Skip to content
Go to file

Latest commit


Git stats


Failed to load latest commit information.
Latest commit message
Commit time

Intro to Natural Language Processing in Python with NLTK and Scikit-learn

Requirements: Get the Anaconda Python Distribution (preferably Python 3.4) This is a super helpful distribution that packages up everything you'll need to do scientific research using Python


  1. Go here:
  2. Click the "Download Anaconda" button on the top right of the page
  3. Enter your email address. Don't worry it's completely free.
  4. Once you enter it you are redirected to
  5. Hit the "I want Python 3.4*" button on the white box labeled "Choose your Installer"
  6. Select the platform you want to install for (Linux, Windows, Mac, etc)
  7. You should be provided with the download. Follow their instructions to install.

Okay! You are all set.

Now, for this tutorial, we're going to be using Ipython Notebook which is a really neat, interactive way to learn Python. Ipython by itself is a powerful command line shell for interactive development. Ipython notebook is a browser-based interactive environment to get pretty graphs and such.

  1. From the command line (cmd) or terminal navigate to where this readme and .ipynb file is.
  2. execute "ipython notebook Intro_Python_NLP"
  3. Your browser should pop up with the notebook tutorial
  4. Follow along, hit the arrow labeled "Run cell" to run the contents of the cell.
  5. Feel free to modify any of the code to test things out and see what happens.



An Introduction to Natural Language Processing in Python with NLTK and Scikit-learn



No releases published
You can’t perform that action at this time.