Machine learning and natural language processing - labs

1. Text mining pipeline

Notebook with all the contents required for this week:

Sample solutions shown in the labs (one of the many possible ok-ish solutions, so for your reference only):

Technical notes on opening the material (a Python notebook):

  • Download the notebook to your drive (physical or Google).
  • In Google Drive, you can use Google Colaboratory to open and work with the notebook (right-click -> Open with Google Colaboratory or similar may be needed on certain browser/OS combinations). Note that you may need to enable Google Suite in your IS account settings to work with Google Colaboratory.
  • Alternatively, feel free to use the Jupyter environment for working with a local copy of the notebook. This should be available on all Linux FI MU machines after adding the Python 3 module (module add python3). Other alternatives like PyCharm are also perfectly fine (you may only need to resolve some dependencies yourself in some labs).