CRAN Package Check Results for Package penalizedSVM

Last updated on 2018-04-24 15:48:21 CEST.

Flavor Version Tinstall Tcheck Ttotal Status Flags
r-devel-linux-x86_64-debian-clang 1.1 4.96 34.78 39.74 ERROR
r-devel-linux-x86_64-debian-gcc 1.1 3.82 27.17 30.99 ERROR
r-devel-linux-x86_64-fedora-clang 1.1 54.21 NOTE
r-devel-linux-x86_64-fedora-gcc 1.1 49.81 NOTE
r-devel-windows-ix86+x86_64 1.1 12.00 47.00 59.00 NOTE
r-patched-linux-x86_64 1.1 4.43 34.38 38.81 ERROR
r-patched-solaris-x86 1.1 72.80 NOTE
r-release-linux-x86_64 1.1 3.75 34.25 38.00 ERROR
r-release-windows-ix86+x86_64 1.1 12.00 47.00 59.00 NOTE
r-release-osx-x86_64 1.1 NOTE
r-oldrel-windows-ix86+x86_64 1.1 3.00 66.00 69.00 NOTE
r-oldrel-osx-x86_64 1.1 NOTE

Check Details

Version: 1.1
Check: package dependencies
Result: NOTE
    Depends: includes the non-default packages:
     ‘e1071’ ‘MASS’ ‘corpcor’ ‘statmod’ ‘tgp’ ‘mlegp’ ‘lhs’
    Adding so many packages to the search path is excessive and importing
    selectively is preferable.
Flavors: r-devel-linux-x86_64-debian-clang, r-devel-linux-x86_64-debian-gcc, r-devel-linux-x86_64-fedora-clang, r-devel-linux-x86_64-fedora-gcc, r-devel-windows-ix86+x86_64, r-patched-linux-x86_64, r-patched-solaris-x86, r-release-linux-x86_64, r-release-windows-ix86+x86_64, r-release-osx-x86_64, r-oldrel-windows-ix86+x86_64, r-oldrel-osx-x86_64

Version: 1.1
Check: dependencies in R code
Result: NOTE
    'library' or 'require' calls to packages already attached by Depends:
     ‘MASS’ ‘corpcor’ ‘e1071’ ‘lhs’ ‘mlegp’ ‘statmod’ ‘tgp’
     Please remove these calls from your code.
Flavors: r-devel-linux-x86_64-debian-clang, r-devel-linux-x86_64-debian-gcc, r-devel-linux-x86_64-fedora-clang, r-devel-linux-x86_64-fedora-gcc, r-devel-windows-ix86+x86_64, r-patched-linux-x86_64, r-patched-solaris-x86, r-release-linux-x86_64, r-release-windows-ix86+x86_64, r-release-osx-x86_64, r-oldrel-windows-ix86+x86_64, r-oldrel-osx-x86_64

Version: 1.1
Check: S3 generic/method consistency
Result: NOTE
    Found the following apparent S3 methods exported but not registered:
     predict.penSVM print.1norm.svm print.scad.svm svm.fs svm.fs.default
     svm.fs.default
    See section ‘Registering S3 methods’ in the ‘Writing R Extensions’
    manual.
Flavors: r-devel-linux-x86_64-debian-clang, r-devel-linux-x86_64-debian-gcc, r-devel-linux-x86_64-fedora-clang, r-devel-linux-x86_64-fedora-gcc, r-patched-linux-x86_64, r-patched-solaris-x86, r-release-linux-x86_64

Version: 1.1
Check: R code for possible problems
Result: NOTE
    .DIRdivide: no visible global function definition for ‘plot’
    .DIRdivide: no visible global function definition for ‘text’
    .DIRdivide: no visible global function definition for ‘legend’
    .DrHSVM.initial: no visible global function definition for ‘optimize’
    .EstNuLong: no visible global function definition for ‘runif’
    .erf: no visible global function definition for ‘pnorm’
    .plot.EPSGO.parms: no visible global function definition for ‘par’
    .plot.EPSGO.parms: no visible global function definition for ‘plot’
    .plot.EPSGO.parms: no visible global function definition for ‘abline’
    .plot.EPSGO.parms: no visible global function definition for ‘text’
    .replaceinf: no visible global function definition for ‘fcn_values<-’
    .run.cv: no visible global function definition for ‘predict’
    .run.discrete: no visible global function definition for ‘str’
    Direct: no visible global function definition for ‘pdf’
    Direct: no visible global function definition for ‘par’
    Direct: no visible global function definition for ‘dev.off’
    EPSGO: no visible global function definition for ‘pdf’
    EPSGO: no visible global function definition for ‘par’
    EPSGO: no visible global function definition for ‘plot’
    EPSGO: no visible global function definition for ‘abline’
    EPSGO: no visible global function definition for ‘text’
    EPSGO: no visible global function definition for ‘runif’
    EPSGO: no visible global function definition for ‘sd’
    EPSGO: no visible global function definition for ‘dev.off’
    ExpImprovement: no visible global function definition for ‘predict’
    ExpImprovement: no visible global function definition for ‘pnorm’
    ExpImprovement: no visible global function definition for ‘dnorm’
    sim.data: no visible global function definition for ‘runif’
    sim.data: no visible global function definition for ‘plogis’
    Undefined global functions or variables:
     abline dev.off dnorm fcn_values<- legend optimize par pdf plogis plot
     pnorm predict runif sd str text
    Consider adding
     importFrom("grDevices", "dev.off", "pdf")
     importFrom("graphics", "abline", "legend", "par", "plot", "text")
     importFrom("stats", "dnorm", "optimize", "plogis", "pnorm", "predict",
     "runif", "sd")
     importFrom("utils", "str")
    to your NAMESPACE file.
Flavors: r-devel-linux-x86_64-debian-clang, r-devel-linux-x86_64-debian-gcc, r-devel-linux-x86_64-fedora-clang, r-devel-linux-x86_64-fedora-gcc, r-devel-windows-ix86+x86_64, r-patched-linux-x86_64, r-patched-solaris-x86, r-release-linux-x86_64, r-release-windows-ix86+x86_64, r-release-osx-x86_64, r-oldrel-windows-ix86+x86_64, r-oldrel-osx-x86_64

