MOA_classification_activelearning: MOA active learning classification

Description Usage Arguments Value See Also Examples

Description

MOA active learning classification

Usage

1

Arguments

control

an object of class MOAmodelOptions as obtained by calling MOAoptions

...

options of parameters passed on to MOAoptions, in case control is left to NULL. Ignored if control is supplied

Value

An object of class MOA_classifier which sets up an untrained MOA model, which can be trained using trainMOA

See Also

MOAoptions, trainMOA

Examples

1
2
3
ctrl <- MOAoptions(model = "ActiveClassifier")
mymodel <- ActiveClassifier(control=ctrl)
mymodel

Example output

Loading required package: RMOAjars
OpenJDK 64-Bit Server VM warning: Can't detect initial thread stack location - find_vma failed
Loading required package: rJava
ActiveClassifier modelling options: 
MOA model name: Active learning classifier for evolving data streams
  - baseLearner: drift.SingleClassifierDrift   (Classifier to train.)
  - activeLearningStrategy: Random   (Active Learning Strategy to use.)
  - budget: 0.1   (Budget to use.)
  - fixedThreshold: 0.9   (Fixed threshold.)
  - step: 0.01   (Floating budget step.)
  - numInstancesInit: 0   (Number of instances at beginning without active learning.)
  - randomSeed: 1   (Seed for random behaviour of the classifier.)

RMOA documentation built on May 29, 2017, 8:58 p.m.