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
Paddle
提交
0aca438a
P
Paddle
项目概览
PaddlePaddle
/
Paddle
大约 1 年 前同步成功
通知
2298
Star
20931
Fork
5422
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1423
列表
看板
标记
里程碑
合并请求
543
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
1,423
Issue
1,423
列表
看板
标记
里程碑
合并请求
543
合并请求
543
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
0aca438a
编写于
3月 02, 2017
作者:
Q
qingqing01
提交者:
GitHub
3月 02, 2017
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #1510 from qingqing01/srl_dataset
CONLL05 dataset for SRL
上级
e95c2283
5eb79bec
变更
12
隐藏空白更改
内联
并排
Showing
12 changed file
with
344 addition
and
3 deletion
+344
-3
python/paddle/v2/dataset/__init__.py
python/paddle/v2/dataset/__init__.py
+14
-0
python/paddle/v2/dataset/cifar.py
python/paddle/v2/dataset/cifar.py
+14
-0
python/paddle/v2/dataset/common.py
python/paddle/v2/dataset/common.py
+14
-0
python/paddle/v2/dataset/conll05.py
python/paddle/v2/dataset/conll05.py
+205
-0
python/paddle/v2/dataset/imdb.py
python/paddle/v2/dataset/imdb.py
+1
-3
python/paddle/v2/dataset/imikolov.py
python/paddle/v2/dataset/imikolov.py
+13
-0
python/paddle/v2/dataset/mnist.py
python/paddle/v2/dataset/mnist.py
+13
-0
python/paddle/v2/dataset/movielens.py
python/paddle/v2/dataset/movielens.py
+14
-0
python/paddle/v2/dataset/tests/cifar_test.py
python/paddle/v2/dataset/tests/cifar_test.py
+14
-0
python/paddle/v2/dataset/tests/common_test.py
python/paddle/v2/dataset/tests/common_test.py
+14
-0
python/paddle/v2/dataset/tests/imdb_test.py
python/paddle/v2/dataset/tests/imdb_test.py
+14
-0
python/paddle/v2/dataset/tests/mnist_test.py
python/paddle/v2/dataset/tests/mnist_test.py
+14
-0
未找到文件。
python/paddle/v2/dataset/__init__.py
浏览文件 @
0aca438a
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import
mnist
import
imikolov
import
imdb
...
...
python/paddle/v2/dataset/cifar.py
浏览文件 @
0aca438a
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
CIFAR dataset: https://www.cs.toronto.edu/~kriz/cifar.html
"""
import
cPickle
import
itertools
import
numpy
...
...
python/paddle/v2/dataset/common.py
浏览文件 @
0aca438a
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import
requests
import
hashlib
import
os
...
...
python/paddle/v2/dataset/conll05.py
0 → 100644
浏览文件 @
0aca438a
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import
paddle.v2.dataset.common
import
tarfile
import
gzip
import
itertools
__all__
=
[
'test, get_dict'
,
'get_embedding'
]
"""
Conll 2005 dataset. Paddle semantic role labeling Book and demo use this
dataset as an example. Because Conll 2005 is not free in public, the default
downloaded URL is test set of Conll 2005 (which is public). Users can change
URL and MD5 to their Conll dataset.
"""
DATA_URL
=
'http://www.cs.upc.edu/~srlconll/conll05st-tests.tar.gz'
DATA_MD5
=
'387719152ae52d60422c016e92a742fc'
WORDDICT_URL
=
'http://paddlepaddle.bj.bcebos.com/demo/srl_dict_and_embedding/wordDict.txt'
WORDDICT_MD5
=
'ea7fb7d4c75cc6254716f0177a506baa'
VERBDICT_URL
=
'http://paddlepaddle.bj.bcebos.com/demo/srl_dict_and_embedding/verbDict.txt'
VERBDICT_MD5
=
'0d2977293bbb6cbefab5b0f97db1e77c'
TRGDICT_URL
=
'http://paddlepaddle.bj.bcebos.com/demo/srl_dict_and_embedding/targetDict.txt'
TRGDICT_MD5
=
'd8c7f03ceb5fc2e5a0fa7503a4353751'
EMB_URL
=
'http://paddlepaddle.bj.bcebos.com/demo/srl_dict_and_embedding/emb'
EMB_MD5
=
'bf436eb0faa1f6f9103017f8be57cdb7'
UNK_IDX
=
0
def
load_dict
(
filename
):
d
=
dict
()
with
open
(
filename
,
'r'
)
as
f
:
for
i
,
line
in
enumerate
(
f
):
d
[
line
.
strip
()]
=
i
return
d
def
corpus_reader
(
data_path
,
words_name
,
props_name
):
"""
Read one corpus. It returns an iterator. Each element of
this iterator is a tuple including sentence and labels. The sentence is
consist of a list of word IDs. The labels include a list of label IDs.
