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
OPTHREE
Paddle
提交
812e21f3
P
Paddle
项目概览
OPTHREE
/
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
1
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
1
Issue
1
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
812e21f3
编写于
2月 27, 2017
作者:
W
wen-bo-yang
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
add cross reading sample files and fix bugs
上级
55d19fc4
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
30 addition
and
22 deletion
+30
-22
paddle/setup.py.in
paddle/setup.py.in
+1
-1
paddle/v2/dataset/config.py
paddle/v2/dataset/config.py
+0
-8
python/paddle/v2/dataset/sentiment.py
python/paddle/v2/dataset/sentiment.py
+29
-13
未找到文件。
paddle/setup.py.in
浏览文件 @
812e21f3
...
@@ -72,7 +72,7 @@ setup(name="py_paddle",
...
@@ -72,7 +72,7 @@ setup(name="py_paddle",
packages=['py_paddle'],
packages=['py_paddle'],
include_dirs = include_dirs,
include_dirs = include_dirs,
install_requires = [
install_requires = [
'nltk',
'nltk
>=3.2.2
',
'numpy>=1.8.0', # The numpy is required.
'numpy>=1.8.0', # The numpy is required.
'protobuf>=3.0.0' # The paddle protobuf version
'protobuf>=3.0.0' # The paddle protobuf version
],
],
...
...
paddle/v2/dataset/config.py
已删除
100644 → 0
浏览文件 @
55d19fc4
import
os
__all__
=
[
'DATA_HOME'
]
DATA_HOME
=
os
.
path
.
expanduser
(
'~/.cache/paddle/dataset'
)
if
not
os
.
path
.
exists
(
DATA_HOME
):
os
.
makedirs
(
DATA_HOME
)
paddle/v2/dataset/sentiment.py
→
p
ython/p
addle/v2/dataset/sentiment.py
浏览文件 @
812e21f3
...
@@ -20,9 +20,9 @@ The script fetch and preprocess movie_reviews data set
...
@@ -20,9 +20,9 @@ The script fetch and preprocess movie_reviews data set
that provided by NLTK
that provided by NLTK
"""
"""
import
nltk
import
nltk
import
numpy
as
np
import
numpy
as
np
from
itertools
import
chain
from
nltk.corpus
import
movie_reviews
from
nltk.corpus
import
movie_reviews
from
config
import
DATA_HOME
from
config
import
DATA_HOME
...
@@ -50,9 +50,10 @@ def download_data_if_not_yet():
...
@@ -50,9 +50,10 @@ def download_data_if_not_yet():
except
LookupError
:
except
LookupError
:
print
"Downloading movie_reviews data set, please wait....."
print
"Downloading movie_reviews data set, please wait....."
nltk
.
download
(
'movie_reviews'
,
download_dir
=
DATA_HOME
)
nltk
.
download
(
'movie_reviews'
,
download_dir
=
DATA_HOME
)
print
"Download data set success......"
# make sure that nltk can find the data
# make sure that nltk can find the data
nltk
.
data
.
path
.
append
(
DATA_HOME
)
nltk
.
data
.
path
.
append
(
DATA_HOME
)
print
"Download data set success....."
print
"Path is "
+
nltk
.
data
.
find
(
'corpora/movie_reviews'
).
path
def
get_word_dict
():
def
get_word_dict
():
...
@@ -67,24 +68,39 @@ def get_word_dict():
...
@@ -67,24 +68,39 @@ def get_word_dict():
words_sort_list
=
words_freq
.
items
()
words_sort_list
=
words_freq
.
items
()
words_sort_list
.
sort
(
cmp
=
lambda
a
,
b
:
b
[
1
]
-
a
[
1
])
words_sort_list
.
sort
(
cmp
=
lambda
a
,
b
:
b
[
1
]
-
a
[
1
])
for
index
,
word
in
enumerate
(
words_sort_list
):
for
index
,
word
in
enumerate
(
words_sort_list
):
words_freq_sorted
.
append
(
word
[
0
]
)
words_freq_sorted
.
append
(
(
word
[
0
],
index
+
1
)
)
return
words_freq_sorted
return
words_freq_sorted
def
sort_files
():
"""
Sorted the sample for cross reading the sample
:return:
files_list
"""
files_list
=
list
()
download_data_if_not_yet
()
neg_file_list
=
movie_reviews
.
fileids
(
'neg'
)
pos_file_list
=
movie_reviews
.
fileids
(
'pos'
)
files_list
=
list
(
chain
.
from_iterable
(
zip
(
neg_file_list
,
pos_file_list
)))
return
files_list
def
load_sentiment_data
():
def
load_sentiment_data
():
"""
"""
Load the data set
Load the data set
:return:
:return:
data_set
data_set
"""
"""
label_dict
=
get_label_dic
t
()
data_set
=
lis
t
()
download_data_if_not_yet
()
download_data_if_not_yet
()
words_freq
=
nltk
.
FreqDist
(
w
.
lower
()
for
w
in
movie_reviews
.
words
())
words_ids
=
dict
(
get_word_dict
())
data_set
=
[([
words_freq
[
word
.
lower
()]
for
sample_file
in
sort_files
():
for
word
in
movie_reviews
.
words
(
fileid
)],
words_list
=
list
()
label_dict
[
category
])
category
=
0
if
'neg'
in
sample_file
else
1
for
category
in
movie_reviews
.
categories
()
for
word
in
movie_reviews
.
words
(
sample_file
):
for
fileid
in
movie_reviews
.
fileids
(
category
)]
words_list
.
append
(
words_ids
[
word
.
lower
()])
data_set
.
append
((
words_list
,
category
))
return
data_set
return
data_set
...
@@ -98,9 +114,9 @@ def reader_creator(data):
...
@@ -98,9 +114,9 @@ def reader_creator(data):
train data set or test data set
train data set or test data set
"""
"""
for
each
in
data
:
for
each
in
data
:
sentences
=
np
.
array
(
each
[
0
],
dtype
=
np
.
int32
)
list_of_int
=
np
.
array
(
each
[
0
],
dtype
=
np
.
int32
)
label
s
=
np
.
array
(
each
[
1
],
dtype
=
np
.
int8
)
label
=
each
[
1
]
yield
sentences
,
labels
yield
list_of_int
,
label
def
train
():
def
train
():
...
...
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