dragnet-org-dragnet-29923b6
setup.py
4KB
.gitignore
389B
requirements.txt
110B
Makefile
913B
.travis.yml
1KB
Vagrantfile
563B
LICENSE
1KB
provision.sh
697B
env
env_dragnet.yml
132B
scripts
train_and_test_models.py
2KB
README.md
9KB
dragnet
lcs.pyx
3KB
blocks.pyx
31KB
compat.py
9KB
model_training.py
10KB
data_processing.py
16KB
__init__.py
1KB
extractor.py
9KB
util.py
6KB
features
weninger.py
4KB
_weninger.pyx
2KB
kohlschuetter.py
1KB
__init__.py
825B
css.py
2KB
standardized.py
2KB
_readability.cc
4KB
_readability.pyx
2KB
_kohlschuetter.pyx
1KB
readability.py
1KB
pickled_models
py3_sklearn_0.18.0
kohlschuetter_readability_weninger_content_model.pkl.gz
435KB
kohlschuetter_readability_weninger_comments_content_block_errors.txt
337B
kohlschuetter_readability_weninger_comments_content_model.pkl.gz
405KB
kohlschuetter_readability_weninger_content_block_errors.txt
338B
kohlschuetter_readability_weninger_comments_model.pkl.gz
444KB
kohlschuetter_readability_weninger_comments_block_errors.txt
339B
py2_sklearn_0.18.0
kohlschuetter_readability_weninger_content_model.pkl.gz
431KB
kohlschuetter_readability_weninger_comments_content_block_errors.txt
338B
kohlschuetter_readability_weninger_comments_content_model.pkl.gz
408KB
kohlschuetter_readability_weninger_content_block_errors.txt
338B
kohlschuetter_readability_weninger_comments_model.pkl.gz
446KB
kohlschuetter_readability_weninger_comments_block_errors.txt
337B
py2_sklearn_0.15.2_0.17.1
kohlschuetter_readability_weninger_content_model.pkl.gz
433KB
kohlschuetter_readability_weninger_comments_content_block_errors.txt
339B
kohlschuetter_readability_weninger_comments_content_model.pkl.gz
405KB
kohlschuetter_readability_weninger_content_block_errors.txt
339B
kohlschuetter_readability_weninger_comments_model.pkl.gz
444KB
kohlschuetter_readability_weninger_comments_block_errors.txt
339B
py3_sklearn_0.15.2_0.17.1
kohlschuetter_readability_weninger_content_model.pkl.gz
430KB
kohlschuetter_readability_weninger_comments_content_block_errors.txt
338B
kohlschuetter_readability_weninger_comments_content_model.pkl.gz
408KB
kohlschuetter_readability_weninger_content_block_errors.txt
339B
kohlschuetter_readability_weninger_comments_model.pkl.gz
444KB
kohlschuetter_readability_weninger_comments_block_errors.txt
338B
sklearn_0.15.2_0.17.1
kohlschuetter_weninger_readability_content_model.pickle.gz
400KB
kohlschuetter_weninger_readability_content_comments_model.pickle.gz
438KB
sklearn_0.18.0
kohlschuetter_weninger_readability_content_model.pickle.gz
398KB
kohlschuetter_weninger_readability_content_comments_model.pickle.gz
437KB
CHANGES.md
541B
dragnet_www2013.pdf
65KB
test
test_readability.py
921B
test_blocks.py
5KB
test_extractor.py
2KB
test_models.py
3KB
test_lcs.py
395B
test_util.py
2KB
datafiles
block_corrected
page_comments_expected.block_corrected.txt
178B
blank_label.block_corrected.txt
0B
page_no_comments_expected.block_corrected.txt
103B
models_content_mod.json
16KB
Corrected
utf-8_chinese.html.corrected.txt
148B
utf-16.html.corrected.txt
128B
iso-8859-1.html.corrected.txt
64B
page_no_comments.html.corrected.txt
23B
ascii.html.corrected.txt
71B
page_comments.html.corrected.txt
89B
blank_label.corrected.txt
0B
utf-8.html.corrected.txt
64B
models_testing.html
101KB
models_content.json
61KB
readability_features.json
4KB
HTML
blank_label.html
304B
page_for_testing.html
908B
page_no_comments.html
180B
page_comments.html
231B
test_weninger.py
802B
test_kohlschuetter.py
11KB
test_data_processing.py
4KB
MANIFEST.IN
72B
暂无评论