CompactRegressionEnsemble - Compact regression ensemble - MATLAB (original) (raw)

Compact regression ensemble

Description

Compact version of a regression ensemble. The compact version does not include the data for training the regression ensemble. Therefore, you cannot perform some tasks with a compact regression ensemble, such as cross validation. Use a compact regression ensemble for making predictions (regressions) of new data.

Properties

expand all

This property is read-only.

Categorical predictor indices, specified as a vector of positive integers. CategoricalPredictors contains index values indicating that the corresponding predictors are categorical. The index values are between 1 and p, where p is the number of predictors used to train the model. If none of the predictors are categorical, then this property is empty ([]).

Data Types: single | double

This property is read-only.

Method used to combine weak learner weights, returned as either'WeightedAverage' or 'WeightedSum'.

Data Types: char

This property is read-only.

Expanded predictor names, returned as a cell array of character vectors.

If the model uses encoding for categorical variables, thenExpandedPredictorNames includes the names that describe the expanded variables. Otherwise, ExpandedPredictorNames is the same asPredictorNames.

Data Types: cell

This property is read-only.

Number of trained weak learners in the ensemble, returned as a positive integer.

Data Types: double

This property is read-only.

Predictor names, specified as a cell array of character vectors. The order of the entries in PredictorNames is the same as in the training data.

Data Types: cell

This property is read-only.

Name of the response variable, returned as a character vector.

Data Types: char

Data Types: char | string | function_handle

This property is read-only.

Trained weak learners, returned as a cell vector. The entries of the cell vector contain the corresponding compact regression models.

Data Types: cell

This property is read-only.

Trained weak learner weights, returned as a numeric vector. TrainedWeights has NumTrained elements, whereNumTrained is the number of weak learners in the ensemble. The ensemble computes the predicted response by aggregating weighted predictions from its learners.

Data Types: double

Object Functions

gather Gather properties of Statistics and Machine Learning Toolbox object from GPU
lime Local interpretable model-agnostic explanations (LIME)
loss Regression error for regression ensemble model
partialDependence Compute partial dependence
plotPartialDependence Create partial dependence plot (PDP) and individual conditional expectation (ICE) plots
predict Predict responses using regression ensemble model
predictorImportance Estimates of predictor importance for regression ensemble of decision trees
removeLearners Remove members of compact regression ensemble
shapley Shapley values

Examples

collapse all

Create a compact regression ensemble for efficiently making predictions on new data.

Load the carsmall data set. Consider a model that explains a car's fuel economy (MPG) using its weight (Weight) and number of cylinders (Cylinders).

load carsmall X = [Weight Cylinders]; Y = MPG;

Train a boosted ensemble of 100 regression trees using the LSBoost. Specify that Cylinders is a categorical variable.

Mdl = fitrensemble(X,Y,'PredictorNames',{'W','C'},... 'CategoricalPredictors',2)

Mdl = RegressionEnsemble PredictorNames: {'W' 'C'} ResponseName: 'Y' CategoricalPredictors: 2 ResponseTransform: 'none' NumObservations: 94 NumTrained: 100 Method: 'LSBoost' LearnerNames: {'Tree'} ReasonForTermination: 'Terminated normally after completing the requested number of training cycles.' FitInfo: [100×1 double] FitInfoDescription: {2×1 cell} Regularization: []

Properties, Methods

Mdl is a RegressionEnsemble model object that contains the training data, among other things.

Create a compact version of Mdl.

CMdl = CompactRegressionEnsemble PredictorNames: {'W' 'C'} ResponseName: 'Y' CategoricalPredictors: 2 ResponseTransform: 'none' NumTrained: 100

Properties, Methods

CMdl is a CompactRegressionEnsemble model object. CMdl is almost the same as Mdl. One exception is that CMdl does not store the training data.

Compare the amounts of space consumed by Mdl and CMdl.

mdlInfo = whos('Mdl'); cMdlInfo = whos('CMdl'); [mdlInfo.bytes cMdlInfo.bytes]

Mdl consumes more space than CMdl.

CMdl.Trained stores the trained regression trees (CompactRegressionTree model objects) that compose Mdl.

Display a graph of the first tree in the compact ensemble.

view(CMdl.Trained{1},'Mode','graph');

Figure Regression tree viewer contains an axes object and other objects of type uimenu, uicontrol. The axes object contains 36 objects of type line, text. One or more of the lines displays its values using only markers

By default, fitrensemble grows shallow trees for boosted ensembles of trees.

Predict the fuel economy of a typical car using the compact ensemble.

typicalX = [mean(X(:,1)) mode(X(:,2))]; predMeanX = predict(CMdl,typicalX)

Tips

For a compact ensemble of regression trees, the Trained property of ens stores a cell vector of ens.NumTrained CompactRegressionTree model objects. For a textual or graphical display of tree t in the cell vector, enter

Extended Capabilities

expand all

Usage notes and limitations:

For more information, see Introduction to Code Generation.

Usage notes and limitations:

For more information, see Run MATLAB Functions on a GPU (Parallel Computing Toolbox).

Version History

Introduced in R2011a