Metadata-Version: 2.1
Name: muldichinese
Version: 0.3
Summary: A Chinese register analyser.
Home-page: https://github.com/Nannan-Liu/Multidimensional-Analysis-Tagger-of-Mandarin-Chinese
Author: Nannan Liu
Author-email: liunannan.bfsumun@gmail.com
License: GNU
Keywords: muldichinese,multidimensional,register,chinese,segmentation,nlp
Platform: UNKNOWN
Classifier: Programming Language :: Python
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Natural Language :: Chinese (Simplified)
Classifier: Natural Language :: Chinese (Traditional)
Classifier: Operating System :: MacOS :: MacOS X
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: POSIX :: Linux
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Education
Classifier: Topic :: Text Processing :: Linguistic
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: nltk
Requires-Dist: PyNLPIR
Requires-Dist: scikit-learn
Requires-Dist: numpy
Requires-Dist: pandas

<h1 id="multidimensional-analysis-tagger-of-mandarin-chinese">Multidimensional-Analysis-Tagger-of-Mandarin-Chinese</h1>
<p>MulDi Chinese (IPA: [ˌmʌl'daɪ] [ˌtʃaɪˈniːz]) is a multidimensional analysis tagger of Mandarin Chinese. 

 - Installation: `pip install muldichinese` 

<h2 id="About">About</h2>
Check the names of your input texts, pos tag the texts, and get the distribution of linguistic features and dimensions of register variation in them

    from muldichinese import MulDiChinese
    mdc=MulDiChinese('/write/path/to/your/file(s)/')
    mdc.pos()
    POS tagging completed.
    mdc.features()
    Standarised frequencies of all 53 features written.
    mdc.dimensions()
    Dimension scores written.

<h2 id="referencing-the-tagger">Reference the tagger</h2>
Liu, N. 2019. Multidimensional Analysis Tagger of Mandarin Chinese. Available at: <a href="https://github.com/Nannan-Liu/Multidimensional-Analysis-Tagger-of-Mandarin-Chinese">https://github.com/Nannan-Liu/Multidimensional-Analysis-Tagger-of-Mandarin-Chinese</a>.</p>
<p>This programme is based on the ICTCLAS, and it is advised to reference ICTCLAS when MulDi Chinese is used. Please refer to <a href="https://dl.acm.org/citation.cfm?id=1119280">https://dl.acm.org/citation.cfm?id=1119280</a>.</p>
<h2 id="requirements">Requirements</h2>
<p>Python packages needed are:

 1. <a href="https://pypi.org/project/PyNLPIR">PyNLPIR</a>
 2. <a href="https://www.nltk.org/#">NLTK</a>
 3. <a href="https://pandas.pydata.org/">Pandas</a>
 4. <a href="https://scikit-learn.org/stable/">scikit learn</a>
 5. <a href="https://numpy.org/">NumPy</a>

</p>
<h2 id="see-manual.pdf-for-more-details">See MulDi Chinese manual.pdf for more details</h2>
<p>The manual contains a detailed description of the 53 features.</p>

