Package
weka.classifiers.trees
Synopsis
Class for building a best-first decision tree classifier. This class uses binary split for both nominal and numeric attributes. For missing values, the method of 'fractional' instances is used.
For more information, see:
Haijian Shi (2007). Best-first decision tree learning. Hamilton, NZ.
Jerome Friedman, Trevor Hastie, Robert Tibshirani (2000). Additive logistic regression : A statistical view of boosting. Annals of statistics. 28(2):337-407.
Available in Weka 3.6.x - 3.7.1. Available via the package management system for Weka >= 3.7.2 (bestFirstTree).
Options
The table below describes the options available for BFTree.
Option | Description |
|---|---|
debug | If set to true, classifier may output additional info to the console. |
heuristic | If heuristic search is used for binary split for nominal attributes. |
minNumObj | Set minimal number of instances at the terminal nodes. |
numFoldsPruning | Number of folds in internal cross-validation. |
pruningStrategy | Sets the pruning strategy. |
seed | The random number seed to be used. |
sizePer | The percentage of the training set size (0-1, 0 not included). |
useErrorRate | If error rate is used as error estimate. if not, root mean squared error is used. |
useGini | If true the Gini index is used for splitting criterion, otherwise the information is used. |
useOneSE | Use the 1SE rule to make pruning decision. |
Capabilities
The table below describes the capabilites of BFTree.
Capability | Supported |
|---|---|
Class | Binary class, Nominal class |
Attributes | Unary attributes, Binary attributes, Empty nominal attributes, Nominal attributes, Missing values, Numeric attributes |
Min # of instances | 1 |