Skip to main content

CWordTM: Towards a Topic Modeling Toolkit from Low-Code to Pro-Code

Project description

A Topic Modeling Toolkit from Low-code to Pro-code

Installation

$ pip install cwordtm

Usage

cwordtm can be used to perform some NLP pre-processing tasks, text exploration, including Chinese one, text visualization (word cloud), and topic modeling (BERTopic, LDA and NMF) as follows:

from cwordtm import meta, util, ta, tm, viz, pivot, quot

version Submodule

Provides some version information.

import cwordtm
print(cwordtm.__version__)

meta Submodule

Provides extracting source code of cwordtm module and adding timing and code-showing features to all functions of the module.

print(meta.get_module_info())

print(meta.get_submodule_info('viz', detailed=True))

quot Submodule

Provides functions to extract the quotation source Scripture in OT based on the presribed NT Scripture.

cdf = util.load_word('cuv.csv')
crom8 = util.extract2(cdf, 'Rom 8')

quot.show_quot(crom8, lang='chi')

pivot Submodule

Provides a pivot table of the prescribed text.

cdf = util.load_word('cuv.csv')

pivot.stat(cdf, chi=True)

ta Submodule

Provides text analytics functions, including extracting the summarization of the prescribed text.

cdf = util.load_word('cuv.csv')
crom8 = util.extract2(cdf, 'Rom 8')

ta.summary_chi(crom8)

tm Submodule

Provides text modeling functions, including LDA, NMF and BERTopics modeling.

lda = tm.lda_process("web.csv", eval=True, timing=True)

nmf = tm.nmf_process("web.csv", eval=True, code=1)

btm = tm.btm_process("cuv.csv", chi=True, cat='ot', eval=True)

btm = tm.btm_process("cuv.csv", chi=True, cat='nt', eval=True, code=2)

util Submodule

Provides loading text and text preprocessing functions.

df = util.load_word()
cdf = util.load_word('cuv.csv')

df.head()
cdf.head()

rom8 = util.extract2(df, 'Rom 8')
crom8 = util.extract2(cdf, 'Rom 8')

viz Submodule

Wordcloud plotting from the prescribed text.

cdf = util.load_word('cuv.csv')

viz.chi_wordcloud(cdf)

Demo

Usage demo file with output:

  1. On BBC News: CWordTM_BBC.pdf

  2. On Chinese Bible (CUV): CWordTM_CUV.pdf

Contributing

Interested in contributing? Check out the contributing guidelines. Please note that this project is released with a Code of Conduct. By contributing to this project, you agree to abide by its terms.

License

cwordtm was created by Dr. Johnny Cheng. It is licensed under the terms of the MIT license.

Credits

cwordtm was created under the guidance of Jehovah, the Almighty God.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cwordtm-0.6.2.tar.gz (18.2 MB view details)

Uploaded Source

Built Distribution

cwordtm-0.6.2-py3-none-any.whl (18.3 MB view details)

Uploaded Python 3

File details

Details for the file cwordtm-0.6.2.tar.gz.

File metadata

  • Download URL: cwordtm-0.6.2.tar.gz
  • Upload date:
  • Size: 18.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.9

File hashes

Hashes for cwordtm-0.6.2.tar.gz
Algorithm Hash digest
SHA256 e311784fb8e523f8ec5553bec3291944bd53087d48fd3072e753cd98920b28f4
MD5 4a4c6f8519c3e687ac2da6f82f66de2d
BLAKE2b-256 65e1b143070557eca5860f2e110aa192954594fcda918b6088145195bdcd14ff

See more details on using hashes here.

File details

Details for the file cwordtm-0.6.2-py3-none-any.whl.

File metadata

  • Download URL: cwordtm-0.6.2-py3-none-any.whl
  • Upload date:
  • Size: 18.3 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.9

File hashes

Hashes for cwordtm-0.6.2-py3-none-any.whl
Algorithm Hash digest
SHA256 1c6a41b9aaa104be926f8a8c242459cb66bba5baed8f7151fa6f8e9a4d4e01a2
MD5 a13391f03e8f1ab05ca307b0726f87f1
BLAKE2b-256 4192107e7d4ede4415fa0b15868ba0bdefb14f05ee656476a978e6f17b159452

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page