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
PaddlePaddle
PaddleDetection
提交
eb1e34d2
P
PaddleDetection
项目概览
PaddlePaddle
/
PaddleDetection
大约 1 年 前同步成功
通知
694
Star
11112
Fork
2696
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
184
列表
看板
标记
里程碑
合并请求
40
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
PaddleDetection
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
184
Issue
184
列表
看板
标记
里程碑
合并请求
40
合并请求
40
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
eb1e34d2
编写于
3月 01, 2017
作者:
Y
Yi Wang
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Add imdb and unit test
上级
349319e5
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
148 addition
and
9 deletion
+148
-9
python/paddle/v2/dataset/common.py
python/paddle/v2/dataset/common.py
+7
-0
python/paddle/v2/dataset/imdb.py
python/paddle/v2/dataset/imdb.py
+101
-0
python/paddle/v2/dataset/tests/imdb_test.py
python/paddle/v2/dataset/tests/imdb_test.py
+40
-9
未找到文件。
python/paddle/v2/dataset/common.py
浏览文件 @
eb1e34d2
...
...
@@ -32,3 +32,10 @@ def download(url, module_name, md5sum):
shutil
.
copyfileobj
(
r
.
raw
,
f
)
return
filename
def
dict_add
(
a_dict
,
ele
):
if
ele
in
a_dict
:
a_dict
[
ele
]
+=
1
else
:
a_dict
[
ele
]
=
1
python/paddle/v2/dataset/imdb.py
浏览文件 @
eb1e34d2
...
...
@@ -17,3 +17,104 @@
"""
IMDB dataset: http://ai.stanford.edu/%7Eamaas/data/sentiment/aclImdb_v1.tar.gz
"""
import
paddle.v2.dataset.common
import
tarfile
import
Queue
import
re
import
string
import
threading
__all__
=
[
'build_dict'
,
'train'
,
'test'
]
URL
=
'http://ai.stanford.edu/%7Eamaas/data/sentiment/aclImdb_v1.tar.gz'
MD5
=
'7c2ac02c03563afcf9b574c7e56c153a'
# Read files that match pattern. Tokenize and yield each file.
def
tokenize
(
pattern
):
with
tarfile
.
open
(
paddle
.
v2
.
dataset
.
common
.
download
(
URL
,
'imdb'
,
MD5
))
as
tarf
:
# Note that we should use tarfile.next(), which does
# sequential access of member files, other than
# tarfile.extractfile, which does random access and might
# destroy hard disks.
tf
=
tarf
.
next
()
while
tf
!=
None
:
if
bool
(
pattern
.
match
(
tf
.
name
)):
# newline and punctuations removal and ad-hoc tokenization.
yield
tarf
.
extractfile
(
tf
).
read
().
rstrip
(
"
\n\r
"
).
translate
(
None
,
string
.
punctuation
).
lower
().
split
()
tf
=
tarf
.
next
()
def
build_dict
(
pattern
,
cutoff
):
word_freq
=
{}
for
doc
in
tokenize
(
pattern
):
for
word
in
doc
:
paddle
.
v2
.
dataset
.
common
.
dict_add
(
word_freq
,
word
)
# Not sure if we should prune less-frequent words here.
word_freq
=
filter
(
lambda
x
:
x
[
1
]
>
cutoff
,
word_freq
.
items
())
dictionary
=
sorted
(
word_freq
,
key
=
lambda
x
:
(
-
x
[
1
],
x
[
0
]))
words
,
_
=
list
(
zip
(
*
dictionary
))
word_idx
=
dict
(
zip
(
words
,
xrange
(
len
(
words
))))
word_idx
[
'<unk>'
]
=
len
(
words
)
return
word_idx
def
reader_creator
(
pos_pattern
,
neg_pattern
,
word_idx
,
buffer_size
):
UNK
=
word_idx
[
'<unk>'
]
qs
=
[
Queue
.
Queue
(
maxsize
=
buffer_size
),
Queue
.
Queue
(
maxsize
=
buffer_size
)]
def
load
(
pattern
,
queue
):
for
doc
in
tokenize
(
pattern
):
queue
.
put
(
doc
)
queue
.
put
(
None
)
def
reader
():
# Creates two threads that loads positive and negative samples
# into qs.
t0
=
threading
.
