Main Content

crossval

Cross-validate machine learning model

    Description

    CVMdl = crossval(Mdl) returns a cross-validated (partitioned) machine learning model (CVMdl) from a trained model (Mdl). By default, crossval uses 10-fold cross-validation on the training data.

    example

    CVMdl = crossval(Mdl,Name=Value) specifies additional options using one or more name-value arguments. For example, you can specify the fraction of data for holdout validation, and the number of folds to use in the cross-validated model.

    example

    Examples

    collapse all

    Load the ionosphere data set. This data set has 34 predictors and 351 binary responses for radar returns, either bad ('b') or good ('g').

    load ionosphere
    rng(1); % For reproducibility

    Train a support vector machine (SVM) classifier. Standardize the predictor data and specify the order of the classes.

    SVMModel = fitcsvm(X,Y,'Standardize',true,'ClassNames',{'b','g'});

    SVMModel is a trained ClassificationSVM classifier. 'b' is the negative class and 'g' is the positive class.

    Cross-validate the classifier using 10-fold cross-validation.

    CVSVMModel = crossval(SVMModel)
    CVSVMModel = 
      ClassificationPartitionedModel
        CrossValidatedModel: 'SVM'
             PredictorNames: {'x1'  'x2'  'x3'  'x4'  'x5'  'x6'  'x7'  'x8'  'x9'  'x10'  'x11'  'x12'  'x13'  'x14'  'x15'  'x16'  'x17'  'x18'  'x19'  'x20'  'x21'  'x22'  'x23'  'x24'  'x25'  'x26'  'x27'  'x28'  'x29'  'x30'  'x31'  'x32'  'x33'  'x34'}
               ResponseName: 'Y'
            NumObservations: 351
                      KFold: 10
                  Partition: [1×1 cvpartition]
                 ClassNames: {'b'  'g'}
             ScoreTransform: 'none'
    
    
      Properties, Methods
    
    

    CVSVMModel is a ClassificationPartitionedModel cross-validated classifier. During cross-validation, the software completes these steps:

    1. Randomly partition the data into 10 sets of equal size.

    2. Train an SVM classifier on nine of the sets.

    3. Repeat steps 1 and 2 k = 10 times. The software leaves out one partition each time and trains on the other nine partitions.

    4. Combine generalization statistics for each fold.

    Display the first model in CVSVMModel.Trained.

    FirstModel = CVSVMModel.Trained{1}
    FirstModel = 
      CompactClassificationSVM
                 ResponseName: 'Y'
        CategoricalPredictors: []
                   ClassNames: {'b'  'g'}
               ScoreTransform: 'none'
                        Alpha: [78×1 double]
                         Bias: -0.2209
             KernelParameters: [1×1 struct]
                           Mu: [0.8888 0 0.6320 0.0406 0.5931 0.1205 0.5361 0.1286 0.5083 0.1879 0.4779 0.1567 0.3924 0.0875 0.3360 0.0789 0.3839 9.6066e-05 0.3562 -0.0308 0.3398 -0.0073 0.3590 -0.0628 0.4064 -0.0664 0.5535 -0.0749 0.3835 … ] (1×34 double)
                        Sigma: [0.3149 0 0.5033 0.4441 0.5255 0.4663 0.4987 0.5205 0.5040 0.4780 0.5649 0.4896 0.6293 0.4924 0.6606 0.4535 0.6133 0.4878 0.6250 0.5140 0.6075 0.5150 0.6068 0.5222 0.5729 0.5103 0.5061 0.5478 0.5712 0.5032 … ] (1×34 double)
               SupportVectors: [78×34 double]
          SupportVectorLabels: [78×1 double]
    
    
      Properties, Methods
    
    

    FirstModel is the first of the 10 trained classifiers. It is a CompactClassificationSVM classifier.

    You can estimate the generalization error by passing CVSVMModel to kfoldLoss.

    Specify a holdout sample proportion for cross-validation. By default, crossval uses 10-fold cross-validation to cross-validate a naive Bayes classifier. However, you have several other options for cross-validation. For example, you can specify a different number of folds or a holdout sample proportion.

    Load the ionosphere data set. This data set has 34 predictors and 351 binary responses for radar returns, either bad ('b') or good ('g').

    load ionosphere

    Remove the first two predictors for stability.

    X = X(:,3:end);
    rng('default'); % For reproducibility

    Train a naive Bayes classifier using the predictors X and class labels Y. A recommended practice is to specify the class names. 'b' is the negative class and 'g' is the positive class. fitcnb assumes that each predictor is conditionally and normally distributed.

