Quantopian's community platform is shutting down. Please read this post for more information and download your code.
Back to Community
Do You Need sklearn?

Greetings Quantopian Community- I'm pretty new to the data science / diy hedge fund world. I have a question I was hoping someone here could answer. The question is: Do I need to use sklearn in order to actually produce a functioning algorithm? - Im a bit confused as to how it's all related. Is it to essentially produce a classifier that is able to distinguish a predefined set in inputs (features & labels) for a desirable outcome? I'm not exactly sure why I see some sample algorithms here: some with sklearn, some not. Can't I just import talib and build an algo without ever using sklearn?

I understand this is a very newbie question, however any input helps me tremendously!

Thank You

Will

1 response

Hi will,

I hope that my response doesn't come too late!

You don't *need * sklearn to have a functioning algorithm. Sklearn is a libraty for machine learning. If the kind of algorithm that you want to implement uses ML, then using sklearn might be a good idea. But you don't need it, and you can find plenty of algorithms in this forum that dont use machine learning!.