cl_id):
...
@@ -140,6 +141,18 @@ def update_tag3_user_portrait(cl_id):
first_positions_score
=
merge_values
(
first_positions_list
)
first_positions_score
=
merge_values
(
first_positions_list
)
second_positions_score
=
merge_values
(
second_positions_list
)
second_positions_score
=
merge_values
(
second_positions_list
)
projects_score
=
merge_values
(
projects_list
)
projects_score
=
merge_values
(
projects_list
)
print
(
projects_score
)
tmp
=
[
"不感兴趣"
,
"没有想法"
,
"八卦来了"
,
"颜值速报"
,
"医美审美干货"
,
"其他项目"
,
"网红颜值"
,
"少年之名"
,
"郑人予"
,
"热点课代表"
,
"私密"
,
"陈瑞泽"
,
"符仁杰"
,
"祖力亚尔"
,
"刘泽旭"
,
"陈家瑨"
]
forbidden_lst
=
[]
for
i
in
tmp
:
forbidden_lst
.
append
(
i
+
"kyc"
)
forbidden_lst
.
extend
(
tmp
)
forbidden_set
=
set
(
forbidden_lst
)
# TODO projects_score remove forbidden_set
res
=
{
res
=
{
"first_demands"
:
first_demands_score
,
"first_demands"
:
first_demands_score
,
...
@@ -154,17 +167,18 @@ def update_tag3_user_portrait(cl_id):
...
@@ -154,17 +167,18 @@ def update_tag3_user_portrait(cl_id):
key
=
"doris:user_portrait:tag3:device_id:"
+
str
(
cl_id
)
key
=
"doris:user_portrait:tag3:device_id:"
+
str
(
cl_id
)
redis_client
=
redis
.
StrictRedis
.
from_url
(
"redis://:ReDis!GmTx*0aN9@172.16.40.173:6379"
)
redis_client
=
redis
.
StrictRedis
.
from_url
(
"redis://:ReDis!GmTx*0aN9@172.16.40.173:6379"
)
if
(
len
(
first_demands_score
.
keys
())
>
0
)
or
(
len
(
second_demands_score
.
keys
())
>
0
)
or
\
# TODO
(
len
(
first_solutions_score
.
keys
())
>
0
)
or
(
len
(
second_solutions_score
.
keys
())
>
0
)
or
\
# if (len(first_demands_score.keys()) > 0) or (len(second_demands_score.keys()) > 0) or \
(
len
(
first_positions_score
.
keys
())
>
0
)
or
(
len
(
second_positions_score
.
keys
())
>
0
)
or
\
# (len(first_solutions_score.keys()) > 0) or (len(second_solutions_score.keys()) > 0) or \
(
len
(
projects_score
.
keys
())
>
0
):
# (len(first_positions_score.keys()) > 0) or (len(second_positions_score.keys()) > 0) or \
redis_client
.
set
(
key
,
json
.
dumps
(
res
))
# (len(projects_score.keys()) > 0):
redis_client
.
expire
(
key
,
60
*
60
*
24
*
30
)
# redis_client.set(key, json.dumps(res))
# redis_client.expire(key, 60 * 60 * 24 * 30)
write_user_portrait
(
cl_id
,
","
.
join
(
first_solutions_score
.
keys
()),
","
.
join
(
second_solutions_score
.
keys
()),
#
write_user_portrait(cl_id, ",".join(first_solutions_score.keys()), ",".join(second_solutions_score.keys()),
","
.
join
(
first_demands_score
.
keys
()),
","
.
join
(
second_demands_score
.
keys
()),
#
",".join(first_demands_score.keys()), ",".join(second_demands_score.keys()),
","
.
join
(
first_positions_score
.
keys
()),
","
.
join
(
second_positions_score
.
keys
()),
#
",".join(first_positions_score.keys()), ",".join(second_positions_score.keys()),
","
.
join
(
projects_score
.
keys
()))
#
",".join(projects_score.keys()))
return
cl_id
return
cl_id
...
@@ -177,7 +191,8 @@ def consume_kafka():
...
@@ -177,7 +191,8 @@ def consume_kafka():
db
.
close
()
db
.
close
()
cursor
.
close
()
cursor
.
close
()
# device_ids_lst = ["androidid_a25a1129c0b38f7b"]
# TODO
device_ids_lst
=
[
"androidid_a25a1129c0b38f7b"
]
sparkConf
=
SparkConf
()
.
set
(
"spark.hive.mapred.supports.subdirectories"
,
"true"
)
\
sparkConf
=
SparkConf
()
.
set
(
"spark.hive.mapred.supports.subdirectories"
,
"true"
)
\
.
set
(
"spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive"
,
"true"
)
\
.
set
(
"spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive"
,
"true"
)
\
...
...
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