    Mdl = fitcnb(X,Y,'ClassNames',{'b','g'});

    Mdl is a trained ClassificationNaiveBayes classifier.

    Cross-validate the classifier by specifying a 30% holdout sample.

    CVMdl = crossval(Mdl,'Holdout',0.3)
    CVMdl = 
      ClassificationPartitionedModel
        CrossValidatedModel: 'NaiveBayes'
             PredictorNames: {'x1'  'x2'  'x3'  'x4'  'x5'  'x6'  'x7'  'x8'  'x9'  'x10'  'x11'  'x12'  'x13'  'x14'  'x15'  'x16'  'x17'  'x18'  'x19'  'x20'  'x21'  'x22'  'x23'  'x24'  'x25'  'x26'  'x27'  'x28'  'x29'  'x30'  'x31'  'x32'}
               ResponseName: 'Y'
            NumObservations: 351
                      KFold: 1
                  Partition: [1×1 cvpartition]
                 ClassNames: {'b'  'g'}
             ScoreTransform: 'none'
    
    
      Properties, Methods
    
    

    CVMdl is a ClassificationPartitionedModel cross-validated, naive Bayes classifier.

    Display the properties of the classifier trained using 70% of the data.

    TrainedModel = CVMdl.Trained{1}
    TrainedModel = 
      CompactClassificationNaiveBayes
                  ResponseName: 'Y'
         CategoricalPredictors: []
                    ClassNames: {'b'  'g'}
                ScoreTransform: 'none'
             DistributionNames: {1×32 cell}
        DistributionParameters: {2×32 cell}
    
    
      Properties, Methods
    
    

    TrainedModel is a CompactClassificationNaiveBayes classifier.

    Estimate the generalization error by passing CVMdl to kfoldloss.

    kfoldLoss(CVMdl)
    ans = 
    0.2095
    

    The out-of-sample misclassification error is approximately 21%.

    Reduce the generalization error by choosing the five most important predictors.

    idx = fscmrmr(X,Y);
    Xnew = X(:,idx(1:5));

    Train a naive Bayes classifier for the new predictor.

    Mdlnew = fitcnb(Xnew,Y,'ClassNames',{'b','g'});

    Cross-validate the new classifier by specifying a 30% holdout sample, and estimate the generalization error.

    CVMdlnew = crossval(Mdlnew,'Holdout',0.3);
    kfoldLoss(CVMdlnew)
    ans = 
    0.1429
    

    The out-of-sample misclassification error is reduced from approximately 21% to approximately 14%.

    Train a regression generalized additive model (GAM) by using fitrgam, and create a cross-validated GAM by using crossval and the holdout option. Then, use kfoldPredict to predict responses for validation-fold observations using a model trained on training-fold observations.

    Load the patients data set.

    load patients

    Create a table that contains the predictor variables (Age, Diastolic, Smoker, Weight, Gender, SelfAssessedHealthStatus) and the response variable (Systolic).

    tbl = table(Age,Diastolic,Smoker,Weight,Gender,SelfAssessedHealthStatus,Systolic);

    Train a GAM that contains linear terms for predictors.

    Mdl = fitrgam(tbl,'Systolic');

    Mdl is a RegressionGAM model object.

    Cross-validate the model by specifying a 30% holdout sample.

    rng('default') % For reproducibility
    CVMdl = crossval(Mdl,'Holdout',0.3)
    CVMdl = 
      RegressionPartitionedGAM
           CrossValidatedModel: 'GAM'
                PredictorNames: {'Age'  'Diastolic'  'Smoker'  'Weight'  'Gender'  'SelfAssessedHealthStatus'}
         CategoricalPredictors: [3 5 6]
                  ResponseName: 'Systolic'
               NumObservations: 100
                         KFold: 1
                     Partition: [1×1 cvpartition]
             NumTrainedPerFold: [1×1 struct]
             ResponseTransform: 'none'
        IsStandardDeviationFit: 0
    
    
      Properties, Methods
    
    

    The crossval function creates a RegressionPartitionedGAM model object CVMdl with the holdout option. During cross-validation, the software completes these steps:

    1. Randomly select and reserve 30% of the data as validation data, and train the model using the rest of the data.

    2. Store the compact, trained model in the Trained property of the cross-validated model object RegressionPartitionedGAM.

    You can choose a different cross-validation setting by using the 'CrossVal', 'CVPartition', 'KFold', or 'Leaveout' name-value argument.

