Metadata-Version: 2.1
Name: BlueWhale3-Text
Version: 1.6.0
Summary: 用于文本挖掘的蓝鲸附加组件。
Home-page: https://github.com/biolab/orange3-text
Author: 大圣实验楼
Author-email: dashenglab@163.com
License: UNKNOWN
Download-URL: https://github.com/biolab/orange3-text/tarball/1.6.0
Keywords: orange3-text,data mining,orange3 add-on
Platform: UNKNOWN
Description-Content-Type: text/markdown
Requires-Dist: BlueWhale3 (>=3.28.0)
Requires-Dist: anyqt
Requires-Dist: beautifulsoup4
Requires-Dist: biopython
Requires-Dist: bluewhale-widget-base (>=4.12.0)
Requires-Dist: conllu
Requires-Dist: docx2txt (>=0.6)
Requires-Dist: gensim (==4.1.2)
Requires-Dist: lemmagen3
Requires-Dist: lxml
Requires-Dist: nltk (>=3.0.5)
Requires-Dist: numpy
Requires-Dist: odfpy (==1.4.1)
Requires-Dist: pandas
Requires-Dist: pdfminer3k (==1.3.4)
Requires-Dist: pyqtgraph
Requires-Dist: pyyaml
Requires-Dist: requests
Requires-Dist: scikit-learn
Requires-Dist: scipy
Requires-Dist: serverfiles
Requires-Dist: simhash (>=2.1.1)
Requires-Dist: six
Requires-Dist: tweepy (>=4.0.0)
Requires-Dist: ufal.udpipe (==1.2.0.3)
Requires-Dist: wikipedia
Requires-Dist: yake
Provides-Extra: doc
Requires-Dist: sphinx ; extra == 'doc'
Requires-Dist: recommonmark ; extra == 'doc'
Requires-Dist: sphinx-rtd-theme ; extra == 'doc'
Requires-Dist: docutils (<0.17) ; extra == 'doc'
Provides-Extra: test
Requires-Dist: coverage ; extra == 'test'

BlueWhale3 Text
============

Orange add-on for text mining. It provides access to publicly available data,
like NY Times, Twitter and PubMed. Further, it provides tools for preprocessing,
constructing vector spaces (like bag-of-words, topic modeling and word2vec) and
visualizations like word cloud end geo map. All features can be combined with
powerful data mining techniques from the Orange data mining framework.

See [documentation](http://orange3-text.readthedocs.org/).

Features
--------
#### Access to data
* Load a corpus of text documents
* Access publicly available data (The Guardian, NY Times, Twitter, Wikipedia, PubMed)

#### Text analysis
* Preprocess corpus
* Generate bag of words
* Embed documents into vector space
* Perform sentiment analysis
* Detect emotions in tweets
* Discover topics in the text
* Compute document statistics
* Visualize frequent words in the word cloud
* Find words that enrich selected documents

