Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
weixin_52226395
Paddle
提交
a74f5365
P
Paddle
项目概览
weixin_52226395
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
提交
a74f5365
编写于
1月 06, 2017
作者:
Y
Yu Yang
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Format code
上级
82bee14d
变更
3
显示空白变更内容
内联
并排
Showing
3 changed file
with
64 addition
and
61 deletion
+64
-61
demo/traffic_prediction/dataprovider.py
demo/traffic_prediction/dataprovider.py
+18
-13
demo/traffic_prediction/gen_result.py
demo/traffic_prediction/gen_result.py
+31
-31
demo/traffic_prediction/trainer_config.py
demo/traffic_prediction/trainer_config.py
+15
-17
未找到文件。
demo/traffic_prediction/dataprovider.py
浏览文件 @
a74f5365
...
@@ -18,6 +18,8 @@ import numpy as np
...
@@ -18,6 +18,8 @@ import numpy as np
TERM_NUM
=
24
TERM_NUM
=
24
FORECASTING_NUM
=
25
FORECASTING_NUM
=
25
LABEL_VALUE_NUM
=
4
LABEL_VALUE_NUM
=
4
def
initHook
(
settings
,
file_list
,
**
kwargs
):
def
initHook
(
settings
,
file_list
,
**
kwargs
):
"""
"""
Init hook is invoked before process data. It will set obj.slots and store data meta.
Init hook is invoked before process data. It will set obj.slots and store data meta.
...
@@ -38,40 +40,43 @@ def initHook(settings, file_list, **kwargs):
...
@@ -38,40 +40,43 @@ def initHook(settings, file_list, **kwargs):
for
i
in
range
(
FORECASTING_NUM
):
for
i
in
range
(
FORECASTING_NUM
):
settings
.
slots
.
append
(
integer_value
(
LABEL_VALUE_NUM
))
settings
.
slots
.
append
(
integer_value
(
LABEL_VALUE_NUM
))
@
provider
(
init_hook
=
initHook
,
cache
=
CacheType
.
CACHE_PASS_IN_MEM
,
should_shuffle
=
True
)
@
provider
(
init_hook
=
initHook
,
cache
=
CacheType
.
CACHE_PASS_IN_MEM
,
should_shuffle
=
True
)
def
process
(
settings
,
file_name
):
def
process
(
settings
,
file_name
):
with
open
(
file_name
)
as
f
:
with
open
(
file_name
)
as
f
:
#abandon fields name
#abandon fields name
f
.
next
()
f
.
next
()
for
row_num
,
line
in
enumerate
(
f
):
for
row_num
,
line
in
enumerate
(
f
):
speeds
=
map
(
int
,
line
.
rstrip
(
'
\r\n
'
).
split
(
","
)[
1
:])
speeds
=
map
(
int
,
line
.
rstrip
(
'
\r\n
'
).
split
(
","
)[
1
:])
# Get the max index.
# Get the max index.
end_time
=
len
(
speeds
)
end_time
=
len
(
speeds
)
# Scanning and generating samples
# Scanning and generating samples
for
i
in
range
(
TERM_NUM
,
end_time
-
FORECASTING_NUM
):
for
i
in
range
(
TERM_NUM
,
end_time
-
FORECASTING_NUM
):
# For dense slot
# For dense slot
pre_spd
=
map
(
float
,
speeds
[
i
-
TERM_NUM
:
i
])
pre_spd
=
map
(
float
,
speeds
[
i
-
TERM_NUM
:
i
])
# Integer value need predicting, values start from 0, so every one minus 1.
# Integer value need predicting, values start from 0, so every one minus 1.
fol_spd
=
[
i
-
1
for
i
in
speeds
[
i
:
i
+
FORECASTING_NUM
]]
fol_spd
=
[
i
-
1
for
i
in
speeds
[
i
:
i
+
FORECASTING_NUM
]]
# Predicting label is missing, abandon the sample.
# Predicting label is missing, abandon the sample.
if
-
1
in
fol_spd
:
if
-
1
in
fol_spd
:
continue
continue
yield
[
pre_spd
]
+
fol_spd
yield
[
pre_spd
]
+
fol_spd
def
predict_initHook
(
settings
,
file_list
,
**
kwargs
):
def
predict_initHook
(
settings
,
file_list
,
**
kwargs
):
settings
.
