PyThaiNLP: Thai Natural Language Processing in Python

PyThaiNLP published the first version is 0.0.4 to PyPI at 6 years ago, so PyThaiNLP 4.0 will have special codename. The codename for PyThaiNLP 4.0 is PyThaiNLP 4.0 (Real).

See 4.0 Milestone.

Documentation: https://pythainlp.github.io/docs/4.0

Report bug: https://github.com/PyThaiNLP/pythainlp/issues

See PyThaiNLP 4.0 Change Log

If you want to contribute to PyThaiNLP, you can read Contributing to PyThaiNLP.

• Delete all LST20 model #728
• https://github.com/PyThaiNLP/pythainlp/commit/947c7be9ce4199af58ecf042629dda4d752dbcd6 Change pythainlp.tools.misspell to pythainlp.tools.misspell.misspell

• Reduce import time #719
• Fix/broken numeric data format (#652) #723

• Add blackboard cls #732
• Add <Karan> rule to TCC and Change TCC rule for newmm #741

• Add blackboard pos_tag #733
• Add ThaiNER 2.0 #781

• Add pythainlp.util.count_thai_chars #748
• Add thai_strptime and convert_years #767

• Add Thai2Rom ONNX model #743

• add khavee to pythainlp #777
• add aek/too checker function to khavee #779

• Add ud_goeswith #757

• Add new science word #763

• Improve: Reduce import time by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/719
• Create CITATION.cff by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/721
• Fix/broken numeric data format (#652) by @noppayut in https://github.com/PyThaiNLP/pythainlp/pull/723
• Add blackboard pos_tag to cls by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/734
• Update perceptron.py by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/736
• Feature/integrate transliteration dictionary (#681) by @noppayut in https://github.com/PyThaiNLP/pythainlp/pull/735
• Delete all LST20 model by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/728
• Add blackboard cls by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/732
• Add blackboard pos_tag by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/733
• Add style.css: extend docs page width by @LXZE in https://github.com/PyThaiNLP/pythainlp/pull/742
• Add <Karan> rule to TCC and Change TCC rule for newmm by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/741
• Setup action to check for code formatting by @new5558 in https://github.com/PyThaiNLP/pythainlp/pull/746
• Add more test for TCC by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/747
• Add Thai2Rom ONNX model by @new5558 in https://github.com/PyThaiNLP/pythainlp/pull/743
• Add pythainlp.util.count_thai_chars by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/748
• Feature: keyword extraction with keybert and frequency ranking by @noppayut in https://github.com/PyThaiNLP/pythainlp/pull/751
• Add ud_goeswith by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/757
• Bump tensorflow from 2.7.2 to 2.9.3 by @dependabot in https://github.com/PyThaiNLP/pythainlp/pull/758
• Add new science word by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/763
• Add thai_strptime and convert_years by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/767
• Fix typo in thai_full_month_lists for February by @PhakphumV in https://github.com/PyThaiNLP/pythainlp/pull/770
• Add pythainlp.util.phoneme by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/772
• Add remove tone ipa by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/776
• add khavee to pythainlp by @kangkengkhadev in https://github.com/PyThaiNLP/pythainlp/pull/777
• Add khavee docs tests by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/778
• add aek/too checker function to khavee by @HRNPH in https://github.com/PyThaiNLP/pythainlp/pull/779
• Add Thai NER 2.0 by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/781
• Add Copyright to the header files by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/782
• Fixed some issues in Khavee. It's a problem with use อ by @kangkengkhadev in https://github.com/PyThaiNLP/pythainlp/pull/785
• PyThaiNLP 4.0 beta 1 by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/786
• fix some bugs and add check_karu_lahu function by @kangkengkhadev in https://github.com/PyThaiNLP/pythainlp/pull/787
• PyThaiNLP 4.0 Released! by @wannaphong in https://github.com/PyThaiNLP/pythainlp/pull/789

Full Changelog: https://github.com/PyThaiNLP/pythainlp/compare/v3.1.0...v4.0.0

<a href="https://github.com/PyThaiNLP/pythainlp/graphs/contributors"> <img src="https://contributors-img.firebaseapp.com/image?repo=PyThaiNLP/pythainlp" /> </a>

Thanks all the contributors. (Image made with contributors-img)

If you want to contributing to PyThaiNLP, you can read Contributing to PyThaiNLP.

• @LXZE made their first contribution in https://github.com/PyThaiNLP/pythainlp/pull/742
• @new5558 made their first contribution in https://github.com/PyThaiNLP/pythainlp/pull/746
• @PhakphumV made their first contribution in https://github.com/PyThaiNLP/pythainlp/pull/770
• @kangkengkhadev made their first contribution in https://github.com/PyThaiNLP/pythainlp/pull/777
• @HRNPH made their first contribution in https://github.com/PyThaiNLP/pythainlp/pull/779