RWeka (version 0.4-47)

Weka_classifier_meta: R/Weka Meta Learners

Description

R interfaces to Weka meta learners.

Usage

AdaBoostM1(formula, data, subset, na.action,
           control = Weka_control(), options = NULL)
Bagging(formula, data, subset, na.action,
        control = Weka_control(), options = NULL)
LogitBoost(formula, data, subset, na.action,
           control = Weka_control(), options = NULL)
MultiBoostAB(formula, data, subset, na.action,
             control = Weka_control(), options = NULL)
Stacking(formula, data, subset, na.action,
         control = Weka_control(), options = NULL)
CostSensitiveClassifier(formula, data, subset, na.action,
                        control = Weka_control(), options = NULL)

Value

A list inheriting from classes Weka_meta and

Weka_classifiers with components including

classifier

a reference (of class jobjRef) to a Java object obtained by applying the Weka buildClassifier method to build the specified model using the given control options.

predictions

a numeric vector or factor with the model predictions for the training instances (the results of calling the Weka classifyInstance method for the built classifier and each instance).

call

the matched call.

Details

There are a predict method for predicting from the fitted models, and a summary method based on evaluate_Weka_classifier.

AdaBoostM1 implements the AdaBoost M1 method of Freund+Schapire:1996.

Bagging provides bagging Breiman:1996.

LogitBoost performs boosting via additive logistic regression Friedman+Hastie+Tibshirani:2000.

MultiBoostAB implements MultiBoosting Webb:2000, an extension to the AdaBoost technique for forming decision committees which can be viewed as a combination of AdaBoost and “wagging”.

Stacking provides stacking Wolpert:1992.

CostSensitiveClassifier makes its base classifier cost-sensitive.

The model formulae should only use the + and - operators to indicate the variables to be included or not used, respectively.

Argument options allows further customization. Currently, options model and instances (or partial matches for these) are used: if set to TRUE, the model frame or the corresponding Weka instances, respectively, are included in the fitted model object, possibly speeding up subsequent computations on the object. By default, neither is included.

References

Breiman:1996, Freund+Schapire:1996, Friedman+Hastie+Tibshirani:2000, Webb:2000, Witten+Frank:2005, Wolpert:1992

See Also

Weka_classifiers

Examples

## Use AdaBoostM1 with decision stumps.
m1 <- AdaBoostM1(Species ~ ., data = iris,
                 control = Weka_control(W = "DecisionStump"))
table(predict(m1), iris$Species)

summary(m1) # uses evaluate_Weka_classifier()

## Control options for the base classifiers employed by the meta
## learners (apart from Stacking) can be given as follows:
m2 <- AdaBoostM1(Species ~ ., data = iris,
                 control = Weka_control(W = list(J48, M = 30)))