I'm trying to learn to use scikit learn
Correct me if I'm wrong, from what I understand (much easier) scikit is
used in this way:
1) instantiate the class for the type of learning / prediction (eg: svm,
IsotonicRegression, LinearRegression etc ...)
2) launch class.fit to learn
3) launch class.predict to predict
The biggest problem I have at the point 1, I understand when to use supervised
learning (classification or regression) and unsupervised, but do not know
which class to instantiate.
I do not have a project in mind, I am interested for educational purposes
and in order to solve this problem I would like to know:
1) you can advise me the best 3 classes for the 3 types of learning (
unsupervised (classification, regression) and unsupervised)?
2) you can recommend a page which explains the various classes and the cases in
which are to be used?