tokenization (naive way) HD

The video shows naive version of the tokenization by the usage of RegExp, as well as the problems of the aproach. In order to have a better understanding of the material you should have understanding of what is a regular expression (recomended video could be found in the links section). In order to start free temp iPython jupyther notebook server to run the notebook from the video next service can be used: https://tmpnb.org/. In order to start own server please use jupyter project: http://jupyter.org/ Links: Link to the Python notebook: https://storage.googleapis.com/youtube-nlp/s1/e1/tokenization.ipynb Link to the HTML version of the Python notebook: https://storage.googleapis.com/youtube-nlp/s1/e1/tokenization.html Link to the Bible txt file: https://storage.googleapis.com/youtube-nlp/s1/e1/bible.txt Regual expression video: https://www.youtube.com/watch?v=hwDhO1GLb_4&index=2&list=PL4LJlvG_SDpxQAwZYtwfXcQr7kGnl9W93