resubPredict

Predict resubstitution labels of discriminant analysis classification model

Syntax

label = resubPredict(mdl)

[label,posterior] = resubPredict(mdl)

[label,posterior,cost] = resubPredict(mdl)

Description

label = resubPredict(mdl) returns the labels that mdl predicts for the data mdl.X.

label is the predictions of mdl on the data that fitcdiscr used to create mdl.

[label,posterior] = resubPredict(mdl) returns the posterior class probabilities for the predictions.

[label,posterior,cost] = resubPredict(mdl) returns the predicted misclassification costs per class for the resubstituted data.

Examples

Number of Misclassifications

Find the total number of misclassifications of the Fisher iris data for a discriminant analysis classifier.

Create a classification model for the Fisher iris data.

load fisheriris
mdl = fitcdiscr(meas,species);

Predict resubstitution labels of the model.

Ypredict = resubPredict(mdl);

Find the total number of different misclassifications.

Ysame = strcmp(Ypredict,species); % true when ==
sum(~Ysame) % how many are different?

ans =
     3

Input Arguments

mdl — Trained discriminant analysis classifier

ClassificationDiscriminant model object

Trained discriminant analysis classifier, specified as a ClassificationDiscriminant model object. To create a discriminant analysis classifier, use fitcdiscr.

Output Arguments

label — Response that mdl predicts for the training data

same data type as the training response data mdl.Y

Response that mdl predicts for the training data, returned as the same data type as the training response data mdl.Y. The predicted class labels are those with minimal expected misclassification cost. See Prediction Using Discriminant Analysis Models.

posterior — Posterior probabilities for classes that mdl predicts

N-by-K matrix

Posterior probabilities for classes that mdl predicts, returned as an N-by-K matrix. Here, N is the number of observations, and K is the number of classes.

cost — Predicted misclassification costs

N-by-K matrix

Predicted misclassification costs, returned as an N-by-K matrix. Here, N is the number of observations, and K is the number of classes. Each cost is the average misclassification cost with respect to the posterior probability.

More About

Posterior Probability

posterior(i,k) is the posterior probability of class k for observation i. For the mathematical definition, see Posterior Probability.

Version History

Introduced in R2011b

R2023b: Observations with missing predictor values are used in resubstitution and cross-validation computations

Starting in R2023b, the following classification model object functions use observations with missing predictor values as part of resubstitution ("resub") and cross-validation ("kfold") computations for classification edges, losses, margins, and predictions.

Model Type	Model Objects	Object Functions
Discriminant analysis classification model	ClassificationDiscriminant	resubEdge, resubLoss, resubMargin, resubPredict
	ClassificationPartitionedModel	kfoldEdge, kfoldLoss, kfoldMargin, kfoldPredict
Ensemble of discriminant analysis learners for classification	ClassificationEnsemble	resubEdge, resubLoss, resubMargin, resubPredict
	ClassificationPartitionedEnsemble	kfoldEdge, kfoldLoss, kfoldMargin, kfoldPredict
Gaussian kernel classification model	ClassificationPartitionedKernel	kfoldEdge, kfoldLoss, kfoldMargin, kfoldPredict
	ClassificationPartitionedKernelECOC	kfoldEdge, kfoldLoss, kfoldMargin, kfoldPredict
Linear classification model	ClassificationPartitionedLinear	kfoldEdge, kfoldLoss, kfoldMargin, kfoldPredict
	ClassificationPartitionedLinearECOC	kfoldEdge, kfoldLoss, kfoldMargin, kfoldPredict
Neural network classification model	ClassificationNeuralNetwork	resubEdge, resubLoss, resubMargin, resubPredict
	ClassificationPartitionedModel	kfoldEdge, kfoldLoss, kfoldMargin, kfoldPredict
Support vector machine (SVM) classification model	ClassificationSVM	resubEdge, resubLoss, resubMargin, resubPredict
	ClassificationPartitionedModel	kfoldEdge, kfoldLoss, kfoldMargin, kfoldPredict

In previous releases, the software omitted observations with missing predictor values from the resubstitution and cross-validation computations.