sidaclassify: Classification approach for Sparse Integrative Discriminant...

In lasandrall/SIDA: Sparse Integrative Discriminant Analysis for Multi-view Structured Data

Classification approach for Sparse Integrative Discriminant Analysis

Description

Performs classification using nearest centroid on separate or combined estimated discriminant vectors, and predicts class membership.

Usage

sidaclassify(hatalpha=hatalpha,Xtestdata=Xtestdata,Xdata=Xdata,Y=Y,
            AssignClassMethod='Joint', standardize=TRUE)

Arguments

hatalpha	A list of estimated sparse discriminant vectors for each view. This may be obtained from sida or cvSIDA
Xtestdata	A list with each entry containing testing views of size ntest \times p_d, where d =1,...,D views. Rows are samples and columns are variables. The order of the list should be the same as the order for the training data, Xdata. If covariates are available, they should be included as a separate view, and set as the last dataset. For binary or categorical covariates (assumes no ordering), we suggest the use of indicator variables. If you want to obtain training error, set as Xdata.
Xdata	A list with each entry containing training views of size n \times p_d, where d =1,...,D views. Rows are samples and columns are variables. If covariates are available, they should be included as a separate view, and set as the last dataset. For binary or categorical covariates (assumes no ordering), we suggest the use of indicator variables.
Y	n \times 1 vector of class membership. Same size as the number of training samples.
AssignClassMethod	Classification method. Either Joint or Separate. Joint uses all discriminant vectors from D datasets to predict class membership. Separate predicts class membership separately for each dataset. Default is Joint
standardize	TRUE or FALSE. If TRUE, data will be normalized to have mean zero and variance one for each variable. Default is TRUE.

Details

The function will return an R object, showing the predicted class and the classification method. To see the results, use the “$" operator.

Value

PredictedClass	Predicted class. If AssignClassMethod='Separate', this will be a ntest\times D matrix, with each column the predicted class for each data.
AssignClassMethod	Classification method used. Joint or Separate.

References

Sandra E. Safo, Eun Jeong Min, and Lillian Haine (2019) , Sparse Linear Discriminant Analysis for Multi-view Structured Data, submitted

See Also

cvSIDA,sida,cvSIDANet,sidanet

Examples

##---- read in data
data(DataExample)

Xdata=DataExample[[1]]
Y=DataExample[[2]]
Xtestdata=DataExample[[3]]
Ytest=DataExample[[4]]


#call sidatunerange to get range of tuning paramater
ngrid=10
mytunerange=sidatunerange(Xdata,Y,ngrid,standardize=TRUE,weight=0.5,withCov=FALSE)

# an example with Tau set as the lower bound
Tau=c(mytunerange$Tauvec[[1]][1], mytunerange$Tauvec[[2]][1])

mysida=sida(Xdata,Y,Tau,withCov=FALSE,Xtestdata=Xtestdata,Ytest=Ytest)


#classification with combined estimated vectors
mysida.classify.Joint=sidaclassify(mysida$hatalpha,Xtestdata,Xdata,Y,
                        AssignClassMethod='Joint')

mysida.PredClass.Joint=mysida.classify.Joint$PredictedClass

#classification with separate estimated vectors
mysida.classify.Separate=sidaclassify(mysida$hatalpha,Xtestdata,Xdata,Y,
                        AssignClassMethod='Separate')

mysida.PredClass.Separate=mysida.classify.Separate$PredictedClass

lasandrall/SIDA documentation built on Oct. 19, 2022, 9:23 a.m.