DataTriad NLP Project

This repo is for the DataTriad NLP project. This is a work in progress.

Downloading the data

Because of the large size of the data files they are not included in the repo and they need to be downloaded. To do this create a data directory, the .gitignore file is set to ignore the data directory so anything included here won't be added to git, then download and unzip the files from here into the newly created data directory.

using the program

For help on what you can do run:

stacksample --help

For help on a specific section (for example training) run:

stacksample train --help