:return: a iterator of data.
:rtype: iterator
"""
def
reader
():
tf
=
tarfile
.
open
(
data_path
)
wf
=
tf
.
extractfile
(
words_name
)
pf
=
tf
.
extractfile
(
props_name
)
with
gzip
.
GzipFile
(
fileobj
=
wf
)
as
words_file
,
gzip
.
GzipFile
(
fileobj
=
pf
)
as
props_file
:
sentences
=
[]
labels
=
[]
one_seg
=
[]
for
word
,
label
in
itertools
.
izip
(
words_file
,
props_file
):
word
=
word
.
strip
()
label
=
label
.
strip
().
split
()
if
len
(
label
)
==
0
:
# end of sentence
for
i
in
xrange
(
len
(
one_seg
[
0
])):
a_kind_lable
=
[
x
[
i
]
for
x
in
one_seg
]
labels
.
append
(
a_kind_lable
)
if
len
(
labels
)
>=
1
:
verb_list
=
[]
for
x
in
labels
[
0
]:
if
x
!=
'-'
:
verb_list
.
append
(
x
)
for
i
,
lbl
in
enumerate
(
labels
[
1
:]):
cur_tag
=
'O'
is_in_bracket
=
False
lbl_seq
=
[]
verb_word
=
''
for
l
in
lbl
:
if
l
==
'*'
and
is_in_bracket
==
False
:
lbl_seq
.
append
(
'O'
)
elif
l
==
'*'
and
is_in_bracket
==
True
:
lbl_seq
.
append
(
'I-'
+
cur_tag
)
elif
l
==
'*)'
:
lbl_seq
.
append
(
'I-'
+
cur_tag
)
is_in_bracket
=
False
elif
l
.
find
(
'('
)
!=
-
1
and
l
.
find
(
')'
)
!=
-
1
:
cur_tag
=
l
[
1
:
l
.
find
(
'*'
)]
lbl_seq
.
append
(
'B-'
+
cur_tag
)
is_in_bracket
=
False
elif
l
.
find
(
'('
)
!=
-
1
and
l
.
find
(
')'
)
==
-
1
:
cur_tag
=
l
[
1
:
l
.
find
(
'*'
)]
lbl_seq
.
append
(
'B-'
+
cur_tag
)
is_in_bracket
=
True
else
:
raise
RuntimeError
(
'Unexpected label: %s'
%
l
)
yield
sentences
,
verb_list
[
i
],
lbl_seq
sentences
=
[]
labels
=
[]
one_seg
=
[]
else
:
sentences
.
append
(
word
)
one_seg
.
append
(
label
)
pf
.
close
()
wf
.
close
()
tf
.
close
()
return
reader
def
reader_creator
(
corpus_reader
,
word_dict
=
None
,
predicate_dict
=
None
,
label_dict
=
None
):
def
reader
():
for
sentence
,
predicate
,
labels
in
corpus_reader
():
sen_len
=
len
(
sentence
)
verb_index
=
labels
.
index
(
'B-V'
)
mark
=
[
0
]
*
len
(
labels
)
if
verb_index
>
0
:
mark
[
verb_index
-
1
]
=
1
ctx_n1
=
sentence
[
verb_index
-
1
]
else
:
ctx_n1
=
'bos'
if
verb_index
>
1
:
mark
[
verb_index
-
2
]
=
1
ctx_n2
=
sentence
[
verb_index
-
2
]
else
:
ctx_n2
=
'bos'
mark
[
verb_index
]
=
1
ctx_0
=
sentence
[
verb_index
]
if
verb_index
<
len
(
labels
)
-
1
:
mark
[
verb_index
+
1
]
=
1
ctx_p1
=
sentence
[
verb_index
+
1
]
else
:
ctx_p1
=
'eos'
if
verb_index
<
len
(
labels
)
-
2
:
mark
[
verb_index
+
2
]
=
1
ctx_p2
=
sentence
[
verb_index
+
2
]
else
:
ctx_p2
=
'eos'
word_idx
=
[
word_dict
.