pool_size
=
sys
.
maxint
settings
.
pool_size
=
sys
.
maxint
settings
.
slots
=
[
dense_vector
(
TERM_NUM
)]
settings
.
slots
=
[
dense_vector
(
TERM_NUM
)]
@
provider
(
init_hook
=
predict_initHook
,
should_shuffle
=
False
)
@
provider
(
init_hook
=
predict_initHook
,
should_shuffle
=
False
)
def
process_predict
(
settings
,
file_name
):
def
process_predict
(
settings
,
file_name
):
with
open
(
file_name
)
as
f
:
with
open
(
file_name
)
as
f
:
#abandon fields name
#abandon fields name
f
.
next
()
f
.
next
()
for
row_num
,
line
in
enumerate
(
f
):
for
row_num
,
line
in
enumerate
(
f
):
speeds
=
map
(
int
,
line
.
rstrip
(
'
\r\n
'
).
split
(
","
))
speeds
=
map
(
int
,
line
.
rstrip
(
'
\r\n
'
).
split
(
","
))
end_time
=
len
(
speeds
)
end_time
=
len
(
speeds
)
pre_spd
=
map
(
float
,
speeds
[
end_time
-
TERM_NUM
:
end_time
])
pre_spd
=
map
(
float
,
speeds
[
end_time
-
TERM_NUM
:
end_time
])
yield
pre_spd
yield
pre_spd
demo/traffic_prediction/gen_result.py
浏览文件 @
a74f5365
res
=
[]
res
=
[]
with
open
(
'./rank-00000'
)
as
f
:
with
open
(
'./rank-00000'
)
as
f
:
for
line
in
f
:
for
line
in
f
:
pred
=
map
(
int
,
line
.
strip
(
'
\r\n
;'
).
split
(
";"
))
pred
=
map
(
int
,
line
.
strip
(
'
\r\n
;'
).
split
(
";"
))
#raw prediction range from 0 to 3
#raw prediction range from 0 to 3
res
.
append
([
i
+
1
for
i
in
pred
])
res
.
append
([
i
+
1
for
i
in
pred
])
file_name
=
open
(
'./data/pred.list'
).
read
().
strip
(
'
\r\n
'
)
file_name
=
open
(
'./data/pred.list'
).
read
().
strip
(
'
\r\n
'
)
FORECASTING_NUM
=
24
FORECASTING_NUM
=
24
header
=
[
'id'
,
header
=
[
'id'
,
'201604200805'
,
'201604200805'
,
'201604200810'
,
'201604200810'
,
'201604200815'
,
'201604200815'
,
...
@@ -33,7 +34,7 @@ header=['id',
...
@@ -33,7 +34,7 @@ header=['id',
'201604200950'
,
'201604200950'
,
'201604200955'
,
'201604200955'
,
'201604201000'
,
'201604201000'
,
]
]
###################
###################
## To CSV format ##
## To CSV format ##
###################
###################
...
@@ -43,5 +44,4 @@ with open(file_name) as f:
...
@@ -43,5 +44,4 @@ with open(file_name) as f:
for
row_num
,
line
in
enumerate
(
f
):
for
row_num
,
line
in
enumerate
(
f
):
fields
=
line
.
rstrip
(
'
\r\n
'
).
split
(
','
)
fields
=
line
.
rstrip
(
'
\r\n
'
).
split
(
','
)
linkid
=
fields
[
0
]
linkid
=
fields
[
0
]
print
linkid
+
','
+
','
.
join
(
map
(
str
,
res
[
row_num
]))
print
linkid
+
','
+
','
.
join
(
map
(
str
,
res
[
row_num
]))
demo/traffic_prediction/trainer_config.py
浏览文件 @
a74f5365
...
@@ -2,26 +2,22 @@
...
