A notebook that uses word embeddings and linear algebra to classify comments on OMB's Federal Data Strategy.
In order to open and run these notebooks, you'll need two things.
- Python 3
- Jupyter Notebook
You could get both of these things separately, but I'd recommend downloading Anaconda's Python distribution in order to get both in one go.
Once you've got Anaconda, you'll then need to install some supplementary Python packages. Most of these provide the natural language processing functionality.
spacy
nltk
gensim
beautifulsoup4
pyenchant
contractions
Once you've got Anaconda and the python dependencies listed above, you're ready to open the notebook and run code (assuming you've got the underlying data file.) See these instructions on how to open Juyter.
Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.
- Scott McAllister - Initial work - csmcallister
See the LICENSE.md file for details