<< covsel_fda (X->Y_classes) Classification fda >>

fact >> (X->Y_classes) Classification > daaply

daaply

application of a discriminant model to a test dataset

Calling sequence

res_da = daapply(da_model,xtest,(ytest))

Arguments

da_model:

a structure containing a discriminant analysis model, obtained with one of the following functions: copda, fda, forwda, knnda or plsda

xtest:

the test dataset; a matrix (n x q) or a Div structure

(ytest):

the classes of the observations of xtest; a conjunctive vector (n x 1) or a disjunctive matrix (n x nclass) or a Div structure

res_da.ypred:

the predicted classes for the observations of xtest

res_da.ypred.d is an hypermatrix of dimensions (n x nclass x lv)

(res_da.confm_test_nobs):

the confusion matrix obtained for the test dataset, expressed as numbers of observations for each class

res_da.confm_test_nobs.d is an hyper-matrix of dimensions (nclass x nclass x lv)

(res_da.confm_test):

the confusion matrix obtained for the test dataset, expressed as percentages for each class

res_da.confm_test.d is an hyper-matrix of dimensions (nclass x nclass x lv)

(res_da.err_test):

the percentage of error for the test dataset

res_da.err_test.d is a vector of dimensions (lv x 1)

(res_da.errbycl_test):

the percentage of error for the test dataset, for each class

res_da.errbycl_test.d is a matrix of dimensions (lv x nclass)

(res_da.notclassed):

the percentage of not-classed observations (all predictions lower than the threshold)

res_da.notclassed.d is a vector (lv x 1)

(res_da.notclassed_bycl):

the percentage of not-classed observations (all predictions lower than the threshold), for each class

res_da.notclassed_bycl.d is a matrix (lv x nclass)

Examples

[res_daaply]=daaply(model_fda,xtest)
[res_daaply]=daaply(model_fda,xtest,ytest)

Authors


Report an issue
<< covsel_fda (X->Y_classes) Classification fda >>