分类集成

用于进行多类学习的提升、随机森林、装袋、随机子空间和 ECOC 集成

分类集成是由多个分类模型的加权组合构成的预测模型。一般来讲，将多个分类模型相结合可以提高预测性能。

要以交互方式研究分类集成，可以使用分类学习器。为了获得更大的灵活性，可以在命令行界面中使用 fitcensemble 来提升或装袋分类树，或者生成一个随机森林。有关支持的所有集成的详细信息，请参阅Ensemble Algorithms。要将多类问题简化为二分类问题的集成，可以训练纠错输出编码 (ECOC) 模型。有关详细信息，请参阅 fitcecoc。

要使用 LSBoost 提升回归树，或者要生成回归树的随机森林，请参阅回归集成。

App

分类学习器使用有监督的机器学习训练模型以对数据进行分类

模块

ClassificationEnsemble PredictClassify observations using ensemble of decision trees (自 R2021a 起)
ClassificationECOC PredictClassify observations using error-correcting output codes (ECOC) classification model (自 R2023a 起)
IncrementalClassificationECOC PredictClassify observations using incremental ECOC classification model (自 R2024a 起)

函数

全部展开

templateDiscriminantDiscriminant analysis classifier template
templateECOCError-correcting output codes learner template
templateEnsembleEnsemble learning template
templateKNNk-nearest neighbor classifier template
templateLinearLinear learner template
templateNaiveBayesNaive Bayes classifier template
templateSVMSupport vector machine template
templateTreeCreate decision tree template

创建分类集成

fitcensembleFit ensemble of learners for classification
compactReduce size of machine learning model

修改分类集成

resumeResume training of classification ensemble model
removeLearnersRemove members of compact classification ensemble

解释分类集成

limeLocal interpretable model-agnostic explanations (LIME)
partialDependenceCompute partial dependence
permutationImportancePredictor importance by permutation (自 R2024a 起)
plotPartialDependenceCreate partial dependence plot (PDP) and individual conditional expectation (ICE) plots
predictorImportanceEstimates of predictor importance for classification ensemble of decision trees
shapleyShapley values (自 R2021a 起)

交叉验证分类集成

crossvalCross-validate machine learning model
kfoldEdgeClassification edge for cross-validated classification model
kfoldLossClassification loss for cross-validated classification model
kfoldMarginClassification margins for cross-validated classification model
kfoldPredictClassify observations in cross-validated classification model
kfoldfunCross-validate function for classification

测量性能

lossClassification loss for classification ensemble model
resubLossResubstitution classification loss for classification ensemble model
compareHoldoutCompare accuracies of two classification models using new data
edgeClassification edge for classification ensemble model
marginClassification margins for classification ensemble model
resubEdgeResubstitution classification edge for classification ensemble model
resubMarginResubstitution classification margins for classification ensemble model
testckfoldCompare accuracies of two classification models by repeated cross-validation

为观测值分类

predictPredict labels using classification ensemble model
resubPredictClassify observations in classification ensemble by resubstitution
oobPredictPredict out-of-bag labels and scores of bagged classification ensemble

收集分类集成的属性

gatherGather properties of Statistics and Machine Learning Toolbox object from GPU
fitcensembleFit ensemble of learners for classification
TreeBaggerEnsemble of bagged decision trees
predictPredict responses using ensemble of bagged decision trees
oobPredictEnsemble predictions for out-of-bag observations

创建 ECOC

fitcecocFit multiclass models for support vector machines or other classifiers
compactReduce size of machine learning model

修改 ECOC

discardSupportVectorsDiscard support vectors of linear SVM binary learners in ECOC model

解释 ECOC

limeLocal interpretable model-agnostic explanations (LIME)
partialDependenceCompute partial dependence
plotPartialDependenceCreate partial dependence plot (PDP) and individual conditional expectation (ICE) plots
shapleyShapley values (自 R2021a 起)

交叉验证 ECOC

crossvalCross-validate machine learning model
kfoldEdgeClassification edge for cross-validated ECOC model
kfoldLossClassification loss for cross-validated ECOC model
kfoldMarginClassification margins for cross-validated ECOC model
kfoldPredictClassify observations in cross-validated ECOC model
kfoldfunCross-validate function using cross-validated ECOC model

测量性能

lossClassification loss for multiclass error-correcting output codes (ECOC) model
resubLossResubstitution classification loss for multiclass error-correcting output codes (ECOC) model
compareHoldoutCompare accuracies of two classification models using new data
edgeClassification edge for multiclass error-correcting output codes (ECOC) model
marginClassification margins for multiclass error-correcting output codes (ECOC) model
resubEdgeResubstitution classification edge for multiclass error-correcting output codes (ECOC) model
resubMarginResubstitution classification margins for multiclass error-correcting output codes (ECOC) model
testckfoldCompare accuracies of two classification models by repeated cross-validation

为观测值分类

predictClassify observations using multiclass error-correcting output codes (ECOC) model
resubPredictClassify observations in multiclass error-correcting output codes (ECOC) model

收集 ECOC 的属性

gatherGather properties of Statistics and Machine Learning Toolbox object from GPU

对象

全部展开

ClassificationEnsembleEnsemble classifier
CompactClassificationEnsembleCompact classification ensemble
ClassificationPartitionedEnsembleCross-validated classification ensemble
TreeBaggerEnsemble of bagged decision trees
CompactTreeBaggerCompact ensemble of bagged decision trees
ClassificationBaggedEnsembleClassification ensemble grown by resampling

类

全部展开

ClassificationECOCMulticlass model for support vector machines (SVMs) and other classifiers
CompactClassificationECOCCompact multiclass model for support vector machines (SVMs) and other classifiers
ClassificationPartitionedECOCCross-validated multiclass ECOC model for support vector machines (SVMs) and other classifiers

主题