ClassificationBaggedEnsemble
Classification ensemble grown by resampling
Description
ClassificationBaggedEnsemble combines a set of trained weak
learner models and the data on which the learners were trained. Use the
predict object function to predict the ensemble response for
new data by aggregating predictions from the weak learners.
Creation
Create a bagged classification ensemble object using fitcensemble. Set the name-value argument Method of
fitcensemble to "Bag" to use bootstrap
aggregation, or bagging (for example, random forest).
For a description of bagged classification ensembles, see Bootstrap Aggregation (Bagging) and Random Forest.
Properties
Object Functions
compact | Reduce size of machine learning model |
compareHoldout | Compare accuracies of two classification models using new data |
crossval | Cross-validate machine learning model |
edge | Classification edge for classification ensemble model |
gather | Gather properties of Statistics and Machine Learning Toolbox object from GPU |
lime | Local interpretable model-agnostic explanations (LIME) |
loss | Classification loss for classification ensemble model |
margin | Classification margins for classification ensemble model |
oobEdge | Out-of-bag classification edge for bagged classification ensemble model |
oobLoss | Out-of-bag classification loss for bagged classification ensemble model |
oobMargin | Out-of-bag classification margins for bagged classification ensemble |
oobPermutedPredictorImportance | Out-of-bag predictor importance estimates for random forest of classification trees by permutation |
oobPredict | Predict out-of-bag labels and scores of bagged classification ensemble |
partialDependence | Compute partial dependence |
plotPartialDependence | Create partial dependence plot (PDP) and individual conditional expectation (ICE) plots |
predict | Predict labels using classification ensemble model |
predictorImportance | Estimates of predictor importance for classification ensemble of decision trees |
resubEdge | Resubstitution classification edge for classification ensemble model |
resubLoss | Resubstitution classification loss for classification ensemble model |
resubMargin | Resubstitution classification margins for classification ensemble model |
resubPredict | Classify observations in classification ensemble by resubstitution |
resume | Resume training of classification ensemble model |
shapley | Shapley values |
testckfold | Compare accuracies of two classification models by repeated cross-validation |
Examples
Load the ionosphere data set.
load ionosphereYou can train a bagged ensemble of 100 classification trees using all measurements.
Mdl = fitcensemble(X,Y,Method="Bag")
fitcensemble uses a default template tree object templateTree() as a weak learner when Method is "Bag". In this example, for reproducibility, specify Reproducible=true when you create a tree template object, and then use the object as a weak learner.
rng(0,"twister") % For reproducibility t = templateTree(Reproducible=true); % For reproducibiliy of random predictor selections Mdl = fitcensemble(X,Y,Method="Bag",Learners=t)
Mdl =
ClassificationBaggedEnsemble
ResponseName: 'Y'
CategoricalPredictors: []
ClassNames: {'b' 'g'}
ScoreTransform: 'none'
NumObservations: 351
NumTrained: 100
Method: 'Bag'
LearnerNames: {'Tree'}
ReasonForTermination: 'Terminated normally after completing the requested number of training cycles.'
FitInfo: []
FitInfoDescription: 'None'
FResample: 1
Replace: 1
UseObsForLearner: [351×100 logical]
Properties, Methods
Mdl is a ClassificationBaggedEnsemble model object.
Mdl.Trained is the property that stores a 100-by-1 cell vector of the trained classification trees (CompactClassificationTree model objects) that compose the ensemble.
Plot a graph of the first trained classification tree.
view(Mdl.Trained{1},Mode="graph")
By default, fitcensemble grows deep decision trees for bagged ensembles.
Estimate the in-sample misclassification rate.
L = resubLoss(Mdl)
L = 0
L is 0, which indicates that Mdl is perfect at classifying the training data.
Tips
For a bagged ensemble of classification trees Mdl, the
Trained property of Mdl stores a cell vector
of Mdl.NumTrained
CompactClassificationTree model objects. For a textual or graphical display
of tree t in the cell vector,
enter
view(Mdl.Trained{t})Alternative Functionality
Bootstrap Aggregation Methods
For classification or regression, you can choose two approaches for bagging:
Classification: create a bagged ensemble using
fitcensembleorTreeBagger.Regression: create a bagged ensemble using
fitrensembleorTreeBagger.
For help choosing between these approaches, see Ensemble Algorithms and Suggestions for Choosing an Appropriate Ensemble Algorithm.
