PyThaiNLP/pythainlp-v3.0.7.zip
PyThaiNLP-pythainlp-bcc596e
.github
ISSUE_TEMPLATE
feature_request.md
611 Bytes
issue_report.md
1.2 kB
pull_request_template.md
480 Bytes
workflows
codeql-analysis.yml
2.4 kB
deploy_docs.yml
1.1 kB
lint.yml
1.3 kB
macos-test.yml
1.4 kB
pypi-publish.yml
729 Bytes
pypi-test.yml
1.0 kB
test.yml
1.0 kB
.gitignore
1.4 kB
.pyup.yml
357 Bytes
CODE_OF_CONDUCT.md
3.4 kB
CONTRIBUTING.md
7.1 kB
Dockerfile
361 Bytes
INTHEWILD.md
433 Bytes
LICENSE
11.4 kB
MANIFEST.in
167 Bytes
Makefile
1.9 kB
README.md
10.2 kB
README_TH.md
15.4 kB
SECURITY.md
306 Bytes
appveyor.yml
5.6 kB
docker_requirements.txt
446 Bytes
docs
Makefile
607 Bytes
api
augment.rst
658 Bytes
benchmarks.rst
655 Bytes
corpus.rst
2.5 kB
generate.rst
333 Bytes
soundex.rst
1.0 kB
spell.rst
708 Bytes
summarize.rst
191 Bytes
tag.rst
15.3 kB
tokenize.rst
2.1 kB
tools.rst
340 Bytes
translate.rst
543 Bytes
transliterate.rst
1.2 kB
ulmfit.rst
734 Bytes
util.rst
1.4 kB
wangchanberta.rst
1.7 kB
word_vector.rst
670 Bytes
build_docs.sh
22 Bytes
clean_directory.sh
1.7 kB
conf.py
7.0 kB
images
evaluation.png
83.9 kB
logo.png
12.5 kB
index.rst
1.1 kB
notes
FAQ.rst
140 Bytes
command_line.rst
4.0 kB
getting_started.rst
2.2 kB
installation.rst
4.0 kB
license.rst
1.5 kB
notebooks
clean-dict.ipynb
3.4 kB
pythainlp
__init__.py
1.7 kB
__main__.py
838 Bytes
augment
__init__.py
126 Bytes
lm
__init__.py
220 Bytes
fasttext.py
2.5 kB
wangchanberta.py
2.9 kB
word2vec
__init__.py
280 Bytes
bpemb_wv.py
1.8 kB
core.py
2.1 kB
ltw2v.py
1.6 kB
thai2fit.py
1.6 kB
wordnet.py
5.9 kB
benchmarks
__init__.py
145 Bytes
word_tokenization.py
7.6 kB
cli
__init__.py
544 Bytes
benchmark.py
5.1 kB
data.py
3.8 kB
soundex.py
1.3 kB
tag.py
2.1 kB
tokenize.py
5.0 kB
corpus
__init__.py
2.1 kB
common.py
7.7 kB
conceptnet.py
4.0 kB
core.py
14.1 kB
corpus_license.md
4.9 kB
countries_th.txt
7.6 kB
crfchunk_orchidpp.model
1.0 MB
default_db.json
748 Bytes
etcc.txt
1.8 MB
family_names_th.txt
260.6 kB
negations_th.txt
23 Bytes
oscar.py
1.7 kB
person_names_female_th.txt
114.0 kB
person_names_male_th.txt
155.0 kB
pos_lst20_perceptron-v0.2.3.json
9.5 MB
pos_orchid_perceptron.json
5.0 MB
pos_orchid_unigram.json
489.8 kB
pos_ud_perceptron-v0.2.json
1.7 MB
pos_ud_unigram-v0.2.json
122.2 kB
sentenceseg_crfcut.model
4.1 MB
stopwords_th.txt
19.9 kB
syllables_th.txt
126.7 kB
thailand_provinces_th.csv
3.5 kB
thainer_crf_1_5_1.model
1.6 MB
tnc.py
2.2 kB
tnc_freq.txt
1.6 MB
ttc.py
1.2 kB
ttc_freq.txt
433.6 kB
util.py
4.5 kB
wordnet.py
14.9 kB