    Predict responses for the validation-fold observations by using kfoldPredict. The function predicts responses for the validation-fold observations by using the model trained on the training-fold observations. The function assigns NaN to the training-fold observations.

    yFit = kfoldPredict(CVMdl);

    Find the validation-fold observation indexes, and create a table containing the observation index, observed response values, and predicted response values. Display the first eight rows of the table.

    idx = find(~isnan(yFit));
    t = table(idx,tbl.Systolic(idx),yFit(idx), ...
        'VariableNames',{'Obseraction Index','Observed Value','Predicted Value'});
    head(t)
        Obseraction Index    Observed Value    Predicted Value
        _________________    ______________    _______________
    
                1                 124              130.22     
                6                 121              124.38     
                7                 130              125.26     
               12                 115              117.05     
               20                 125              121.82     
               22                 123              116.99     
               23                 114                 107     
               24                 128              122.52     
    

    Compute the regression error (mean squared error) for the validation-fold observations.

    L = kfoldLoss(CVMdl)
    L = 
    43.8715
    

    Cross-validate an ECOC classifier with SVM binary learners, and estimate the generalized classification error.

    Load Fisher's iris data set. Specify the predictor data X and the response data Y.

    load fisheriris
    X = meas;
    Y = species;
    rng(1); % For reproducibility

    Create an SVM template, and standardize the predictors.

    t = templateSVM('Standardize',true)
    t = 
    Fit template for SVM.
        Standardize: 1
    
    

    t is an SVM template. Most of the template object properties are empty. When training the ECOC classifier, the software sets the applicable properties to their default values.

    Train the ECOC classifier, and specify the class order.

    Mdl = fitcecoc(X,Y,'Learners',t,...
        'ClassNames',{'setosa','versicolor','virginica'});

    Mdl is a ClassificationECOC classifier. You can access its properties using dot notation.

    Cross-validate Mdl using 10-fold cross-validation.

    CVMdl = crossval(Mdl);

    CVMdl is a ClassificationPartitionedECOC cross-validated ECOC classifier.

    Estimate the generalized classification error.

    genError = kfoldLoss(CVMdl)
    genError = 
    0.0400
    

    The generalized classification error is 4%, which indicates that the ECOC classifier generalizes fairly well.

    Compute the quantile loss for a quantile neural network regression model, first partitioned using holdout validation and then partitioned using 5-fold cross-validation. Compare the two losses.

    Load the carbig data set, which contains measurements of cars made in the 1970s and early 1980s. Create a table containing the predictor variables Acceleration, Cylinders, Displacement, and so on, as well as the response variable MPG. View the first eight observations.

    load carbig
    cars = table(Acceleration,Cylinders,Displacement, ...
        Horsepower,Model_Year,Origin,Weight,MPG);
    head(cars)
        Acceleration    Cylinders    Displacement    Horsepower    Model_Year    Origin     Weight    MPG
        ____________    _________    ____________    __________    __________    _______    ______    ___
    
              12            8            307            130            70        USA         3504     18 
            11.5            8            350            165            70        USA         3693     15 
              11            8            318            150            70        USA         3436     18 
              12            8            304            150            70        USA         3433     16 
            10.5            8            302            140            70        USA         3449     17 
              10            8            429            198            70        USA         4341     15 
               9            8            454            220            70        USA         4354     14 
             8.5            8            440            215            70        USA         4312     14 
    

    Remove rows of cars where the table has missing values.

    cars = rmmissing(cars);

    Categorize the cars based on whether they were made in the USA.

    cars.Origin = categorical(cellstr(cars.Origin));
    cars.Origin = mergecats(cars.Origin,["France","Japan",...
        "Germany","Sweden","Italy","England"],"NotUSA");

    Partition the data using cvpartition. First, create a partition for holdout validation, using approximately 80% of the observations for the training data and 20% for the test data. Then, create a partition for 5-fold cross-validation.

    rng(0,"twister") % For reproducibility
    holdoutPartition = cvpartition(height(cars),Holdout=0.20);
    kfoldPartition = cvpartition(height(cars),KFold=5);

    Train a quantile neural network regression model using the cars data. Specify MPG as the response variable, and standardize the numeric predictors. Use the default 0.5 quantile (median).

