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
2b08e1b9
Commit
2b08e1b9
authored
Aug 28, 2018
by
张彦钊
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add print
parent
34cb81cc
Show whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
14 additions
and
4 deletions
+14
-4
diaryQueueUpdate.py
diaryQueueUpdate.py
+3
-3
processData.py
processData.py
+2
-1
train.py
train.py
+1
-0
utils.py
utils.py
+8
-0
No files found.
diaryQueueUpdate.py
View file @
2b08e1b9
...
...
@@ -233,10 +233,10 @@ if __name__ == "__main__":
print
(
"累计预测用户总数:{}"
.
format
(
total_number
))
if
device_city_list
!=
[]:
for
device_city
in
device_city_list
:
start
=
time
.
time
()
#
start = time.time()
multi_proecess_update
(
device_city
[
0
],
device_city
[
1
],
data_set_cid
,
total_video_id
)
end
=
time
.
time
()
print
(
"更新该用户队列耗时{}秒"
.
format
((
end
-
start
)))
#
end = time.time()
#
print("更新该用户队列耗时{}秒".format((end - start)))
...
...
processData.py
View file @
2b08e1b9
...
...
@@ -68,7 +68,8 @@ def ffm_transform(data, test_number, validation_number):
print
(
"Start ffm transform"
)
start
=
time
.
time
()
ffm_train
=
multiFFMFormatPandas
()
data
=
ffm_train
.
fit_transform
(
data
,
y
=
'y'
,
n
=
50000
,
processes
=
8
)
# 服务器内存空闲的时候,可以下面的6改成8。6比较稳定,如果服务器内存占用较多的时候,用8可能因为分配不到内存,脚本挂掉。
data
=
ffm_train
.
fit_transform
(
data
,
y
=
'y'
,
n
=
50000
,
processes
=
6
)
with
open
(
DIRECTORY_PATH
+
"train/ffm.pkl"
,
"wb"
)
as
f
:
pickle
.
dump
(
ffm_train
,
f
)
...
...
train.py
View file @
2b08e1b9
...
...
@@ -29,3 +29,4 @@ if __name__ == "__main__":
utils.py
View file @
2b08e1b9
...
...
@@ -8,6 +8,7 @@ import pandas as pd
from
sklearn
import
metrics
from
sklearn.metrics
import
auc
from
multiprocessing
import
Pool
import
os
def
get_date
():
...
...
@@ -46,6 +47,13 @@ def con_sql(sql):
return
df
def
move_file
():
for
eachFile
in
os
.
listdir
(
"/data2/"
):
if
"xlearn"
in
eachFile
:
os
.
remove
(
"/tmp"
+
"/"
+
eachFile
)
# 把数据写到redis里
# TODO 生产环境的redis地址没有提供,下面的地址是测试环境的,需要改成生产环境地址
def
add_data_to_redis
(
key
,
val
):
...
...
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