get
(
w
,
UNK_IDX
)
for
w
in
sentence
]
pred_idx
=
[
predicate_dict
.
get
(
predicate
)]
*
sen_len
ctx_n2_idx
=
[
word_dict
.
get
(
ctx_n2
,
UNK_IDX
)]
*
sen_len
ctx_n1_idx
=
[
word_dict
.
get
(
ctx_n1
,
UNK_IDX
)]
*
sen_len
ctx_0_idx
=
[
word_dict
.
get
(
ctx_0
,
UNK_IDX
)]
*
sen_len
ctx_p1_idx
=
[
word_dict
.
get
(
ctx_p1
,
UNK_IDX
)]
*
sen_len
ctx_p2_idx
=
[
word_dict
.
get
(
ctx_p2
,
UNK_IDX
)]
*
sen_len
label_idx
=
[
label_dict
.
get
(
w
)
for
w
in
labels
]
yield
word_idx
,
pred_idx
,
ctx_n2_idx
,
ctx_n1_idx
,
\
ctx_0_idx
,
ctx_p1_idx
,
ctx_p2_idx
,
mark
,
label_idx
return
reader
()
def
get_dict
():
word_dict
=
load_dict
(
common
.
download
(
WORDDICT_URL
,
'conll05st'
,
WORDDICT_MD5
))
verb_dict
=
load_dict
(
common
.
download
(
VERBDICT_URL
,
'conll05st'
,
VERBDICT_MD5
))
label_dict
=
load_dict
(
common
.
download
(
TRGDICT_URL
,
'conll05st'
,
TRGDICT_MD5
))
return
word_dict
,
verb_dict
,
label_dict
def
get_embedding
():
return
common
.
download
(
EMB_URL
,
'conll05st'
,
EMB_MD5
)
def
test
():
word_dict
,
verb_dict
,
label_dict
=
get_dict
()
reader
=
corpus_reader
(
common
.
download
(
DATA_URL
,
'conll05st'
,
DATA_MD5
),
words_name
=
'conll05st-release/test.wsj/words/test.wsj.words.gz'
,
props_name
=
'conll05st-release/test.wsj/props/test.wsj.props.gz'
)
return
reader_creator
(
reader
,
word_dict
,
verb_dict
,
label_dict
)
if
__name__
==
'__main__'
:
print
get_embedding
()
for
f
in
test
():
print
f
python/paddle/v2/dataset/imdb.py
浏览文件 @
0aca438a
# /usr/bin/env python
# -*- coding:utf-8 -*-
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
...
...
@@ -17,6 +14,7 @@
"""
IMDB dataset: http://ai.stanford.edu/%7Eamaas/data/sentiment/aclImdb_v1.tar.gz
"""
import
paddle.v2.dataset.common
import
tarfile
import
Queue
...
...
python/paddle/v2/dataset/imikolov.py
浏览文件 @
0aca438a
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
imikolov's simple dataset: http://www.fit.vutbr.cz/~imikolov/rnnlm/
"""
...
...
python/paddle/v2/dataset/mnist.py
浏览文件 @
0aca438a
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
MNIST dataset.
"""
...
...
python/paddle/v2/dataset/movielens.py
浏览文件 @
0aca438a
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import
zipfile
from
common
import
download
import
re
...
...
python/paddle/v2/dataset/tests/cifar_test.py
浏览文件 @
0aca438a
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import
paddle.v2.dataset.cifar
import
unittest
...
...
python/paddle/v2/dataset/tests/common_test.py
浏览文件 @
0aca438a
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import
paddle.v2.dataset.common
import
unittest
import
tempfile
...
...
python/paddle/v2/dataset/tests/imdb_test.py
浏览文件 @
0aca438a
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import
paddle.v2.dataset.imdb
import
unittest
import
re
...
...
python/paddle/v2/dataset/tests/mnist_test.py
浏览文件 @
0aca438a
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import
paddle.v2.dataset.mnist
import
unittest
...
...
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