Cost-Complexity pruning of Random Forests ISMM 2017

• Paper, Poster,
• Only Classification tasks have been evaluated.

Datasets

• Download winequality dataset, and other datasets and change utils.py to add new datasets to test out the pruning algorithm.

Todo

• Calculate the test leaves id at the same time as train leaves id
  • Then predict with optimal leaf labeling

New references

• Impact of subsampling and pruning on random forests Paper
• Understanding variable importances in forests of randomized trees Paper