ClassificationBaggedEnsemble class -

Classification ensemble grown by resampling

Description

ClassificationBaggedEnsemble combines a set of trained weak learner models and data on which these learners were trained. It can predict ensemble response for new data by aggregating predictions from its weak learners.

Construction

ens = fitensemble(X,Y,'bag',nlearn,learners,'type','classification') creates a bagged classification ensemble. For syntax details, see the fitensemble reference page.

Properties

`CategoricalPredictors`	List of categorical predictors. `CategoricalPredictors` is a numeric vector with indices from `1` to `p`, where `p` is the number of columns of `X`.
`CombineWeights`	String describing how `ens` combines weak learner weights, either `'WeightedSum'` or `'WeightedAverage'`.
`FitInfo`	Numeric array of fit information. The `FitInfoDescription` property describes the content of this array.
`FitInfoDescription`	String describing the meaning of the `FitInfo` array.
`FResample`	Numeric scalar between `0` and `1`. `FResample` is the fraction of training data `fitensemble` resampled at random for every weak learner when constructing the ensemble.
`Method`	String describing the method that creates `ens`.
`ModelParams`	Parameters used in training `ens`.
`NTrained`	Number of trained weak learners in `ens`, a scalar.
`PredictorNames`	Cell array of names for the predictor variables, in the order in which they appear in `X`.
`ReasonForTermination`	String describing the reason `fitensemble` stopped adding weak learners to the ensemble.
`Replace`	Logical value indicating if the ensemble was trained with replacement (`true`) or without replacement (`false`).
`ResponseName`	String with the name of the response variable `Y`.
`ScoreTransform`	Function handle for transforming scores, or string representing a built-in transformation function. `'none'` means no transformation; equivalently, `'none'` means `@(x)x`. For a list of built-in transformation functions and the syntax of custom transformation functions, see `ClassificationTree.fit`. Add or change a `ScoreTransform` function by dot addressing: ens.ScoreTransform = '`function`' or ens.ScoreTransform = @`function`
`Trained`	Trained learners, a cell array of compact classification models.
`TrainedWeights`	Numeric vector of trained weights for the weak learners in `ens`. `TrainedWeights` has `T` elements, where `T` is the number of weak learners in `learners`.
`UseObsForLearner`	Logical matrix of size `N`-by-`NTrained`, where `N` is the number of observations in the training data and `NTrained` is the number of trained weak learners. `UseObsForLearner(I,J)` is `true` if observation `I` was used for training learner `J`, and is `false` otherwise.
`W`	Scaled `weights`, a vector with length `n`, the number of rows in `X`. The sum of the elements of `W` is `1`.
`X`	Matrix of predictor values that trained the ensemble. Each column of `X` represents one variable, and each row represents one observation.
`Y`	Numeric vector, vector of categorical variables (nominal or ordinal), logical vector, character array, or cell array of strings. Each row of `Y` represents the classification of the corresponding row of `X`.

Methods

oobEdge	Out-of-bag classification edge
oobLoss	Out-of-bag classification error
oobMargin	Out-of-bag classification margins
oobPredict	Predict out-of-bag response of ensemble

Inherited Methods

compact	Compact classification ensemble
crossval	Cross validate ensemble
resubEdge	Classification edge by resubstitution
resubLoss	Classification error by resubstitution
resubMargin	Classification margins by resubstitution
resubPredict	Predict ensemble response by resubstitution
resume	Resume training ensemble

edge	Classification edge
loss	Classification error
margin	Classification margins
predict	Predict classification
predictorImportance	Estimates of predictor importance

Copy Semantics

Value. To learn how value classes affect copy operations, see Copying Objects in the MATLAB Programming Fundamentals documentation.

Examples

Construct a bagged ensemble for the ionosphere data, and examine its resubstitution loss:

load ionosphere
rng(0,'twister') % for reproducibility
ens = fitensemble(X,Y,'bag',100,'Tree',...
    'type','classification');
L = resubLoss(ens)

L =
     0

The ensemble does a perfect job classifying its training data.

How To

Ensemble Methods

Search MATLAB Documentation
R2012a Documentation → Statistics Toolbox
View documentation for other releases	Learn more about Statistics Toolbox