The Open-Source Data Science Masters – Curriculum by Clare Corthell.
An interesting mixture of online courses, books, software tools, etc.
Fully mastering all of the material mentioned would probably equal or exceed an MS in Data Science.
Probably.
I say “probably” because data sets, algorithms, processing models, and the like all have built-in assumptions that impact the results.
In a masters program worthy of the name, the assumptions of common methods of data analysis would be taught, along side how to recognize/discover assumptions in data and/or methodologies.
In lieu of a formal course of that nature, I suggest How to Lie with Statistics by Darrell Huff and How to Lie with Maps by Mark Monmonier.
Data Mining is more general than either of those two works so a “How to Lie with Data Mining” would not be amiss.
Or even a “Data Mining Lies Yearbook (year)” that annotates stories, press releases, articles, presentations with their questionable assumptions and/or choices.
Bearing in mind that incompetence is a far more common explanation of lies than malice.