Synopsis
Learns a single decision tree. For each split only a random subset of attributes is available.
Description
This operator learns decision trees from both nominal and numerical data. Decision trees are powerful classification methods which often can also easily be understood. The random tree learner works similar to Quinlan's C4.5 or CART but it selects a random subset of attributes before it is applied. The size of the subset is defined by the parameter subset_ratio.
Input
- training set: expects: ExampleSet
Output
- model:
- exampleSet:
Parameters
- criterion: Specifies the used criterion for selecting attributes and numerical splits.
- minimal size for split: The minimal size of a node in order to allow a split.
- minimal leaf size: The minimal size of all leaves.
- minimal gain: The minimal gain which must be achieved in order to produce a split.
- maximal depth: The maximum tree depth (-1: no bound)
- confidence: The confidence level used for the pessimistic error calculation of pruning.
- number of prepruning alternatives: The number of alternative nodes tried when prepruning would prevent a split.
- no pre pruning: Disables the pre pruning and delivers a tree without any prepruning.
- no pruning: Disables the pruning and delivers an unpruned tree.
- guess subset ratio: Indicates that log(m) + 1 features are used, otherwise a ratio has to be specified.
- subset ratio: Ratio of randomly chosen attributes to test
- use local random seed: Indicates if a local random seed should be used.
- local random seed: Specifies the local random seed