Thread
(
target
=
load
,
args
=
(
pos_pattern
,
qs
[
0
],
))
t0
.
daemon
=
True
t0
.
start
()
t1
=
threading
.
Thread
(
target
=
load
,
args
=
(
neg_pattern
,
qs
[
1
],
))
t1
.
daemon
=
True
t1
.
start
()
# Read alternatively from qs[0] and qs[1].
i
=
0
doc
=
qs
[
i
].
get
()
while
doc
!=
None
:
yield
[
word_idx
.
get
(
w
,
UNK
)
for
w
in
doc
],
i
%
2
i
+=
1
doc
=
qs
[
i
%
2
].
get
()
# If any queue is empty, reads from the other queue.
i
+=
1
doc
=
qs
[
i
%
2
].
get
()
while
doc
!=
None
:
yield
[
word_idx
.
get
(
w
,
UNK
)
for
w
in
doc
],
i
%
2
doc
=
qs
[
i
%
2
].
get
()
return
reader
()
def
train
(
word_idx
):
return
reader_creator
(
re
.
compile
(
"aclImdb/train/pos/.*\.txt$"
),
re
.
compile
(
"aclImdb/train/neg/.*\.txt$"
),
word_idx
,
1000
)
def
test
(
word_idx
):
return
reader_creator
(
re
.
compile
(
"aclImdb/test/pos/.*\.txt$"
),
re
.
compile
(
"aclImdb/test/neg/.*\.txt$"
),
word_idx
,
1000
)
python/paddle/v2/dataset/tests/imdb_test.py
浏览文件 @
eb1e34d2
import
paddle.v2.dataset.common
import
tarfile
import
paddle.v2.dataset.imdb
import
unittest
import
re
URL
=
'http://ai.stanford.edu/%7Eamaas/data/sentiment/aclImdb_v1.tar.gz'
MD5
=
'7c2ac02c03563afcf9b574c7e56c153a'
TRAIN_POS_PATTERN
=
re
.
compile
(
"aclImdb/train/pos/.*\.txt$"
)
TRAIN_NEG_PATTERN
=
re
.
compile
(
"aclImdb/train/neg/.*\.txt$"
)
TRAIN_PATTERN
=
re
.
compile
(
"aclImdb/train/.*\.txt$"
)
tarf
=
tarfile
.
open
(
paddle
.
v2
.
dataset
.
common
.
download
(
URL
,
'imdb'
,
MD5
))
TEST_POS_PATTERN
=
re
.
compile
(
"aclImdb/test/pos/.*\.txt$"
)
TEST_NEG_PATTERN
=
re
.
compile
(
"aclImdb/test/neg/.*\.txt$"
)
TEST_PATTERN
=
re
.
compile
(
"aclImdb/test/.*\.txt$"
)
tf
=
tarf
.
next
()
while
tf
!=
None
:
print
tf
.
name
tf
=
tarf
.
next
()
class
TestIMDB
(
unittest
.
TestCase
):
word_idx
=
None
def
test_build_dict
(
self
):
if
self
.
word_idx
==
None
:
self
.
word_idx
=
paddle
.
v2
.
dataset
.
imdb
.
build_dict
(
TRAIN_PATTERN
,
150
)
self
.
assertEqual
(
len
(
self
.
word_idx
),
7036
)
def
check_dataset
(
self
,
dataset
,
expected_size
):
if
self
.
word_idx
==
None
:
self
.
word_idx
=
paddle
.
v2
.
dataset
.
imdb
.
build_dict
(
TRAIN_PATTERN
,
150
)
sum
=
0
for
l
in
dataset
(
self
.
word_idx
):
self
.
assertEqual
(
l
[
1
],
sum
%
2
)
sum
+=
1
self
.
assertEqual
(
sum
,
expected_size
)
def
test_train
(
self
):
self
.
check_dataset
(
paddle
.
v2
.
dataset
.
imdb
.
train
,
25000
)
def
test_test
(
self
):
self
.
check_dataset
(
paddle
.
v2
.
dataset
.
imdb
.
test
,
25000
)
if
__name__
==
'__main__'
:
unittest
.
main
()
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