    Mdl = fitrqnet(cars,"MPG",Standardize=true);

    Create the partitioned quantile regression models using crossval.

    holdoutMdl = crossval(Mdl,CVPartition=holdoutPartition)
    holdoutMdl = 
      RegressionPartitionedQuantileModel
          CrossValidatedModel: 'QuantileNeuralNetwork'
               PredictorNames: {'Acceleration'  'Cylinders'  'Displacement'  'Horsepower'  'Model_Year'  'Origin'  'Weight'}
        CategoricalPredictors: 6
                 ResponseName: 'MPG'
              NumObservations: 392
                        KFold: 1
                    Partition: [1×1 cvpartition]
            ResponseTransform: 'none'
                    Quantiles: 0.5000
    
    
      Properties, Methods
    
    
    kfoldMdl = crossval(Mdl,CVPartition=kfoldPartition)
    kfoldMdl = 
      RegressionPartitionedQuantileModel
          CrossValidatedModel: 'QuantileNeuralNetwork'
               PredictorNames: {'Acceleration'  'Cylinders'  'Displacement'  'Horsepower'  'Model_Year'  'Origin'  'Weight'}
        CategoricalPredictors: 6
                 ResponseName: 'MPG'
              NumObservations: 392
                        KFold: 5
                    Partition: [1×1 cvpartition]
            ResponseTransform: 'none'
                    Quantiles: 0.5000
    
    
      Properties, Methods
    
    

    Compute the quantile loss for holdoutMdl and kfoldMdl by using the kfoldLoss object function.

    holdoutL = kfoldLoss(holdoutMdl)
    holdoutL = 
    0.9488
    
    kfoldL = kfoldLoss(kfoldMdl)
    kfoldL = 
    0.9628
    

    holdoutL is the quantile loss computed using one holdout set, while kfoldL is an average quantile loss computed using five holdout sets. Cross-validation metrics tend to be better indicators of a model's performance on unseen data.

    Input Arguments

    collapse all

    Machine learning model, specified as a full classification, regression, or quantile regression model object, as given in the following tables of supported models.

    Classification Model Object

    ModelFull Classification Model Object
    Discriminant analysis classifierClassificationDiscriminant
    Multiclass error-correcting output codes (ECOC) modelClassificationECOC
    Ensemble classifierClassificationEnsemble, ClassificationBaggedEnsemble
    Generalized additive modelClassificationGAM
    k-nearest neighbor modelClassificationKNN
    Naive Bayes modelClassificationNaiveBayes
    Neural network modelClassificationNeuralNetwork
    Support vector machine for one-class and binary classificationClassificationSVM
    Binary decision tree for multiclass classificationClassificationTree

    Regression Model Object

    ModelFull Regression Model Object
    Regression ensemble modelRegressionEnsemble, RegressionBaggedEnsemble
    Gaussian process regression (GPR) modelRegressionGP (If you supply a custom ActiveSet value in the call to fitrgp, then you cannot cross-validate the GPR model.)
    Generalized additive model (GAM)RegressionGAM
    Neural network modelRegressionNeuralNetwork (If you use multiple response variables in the call to fitrnet, then you cannot cross-validate the neural network model.)
    Support vector machine regression modelRegressionSVM
    Regression tree modelRegressionTree

    Quantile Regression Model Object

    ModelFull Quantile Regression Model Object

    Quantile linear regression model (since R2025a)

    RegressionQuantileLinear

    Quantile neural network model for regression (since R2025a)

    RegressionQuantileNeuralNetwork

    Name-Value Arguments

    collapse all

    Specify optional pairs of arguments as Name1=Value1,...,NameN=ValueN, where Name is the argument name and Value is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.

    Before R2021a, use commas to separate each name and value, and enclose Name in quotes.

    Example: crossval(Mdl,KFold=3) specifies to use three folds in the cross-validated model.

    Cross-validation partition, specified as a cvpartition object that specifies the type of cross-validation and the indexing for the training and validation sets.

    To create a cross-validated model, you can specify only one of these four name-value arguments: CVPartition, Holdout, KFold, or Leaveout.

    Example: Suppose you create a random partition for 5-fold cross-validation on 500 observations by using cvp = cvpartition(500,KFold=5). Then, you can specify the cross-validation partition by setting CVPartition=cvp.

    Fraction of the data used for holdout validation, specified as a scalar value in the range (0,1). If you specify Holdout=p, then the software completes these steps:

    1. Randomly select and reserve p*100% of the data as validation data, and train the model using the rest of the data.

    2. Store the compact trained model in the Trained property of the cross-validated model.

    To create a cross-validated model, you can specify only one of these four name-value arguments: CVPartition, Holdout, KFold, or Leaveout.

