Natural Language Processing with Python Quick Start Guide

Introducing textacy

Textacy is a very underappreciated set of tools that revolves around spaCy. Its tagline tells you exactly what it does: NLP, before and after spaCy. It implements tools that use spaCy under the hood, ranging from data-streaming utilities for production use to higher level text-clustering functions.

You can install textacy via pip or conda. On conda, it's available on the conda-forge channel instead of the main conda channel. We've done this by adding a -c flag and the channel name after that:

# !conda install -c conda-forge textacy # !pip install textacy

import textacy

Now that we have the set up and have installation out of our way, let's get ready to tackle our challenge in the following section.