Hey all,
This was posed as a question at Stack Overflow and I'm answering here.
Write-ups on Document Term Matrices (DTMs) are easily found on Google, and borrowing from a discussion for both R and Python here, I've created a DTM using simple Alteryx tools in the attached workflow. The example there utilizes the text from all Inaugural addresses, which is included in my attachment. Basically, I just split the terms based on various non-numeric characters, then summarized and transposed in two different ways (by year, or president). You can also transpose by word to get a more formal DTM, however that's very wide and will not display nicely due to that width.
Anyway, it's a start - hope it helps anyone pursuing DTM with raw Alteryx tools.
- John
Solved! Go to Solution.
