This repository contains materials for the NLP tutorial presented at ODSC West '22 and PyData NYC
In order to run the notebooks here (2 options):
- Download the IMDb sentiment dataset. Untar the file in this directory and you should be able to run everything.
- Download the processed version of the above
blog_notebook This is the notebook from the ODSC blog post
tutorial_notebook_part1 Part 1: Bagging approaches, can be run fairly easily on a local machine
tutorial_notebook_part2 Part 2: Deep Learning approaches, designed for use with GPU, particularly the free one from Google Colab
odsc23_bagtobert.pdf Slides from ODSC East Google slides version
odsc22_bagtobert.pdf Slides from ODSC West Google slides version
pydata_bagtobert.pdf Slides from PyData NYC Google slides version