    Example: Holdout=0.1

    Data Types: double | single

    Number of folds to use in the cross-validated model, specified as a positive integer value greater than 1. If you specify KFold=k, then the software completes these steps:

    1. Randomly partition the data into k sets.

    2. For each set, reserve the set as validation data, and train the model using the other k – 1 sets.

    3. Store the k compact trained models in a k-by-1 cell vector in the Trained property of the cross-validated model.

    To create a cross-validated model, you can specify only one of these four name-value arguments: CVPartition, Holdout, KFold, or Leaveout.

    Example: KFold=5

    Data Types: single | double

    Leave-one-out cross-validation flag, specified as "on" or "off". If you specify Leaveout="on", then for each of the n observations (where n is the number of observations, excluding missing observations, specified in the NumObservations property of the model), the software completes these steps:

    1. Reserve the one observation as validation data, and train the model using the other n – 1 observations.

    2. Store the n compact trained models in an n-by-1 cell vector in the Trained property of the cross-validated model.

    To create a cross-validated model, you can specify only one of these four name-value arguments: CVPartition, Holdout, KFold, or Leaveout.

    Example: Leaveout="on"

    Data Types: char | string

    Printout frequency, specified as a positive integer or "off".

    To track the number of folds trained by the software so far, specify a positive integer m. The software displays a message to the command line every time it finishes training m folds.

    If you specify "off", the software does not display a message when it completes training folds.

    Note

    You can specify Nprint only if Mdl is a ClassificationEnsemble or RegressionEnsemble model object.

    Example: NPrint=5

    Data Types: single | double | char | string

    Options for computing in parallel, specified as a structure. Create the Options structure using statset.

    You need Parallel Computing Toolbox™ to run computations in parallel.

    You can specify Options only if Mdl is a ClassificationECOC model object.

    Example: Options=statset(UseParallel=true)

    Data Types: struct

    Output Arguments

    collapse all

    Cross-validated machine learning model, returned as one of the cross-validated (partitioned) model objects in the following tables, depending on the input model Mdl.

    Classification Model Object

    ModelClassification Model (Mdl)Cross-Validated Model (CVMdl)
    Discriminant analysis classifierClassificationDiscriminantClassificationPartitionedModel
    Multiclass error-correcting output codes (ECOC) modelClassificationECOCClassificationPartitionedECOC
    Ensemble classifierClassificationEnsemble, ClassificationBaggedEnsembleClassificationPartitionedEnsemble
    Generalized additive modelClassificationGAMClassificationPartitionedGAM
    k-nearest neighbor modelClassificationKNNClassificationPartitionedModel
    Naive Bayes modelClassificationNaiveBayesClassificationPartitionedModel
    Neural network modelClassificationNeuralNetworkClassificationPartitionedModel
    Support vector machine for one-class and binary classificationClassificationSVMClassificationPartitionedModel
    Binary decision tree for multiclass classificationClassificationTreeClassificationPartitionedModel

    Regression Model Object

    ModelRegression Model (Mdl)Cross-Validated Model (CVMdl)
    Regression ensemble modelRegressionEnsemble, RegressionBaggedEnsembleRegressionPartitionedEnsemble
    Gaussian process regression modelRegressionGPRegressionPartitionedGP
    Generalized additive modelRegressionGAMRegressionPartitionedGAM
    Neural network modelRegressionNeuralNetworkRegressionPartitionedNeuralNetwork
    Support vector machine regression modelRegressionSVMRegressionPartitionedSVM
    Regression tree modelRegressionTreeRegressionPartitionedModel

    Quantile Regression Model Object

    ModelQuantile Regression Model (Mdl)Cross-Validated Model (CVMdl)

    Quantile linear regression model (since R2025a)

    RegressionQuantileLinearRegressionPartitionedQuantileModel

    Quantile neural network model for regression (since R2025a)

    RegressionQuantileNeuralNetworkRegressionPartitionedQuantileModel

    Tips

    • Assess the predictive performance of Mdl on cross-validated data using the kfold functions and properties of CVMdl, such as kfoldPredict, kfoldLoss, kfoldMargin, and kfoldEdge for classification; kfoldPredict and kfoldLoss for regression; and kfoldPredict and kfoldLoss for quantile regression.

    • Return a partitioned classifier with stratified partitioning by using the name-value argument KFold or Holdout.

    • Create a cvpartition object cvp using cvp = cvpartition(n,KFold=k). Return a partitioned classifier with nonstratified partitioning by using the name-value argument CVPartition=cvp.

    Alternative Functionality

    Instead of training a model and then cross-validating it, you can create a cross-validated model directly by using a fitting function and specifying one of these name-value arguments: CVPartition, Holdout, KFold, or Leaveout.

    Extended Capabilities

    expand all

    Version History

    Introduced in R2012a

    expand all

    See Also