Flow
weka.FilteredClassifier_Discretize_J48

weka.FilteredClassifier_Discretize_J48

Visibility: public Uploaded 15-05-2014 by Joaquin Vanschoren Weka_3.7.10 55 runs
0 likes downloaded by 1 people 0 issues 0 downvotes , 1 total downloads
  • Verified_Supervised_Classification
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Weka implementation of FilteredClassifier

Components

Wweka.J48(1)Full name of base classifier. (default: weka.classifiers.trees.J48)
Fweka.Discretize(1)Full class name of filter to use, followed by filter options. eg: "weka.filters.unsupervised.attribute.Remove -V -R 1,2"

Parameters

ALaplace smoothing for predicted probabilities.
BUse binary splits only.
CSet confidence threshold for pruning. (default 0.25)
DIf set, classifier is run in debug mode and may output additional info to the console
FFull class name of filter to use, followed by filter options. eg: "weka.filters.unsupervised.attribute.Remove -V -R 1,2"default: weka.filters.supervised.attribute.Discretize
JDo not use MDL correction for info gain on numeric attributes.
LDo not clean up after the tree has been built.
MSet minimum number of instances per leaf. (default 2)
NSet number of folds for reduced error pruning. One fold is used as pruning set. (default 3)
ODo not collapse tree.
QSeed for random data shuffling (default 1).
RUse reduced error pruning.
SDon't perform subtree raising.
UUse unpruned tree.
WFull name of base classifier. (default: weka.classifiers.trees.J48)default: weka.classifiers.trees.J48

0
Runs

List all runs
Parameter:
Rendering chart
Rendering table