This is the first big learning unit of the text classification specialization. It will introduce you to common tools used when dealing with natural language processing problems.
We will focus on how to extract and process features from raw text. The objective is to prepare you for the hackathon, so you can see the exercises as a small scale version of the processing you might do in the hackathon.
If you are able to solve this BLU, you should be familiar with several basic techniques of text processing and feature extraction :)
As in the previous BLUs, go through the Learning Notebooks (they are in the Learning Notebooks folder), then do the Exercise notebook, and submit it on the portal.
You can and should ask for help, be it about Learning Notebooks, Exercises, or anything else. Please checkout the How to Ask for Help, and remember not to share code when asking for help about the exercises!
This repo is completely open source and is continuously improving over time. When you spot a mistake, please check whether it has been detected in the issues. If it hasn't, please open an issue, explaining in details where it is (e.g. in what notebook, and on what line), and how to reproduce the error. If it is an easy fix, feel free to make a pull request.