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
b38b8e05
Commit
b38b8e05
authored
Aug 15, 2018
by
张彦钊
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add print for test
parent
fca10857
Show whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
8 additions
and
11 deletions
+8
-11
predictDiary.py
predictDiary.py
+8
-9
userProfile.py
userProfile.py
+0
-2
No files found.
predictDiary.py
View file @
b38b8e05
...
@@ -11,13 +11,10 @@ from utils import *
...
@@ -11,13 +11,10 @@ from utils import *
def
feature_en
(
user_profile
):
def
feature_en
(
user_profile
):
file_name
=
DIRECTORY_PATH
+
"diaryTestSet/{0}DiaryTop3000.csv"
.
format
(
user_profile
[
'city_id'
])
file_name
=
DIRECTORY_PATH
+
"diaryTestSet/{0}DiaryTop3000.csv"
.
format
(
user_profile
[
'city_id'
])
data
=
pd
.
read_csv
(
file_name
)
data
=
pd
.
read_csv
(
file_name
)
data
[
"device_id"
]
=
user_profile
[
'device_id'
]
data
[
"device_id"
]
=
user_profile
[
'device_id'
]
now
=
datetime
.
now
()
now
=
datetime
.
now
()
data
[
"hour"
]
=
now
.
hour
data
[
"hour"
]
=
now
.
hour
data
[
"minute"
]
=
now
.
minute
data
[
"minute"
]
=
now
.
minute
data
.
loc
[
data
[
"hour"
]
==
0
,
[
"hour"
]]
=
24
data
.
loc
[
data
[
"hour"
]
==
0
,
[
"hour"
]]
=
24
data
.
loc
[
data
[
"minute"
]
==
0
,
[
"minute"
]]
=
60
data
.
loc
[
data
[
"minute"
]
==
0
,
[
"minute"
]]
=
60
data
[
"hour"
]
=
data
[
"hour"
]
.
astype
(
"category"
)
data
[
"hour"
]
=
data
[
"hour"
]
.
astype
(
"category"
)
...
@@ -50,12 +47,14 @@ def predict(user_profile):
...
@@ -50,12 +47,14 @@ def predict(user_profile):
ffm_model
=
xl
.
create_ffm
()
ffm_model
=
xl
.
create_ffm
()
ffm_model
.
setTest
(
instance_file_path
)
ffm_model
.
setTest
(
instance_file_path
)
ffm_model
.
setSigmoid
()
ffm_model
.
setSigmoid
()
#日志保存路径,如果不加这个参数,日志默认保存在/temp路径下,不符合规范
#日志保存路径,如果不加这个参数,日志默认保存在/temp路径下,不符合规范
param
=
{
"log"
:
"/data2/models/result"
}
param
=
{
"log"
:
"/data2/models/result"
}
ffm_model
.
predict
(
param
,
DIRECTORY_PATH
+
"model.out"
,
ffm_model
.
predict
(
param
,
DIRECTORY_PATH
+
"model.out"
,
DIRECTORY_PATH
+
"result/{0}_output.txt"
.
format
(
user_profile
[
'device_id'
]))
DIRECTORY_PATH
+
"result/{0}_output.txt"
.
format
(
user_profile
[
'device_id'
]))
print
(
"预测结束"
)
print
(
"预测结束"
)
predict_save_to_local
(
user_profile
,
instance
)
predict_save_to_local
(
user_profile
,
instance
)
#TODO 没有提供生产环境的redis地址,所以这个函数先不运行
#TODO 没有提供生产环境的redis地址,所以这个函数先不运行
# predict_save_to_redis(user_profile, instance)
# predict_save_to_redis(user_profile, instance)
...
@@ -85,7 +84,7 @@ def predict_save_to_redis(user_profile, instance):
...
@@ -85,7 +84,7 @@ def predict_save_to_redis(user_profile, instance):
def
router
(
device_id
):
def
router
(
device_id
):
user_profile
,
not_exist
=
fetch_user_profile
(
device_id
)
user_profile
,
not_exist
=
fetch_user_profile
(
device_id
)
if
not_exist
==
True
:
if
not_exist
:
print
(
'Sorry, we don
\'
t have you.'
)
print
(
'Sorry, we don
\'
t have you.'
)
else
:
else
:
predict
(
user_profile
)
predict
(
user_profile
)
...
@@ -94,20 +93,20 @@ def router(device_id):
...
@@ -94,20 +93,20 @@ def router(device_id):
if
__name__
==
"__main__"
:
if
__name__
==
"__main__"
:
# TODO 如果耗时小于一分钟,下一次取到的device_id和上一次相同
# TODO 如果耗时小于一分钟,下一次取到的device_id和上一次相同
while
True
:
while
True
:
start
=
time
.
time
()
empty
,
device_id_list
=
get_active_users
()
empty
,
device_id_list
=
get_active_users
()
if
empty
==
True
:
if
empty
:
time
.
sleep
(
60
)
time
.
sleep
(
60
)
else
:
else
:
old_device_id_list
=
pd
.
read_csv
(
DIRECTORY_PATH
+
"data_set_device_id.csv"
)[
"device_id"
]
.
values
.
tolist
()
old_device_id_list
=
pd
.
read_csv
(
DIRECTORY_PATH
+
"data_set_device_id.csv"
)[
"device_id"
]
.
values
.
tolist
()
for
device_id
in
device_id_list
:
for
device_id
in
device_id_list
:
if
device_id
in
old_device_id_list
:
if
device_id
in
old_device_id_list
:
start
=
time
.
time
()
router
(
device_id
)
router
(
device_id
)
end
=
time
.
time
()
print
(
"该用户预测耗时{}秒"
.
format
(
end
-
start
))
else
:
else
:
print
(
"该用户不是老用户,不能预测"
)
print
(
"该用户不是老用户,不能预测"
)
end
=
time
.
time
()
time_cost
=
(
end
-
start
)
print
(
"耗时{}秒"
.
format
(
time_cost
))
userProfile.py
View file @
b38b8e05
from
utils
import
con_sql
from
utils
import
con_sql
from
datetime
import
datetime
from
datetime
import
datetime
...
...
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