2012/9/4 Sheila the angel <[email protected]>: > Hello, > I would like to know what are the native multiclass classification > algorithms in Sklearn. > For example SVM are basically binary classification algorithm while Tree > methods are Multiclass algorithm (not sure about this).
It all depends on what you call "naturally". Why do you need this? All implementations of classifiers in scikit-learn can accept multi-class targets by default (some of them use a family of binary models with a one-vs-all or one-vs-the-rest scheme internally). Individual models docstrings give more details. If I remember correctly only the tree-based algorithm and nearest neighbors / centroid related classifiers are "naturally" multiclass. But this is more a theoretical distinction rather than an implementation-specific consideration, hence not specific to scikit-learn. -- Olivier http://twitter.com/ogrisel - http://github.com/ogrisel ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
