Transcription of Package ‘xyz’ - R
1 Package xyz April 3, 2017 TypePackageTitleThe 'xyz' Algorithm for Fast Interaction Search inHigh-Dimensional ThaneiDescriptionHigh dimensional interaction search by brute force requires aquadratic computational cost in the number of variables. The xyz algorithm prov-ably finds strong interactions in almost linear details of the algorithm see: G. Thanei, N. Meinshausen and R. Shah (2016). The xyz algo-rithm for fast interaction search in high-dimensional data < >.LicenseGPLLazyDataTRUEI mportsstats, Rcpp (>= ) , rmarkdownVignetteBuilderknitrSystemRequi rementsC++11 NeedsCompilationyesRepositoryCRANDate/Pu blication2017-04-03 16:39:20 UTCR topics documented:xyz.
2 2xyz_regression ..2xyz_search ..3 Index512xyz_regressionxyzxyz: A Package for fast interaction search in high dimensional datausing the xyz : A Package for fast interaction search in high dimensional data using the xyz functionsxyz_search, xyz_regressionReferencesG. Thanei, N. Meinshausen and R. Shah (2016). The xyz algorithm for fast interaction search inhigh-dimensional data. < >xyz_regressionElasticnet with interactions (glmnet)DescriptionElasticnet with interactions (glmnet)Usagexyz_regression(X, Y, lambdas = NULL, n_lambda = 10, alpha = , L = 10,standardize = TRUE, standardize_response = TRUE)ArgumentsXA vector of decreasing real numbers containing user specified values of natural number indicating how long the path of lambdas should real number between 0 and 1 (the elastic net parameter)
3 LAn integer indicating how many projection steps are boolean indicating if X should be scaled and boolean indicating if Y should be scaled and interactions (of typetype) Thanei, N. Meinshausen and R. Shah (2016). The xyz algorithm for fast interaction search inhigh-dimensional data. < >Examplesn<-300p<-1000#build matrix of predictorsX<-matrix(rnorm(n*p),n,p)#buil d a main effect and an interaction into YY<-4*X[,1]*X[,2]-5*X[,4]+rnorm(n)result <-xyz_regression(X,Y,n_lambda=10,alpha= ,L=10)#print the resultprint(result)#plot the resultplot(result)xyz_searchInteraction searchDescriptionInteraction searchUsagexyz_search(X, Y, L = 10, N = 100, binary = TRUE, negative = TRUE)
4 ArgumentsXA integer indicating how many projection steps are integer, controlling the number of pairs that will be returned in the logical indicating if X is binary or logical indicating if also negative interactions should be searched interactions Thanei, N. Meinshausen and R. Shah (2016). The xyz algorithm for fast interaction search inhigh-dimensional data. < >4xyz_searchExamplesn<-300p<-1000#constru ct a binary matrixX<-matrix(sample(c(-1,1),replace=T RUE,n*p),n,p)#set an interaction of the pair (1,2)Y<-X[,1]*X[,2]+rnorm(n)#run the interaction searchresult<-xyz_search(X,Y,L=10,N=10,b inary=TRUE,negative=TRUE)#print the resultprint(result)Indexxyz, 2xyz- Package (xyz), 2xyz_regression, 2xyz_search, 35
