I want to utilize data science without understanding of mathematics and statistics for business data analysis. I know random forest, linear regression, logistic regression, and xgboost conceptually, but I don't know how to actually utilize them, yet. What's the quickest way to learn how to do basic data science in python and/or clojure?
Thanks.
Another recommendation is to pick up a small project that you are curious about and work on in the open, so you can share your experiments and we may be able to think about together.
Hi. You may try the Noj documentation: https://scicloj.github.io/noj/ Yesterday we ran a couple of workshops on Noj, and the recordings were shared at the Zulip chat (requires login): https://scicloj.github.io/scinoj-light-1/workshop.html https://clojurians.zulipchat.com/#narrow/channel/479601-scinoj-light-1/topic/recordings/
I have a very high-level conceptual understanding, but I don't know how to use ML algorithms, yet.
I'd recommend learning some probability & statistics to be able to reason about uncertainty, bias, sampling, etc.
Is there any quick learning material for aspiring data scientists?
This book by VanderPlas has some nice chapters: https://jakevdp.github.io/PythonDataScienceHandbook/