TextRank implementation for text summarization and keyword extraction in Python
# This fork is being ported to python 3
- Text summarization
- Keyword extraction
- Text modeling with graph and gexf exportation
Text summarization:
>>> text = """Automatic summarization is the process of reducing a text document with a computer program in order to create a summary that retains the most important points of the original document. As the problem of information overload has grown, and as the quantity of data has increased, so has interest in automatic summarization. Technologies that can make a coherent summary take into account variables such as length, writing style and syntax. An example of the use of summarization technology is search engines such as Google. Document summarization is another.""" >>> from summa import summarizer >>> print summarizer.summarize(text) 'Automatic summarization is the process of reducing a text document with a computer program in order to create a summary that retains the most important points of the original document.'
Keyword extraction:
>>> from summa import keywords >>> print keywords.keywords(text) document automatic summarization technologies technology
This software depends on NumPy and Scipy, two Python packages for scientific computing. You must have them installed prior to installing summa:
pip install summa
If you are going to use the export function, you also need NetworkX. For a better performance of keyword extraction, install Pattern
This version has been tested under Python 2.7
Command-line usage:
cd path/to/folder/summa/ python textrank.py -t FILE
Export:
>>> from summa.export import gexf_export >>> gexf_export(text, path="graph.gexf")
Define length of the summary as a proportion of the text (also available in
keywords
):>>> from summa.summarizer import summarize >>> summarize(text, ratio=0.2)
Define length of the summary by aproximate number of words (also available in
keywords
):>>> summarize(text, words=50)
Define input text language (also available in
keywords
):>>> summarize(text, language='spanish')
The available languages are "danish", "dutch", "english", "finnish", "french", "german", "hungarian", "italian", "norwegian", "porter", "portuguese", "romanian", "russian", "spanish", "swedish"
Get results as a list (also available in
keywords
):>>> summarize(text, split=True) ['Automatic summarization is the process of reducing a text document with a computer program in order to create a summary that retains the most important points of the original document.']
Summa is open source software released under the The MIT License (MIT). Copyright (c) 2014 - now Summa NLP