CODEWITHSUNDEEP
pythonalgorithmdecision-tree
pmarini
pmarini

Reputation: 121

sklearn DecisionTreeClassifier: which is the optmized Cart algorithm implementation?

according to the online sklearn documentation (v0.14), the growth of a tree classifier is done via an "optimized version of the CART algorithm". Do someone know the details about such implementation? I'm writing an homemade Cart training algorithm, and my version is at best 20 times slower given the same input.

Thank you for sharing any information

Pietro

Upvotes: 1

Views: 1235

Answers (1)

damienfrancois
damienfrancois

Reputation: 59110

Apparently, from the comments in the source, it is the CART algorithm with some added features borrowed from classics from the litterature:

  • L. Breiman, J. Friedman, R. Olshen, and C. Stone, "Classification and Regression Trees", Wadsworth, Belmont, CA, 1984.

  • T. Hastie, R. Tibshirani and J. Friedman. "Elements of Statistical Learning", Springer, 2009.

  • L. Breiman, and A. Cutler, "Random Forests", http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm

Upvotes: 2

Related Questions