Word-frequency from job descriptions and my résumé, cover letter, etc. All this will make job applications better, because I can make sure we have a good match. This is supposed to be zeroth order - later we can use word-to-vec, ngram-to-vec, document-to-vec, or other things.
The version of the notebook here on GitHub that is easy to navigate is at this branch, not here in the main branch. My suggestion is to check things out in the CoLab version of the notebook. That (CoLab) version is meant to be one where you can see input and output. Getting files, etc. onto the CoLab machine would be a bit difficult.
This is part 4, which is the most interesting. If you have the time and the inclination, part 3 is the next one I'd suggest. After that, I'd suggest you start at the beginning. All parts are linked below. Note that here, as with the other Google CoLab Notebooks, the point is to give a notebook with the input and the output. For some, you might be able to re-do the code running. For others, the versions of Python and the libraries won't be compatible. You can see the MyBinder versions for those.
You can use the MyBinder Version, too. Make sure to use the links to go from one part to another, e.g. use the part 2 binder badge that is visible in the part 1 notebook to go from 1 to 2. There is a little finesse in making sure that things created in part 1 will be available in part 2, things created in part 2 available in part 3, etc. I think that you can start at any part, but I'm not sure. I was able to do it, but I'm not sure I don't have some different settings in the background.
The link below will take you to part 1 of the polished-5part-presented
branch notebook
with just the input.