wordnet_th.db
11.2 MB
words_th.txt
1.5 MB
words_th_thai2fit_201810.txt
1.2 MB
generate
__init__.py
171 Bytes
core.py
8.8 kB
thai2fit.py
2.5 kB
soundex
__init__.py
405 Bytes
core.py
2.3 kB
lk82.py
4.0 kB
metasound.py
2.9 kB
udom83.py
2.7 kB
spell
__init__.py
378 Bytes
core.py
5.9 kB
phunspell.py
403 Bytes
pn.py
11.8 kB
symspellpy.py
1.7 kB
tltk.py
228 Bytes
summarize
__init__.py
171 Bytes
core.py
5.5 kB
freq.py
1.8 kB
mt5.py
1.9 kB
tag
__init__.py
573 Bytes
_tag_perceptron.py
9.9 kB
chunk.py
914 Bytes
crfchunk.py
2.2 kB
locations.py
915 Bytes
lst20.py
1.6 kB
named_entity.py
3.6 kB
orchid.py
3.5 kB
perceptron.py
2.0 kB
pos_tag.py
7.4 kB
thainer.py
7.6 kB
tltk.py
3.2 kB
unigram.py
2.4 kB
tokenize
__init__.py
993 Bytes
attacut.py
1.2 kB
core.py
24.0 kB
crfcls.py
2.0 kB
crfcut.py
5.2 kB
deepcut.py
742 Bytes
etcc.py
2.1 kB
longest.py
4.3 kB
multi_cut.py
4.4 kB
nercut.py
2.3 kB
newmm.py
6.8 kB
nlpo3.py
2.1 kB
oskut.py
709 Bytes
pyicu.py
854 Bytes
sefr_cut.py
641 Bytes
ssg.py
271 Bytes
tcc.py
2.1 kB
tltk.py
920 Bytes
tools
__init__.py
365 Bytes
misspell.py
3.9 kB
path.py
1.9 kB
translate
__init__.py
260 Bytes
core.py
2.6 kB
en_th.py
4.6 kB
th_fr.py
1.6 kB
zh_th.py
2.8 kB
transliterate
__init__.py
262 Bytes
core.py
5.2 kB
ipa.py
462 Bytes
pyicu.py
606 Bytes
royin.py
5.6 kB
spoonerism.py
2.3 kB
thai2rom.py
11.5 kB
thaig2p.py
11.4 kB
tltk.py
457 Bytes
w2p.py
6.5 kB
ulmfit
__init__.py
1.5 kB
core.py
8.4 kB
preprocess.py
9.9 kB
tokenizer.py
2.2 kB
util
__init__.py
2.2 kB
collate.py
1.8 kB
date.py
4.9 kB
digitconv.py
5.2 kB
emojiconv.py
93.4 kB
keyboard.py
6.6 kB
keywords.py
3.6 kB
normalize.py
8.8 kB
numtoword.py
3.1 kB
strftime.py
13.2 kB
thai.py
3.6 kB
thaiwordcheck.py
3.2 kB
time.py
10.0 kB
trie.py
3.6 kB
wordtonum.py
6.5 kB
wangchanberta
__init__.py
207 Bytes
core.py
5.0 kB
postag.py
3.0 kB
word_vector
__init__.py
418 Bytes
core.py
24.5 kB
requirements.txt
80 Bytes
setup.cfg
690 Bytes
setup.py
4.6 kB
tests
__init__.py
295 Bytes
data
input.txt
45 Bytes
sentences.yml
1.3 kB
test.txt
46 Bytes
test_augment.py
1.8 kB
test_benchmarks.py
2.9 kB
test_cli.py
6.1 kB
test_corpus.py
6.9 kB
test_generate.py
2.2 kB
test_misspell.py
2.1 kB
test_soundex.py
2.6 kB
test_spell.py
5.0 kB
test_summarize.py
1.7 kB
test_tag.py
17.3 kB
test_tokenize.py
48.8 kB
test_tools.py
484 Bytes
test_translate.py
2.3 kB
test_transliterate.py
6.3 kB
test_ulmfit.py
9.0 kB
test_util.py
30.2 kB
test_wangchanberta.py
3.3 kB
test_word_vector.py
3.4 kB
tokenization-benchmark.md
5.4 kB
tox.ini
512 Bytes