@@ -2,26 +2,22 @@
#-*python-*-
#-*python-*-
from
paddle.trainer_config_helpers
import
*
from
paddle.trainer_config_helpers
import
*
################################### DATA Configuration #############################################
################################### DATA Configuration #############################################
is_predict
=
get_config_arg
(
'is_predict'
,
bool
,
False
)
is_predict
=
get_config_arg
(
'is_predict'
,
bool
,
False
)
trn
=
'./data/train.list'
if
not
is_predict
else
None
trn
=
'./data/train.list'
if
not
is_predict
else
None
tst
=
'./data/test.list'
if
not
is_predict
else
'./data/pred.list'
tst
=
'./data/test.list'
if
not
is_predict
else
'./data/pred.list'
process
=
'process'
if
not
is_predict
else
'process_predict'
process
=
'process'
if
not
is_predict
else
'process_predict'
define_py_data_sources2
(
train_list
=
trn
,
define_py_data_sources2
(
test_list
=
tst
,
train_list
=
trn
,
test_list
=
tst
,
module
=
"dataprovider"
,
obj
=
process
)
module
=
"dataprovider"
,
obj
=
process
)
################################### Parameter Configuaration #######################################
################################### Parameter Configuaration #######################################
TERM_NUM
=
24
TERM_NUM
=
24
FORECASTING_NUM
=
25
FORECASTING_NUM
=
25
emb_size
=
16
emb_size
=
16
batch_size
=
128
if
not
is_predict
else
1
batch_size
=
128
if
not
is_predict
else
1
settings
(
settings
(
batch_size
=
batch_size
,
batch_size
=
batch_size
,
learning_rate
=
1e-3
,
learning_rate
=
1e-3
,
learning_method
=
RMSPropOptimizer
()
learning_method
=
RMSPropOptimizer
())
)
################################### Algorithm Configuration ########################################
################################### Algorithm Configuration ########################################
output_label
=
[]
output_label
=
[]
...
@@ -29,15 +25,17 @@ output_label = []
...
@@ -29,15 +25,17 @@ output_label = []
link_encode
=
data_layer
(
name
=
'link_encode'
,
size
=
TERM_NUM
)
link_encode
=
data_layer
(
name
=
'link_encode'
,
size
=
TERM_NUM
)
for
i
in
xrange
(
FORECASTING_NUM
):
for
i
in
xrange
(
FORECASTING_NUM
):
# Each task share same weight.
# Each task share same weight.
link_param
=
ParamAttr
(
name
=
'_link_vec.w'
,
initial_max
=
1.0
,
initial_min
=-
1.0
)
link_param
=
ParamAttr
(
link_vec
=
fc_layer
(
input
=
link_encode
,
size
=
emb_size
,
param_attr
=
link_param
)
name
=
'_link_vec.w'
,
initial_max
=
1.0
,
initial_min
=-
1.0
)
link_vec
=
fc_layer
(
input
=
link_encode
,
size
=
emb_size
,
param_attr
=
link_param
)
score
=
fc_layer
(
input
=
link_vec
,
size
=
4
,
act
=
SoftmaxActivation
())
score
=
fc_layer
(
input
=
link_vec
,
size
=
4
,
act
=
SoftmaxActivation
())
if
is_predict
:
if
is_predict
:
maxid
=
maxid_layer
(
score
)
maxid
=
maxid_layer
(
score
)
output_label
.
append
(
maxid
)
output_label
.
append
(
maxid
)
else
:
else
:
# Multi-task training.
# Multi-task training.
label
=
data_layer
(
name
=
'label_%dmin'
%
((
i
+
1
)
*
5
),
size
=
4
)
label
=
data_layer
(
name
=
'label_%dmin'
%
((
i
+
1
)
*
5
),
size
=
4
)
cls
=
classification_cost
(
input
=
score
,
name
=
"cost_%dmin"
%
((
i
+
1
)
*
5
),
label
=
label
)
cls
=
classification_cost
(
input
=
score
,
name
=
"cost_%dmin"
%
((
i
+
1
)
*
5
),
label
=
label
)
output_label
.
append
(
cls
)
output_label
.
append
(
cls
)
outputs
(
output_label
)
outputs
(
output_label
)
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录