In this tutorial we'll dive in topic mining. We'll analyze a dataset of newsfeeds extracted from more than 60 sources thanks to a web service called newsapi.org .
We'll show how to process this text data, analyze it and automatically extract visual clusters of topics from it.
We'll show how to put in practice great python tools for interactive visualization, topic mining and text analytics: scikit-learn, gensim for the modeling, Bokeh and PyLDAvis for the plots.
All the code is available to you to run and test.
In this tutorial, I'll be using python 2.7
One thing I recommend is downloading the Anaconda distribution for python 2.7 from this link. This distribution wraps python with the necessary packages used in data science like Numpy, Pandas, Scipy or Scikit-learn.
pip install tqdm conda install -c anaconda nltk=3.2.2 conda install bokeh pip install --upgrade gensim pip install pyldavis pip install wordcloud
If you have any question or recommendation regarding the content of this article, please refer to the website's comment section.