Version: 1.1
Check: Rd line widths
Result: NOTE
    Rd file 'EPSGO.Rd':
     \examples lines wider than 100 characters:
     # computation intensive; for demostration reasons only for the first 100 features
     system.time(fit<-EPSGO(Q.func, bounds=bounds, parms.coding="log2", fminlower=0,
     show='none', N=21, maxevals=500,
     pdf.name=NULL, seed=seed,
     # Q.func specific parameters:
     x.svm=t(train$x)[,1:100], y.svm=train$y, inner.val.method="cv" ... [TRUNCATED]
     cross.inner=5, maxIter=10 ))
     print(paste("minimal 5-fold cv error:", fit$fmin, "by log2(lambda1)=", fit$xmin))
    
    Rd file 'predict.Rd':
     \examples lines wider than 100 characters:
     # cross.outer= 0, grid.search = "discrete",
     # lambda1.set=lambda1.1norm, show="none",
     # parms.coding = "none",
     # maxIter = 700, inner.val.method = "cv", cross.inner= 5,
     # seed=seed, verbose=FALSE )
    
    Rd file 'svm.fs.Rd':
     \usage lines wider than 90 characters:
     # chose the search method for tuning lambda1,2: 'interval' or 'discrete'
     # method for the inner validation: cross validation, gacv
     \examples lines wider than 100 characters:
     system.time(scad.fix<- svm.fs(t(train$x)[,1:100], y=train$y, fs.method="scad",
     cross.outer= 0, grid.search = "discrete ... [TRUNCATED]
     lambda1.set=lambda1.scad,
     parms.coding = "none", show="none",
     maxIter = 10, inner.val.method = "cv", ... [TRUNCATED]
     seed=seed, verbose=FALSE) )
     #epsi.set<-vector(); for (num in (1:9)) epsi.set<-sort(c(epsi.set, c(num*10^seq(-5, -1, 1 ))) )
     # cross.outer= 0, grid.search = "discrete ... [TRUNCATED]
     # lambda1.set=lambda1.1norm,
     # parms.coding = "none", show="none",
     # maxIter = 700, inner.val.method = "cv", ... [TRUNCATED]
     # seed=seed, verbose=FALSE )
     system.time( scad<- svm.fs(t(train$x)[,1:100], y=train$y, fs.method="scad", bounds=bounds,
     cross.outer= 0, grid.search = "interval ... [TRUNCATED]
     inner.val.method = "cv", cross.inner= 5 ... [TRUNCATED]
     seed=seed, parms.coding = "log2", show ... [TRUNCATED]
    
    These lines will be truncated in the PDF manual.
Flavors: r-devel-linux-x86_64-debian-clang, r-devel-linux-x86_64-debian-gcc, r-devel-linux-x86_64-fedora-clang, r-devel-linux-x86_64-fedora-gcc, r-patched-linux-x86_64, r-release-linux-x86_64

Version: 1.1
Check: Rd \usage sections
Result: NOTE
    S3 methods shown with full name in documentation object 'print':
     ‘print.scad.svm’ ‘print.1norm.svm’
    
    The \usage entries for S3 methods should use the \method markup and not
    their full name.
    See chapter ‘Writing R documentation files’ in the ‘Writing R
    Extensions’ manual.
Flavors: r-devel-linux-x86_64-debian-clang, r-devel-linux-x86_64-debian-gcc, r-devel-linux-x86_64-fedora-clang, r-devel-linux-x86_64-fedora-gcc, r-devel-windows-ix86+x86_64, r-patched-linux-x86_64, r-patched-solaris-x86, r-release-linux-x86_64, r-release-windows-ix86+x86_64, r-release-osx-x86_64, r-oldrel-windows-ix86+x86_64, r-oldrel-osx-x86_64

Version: 1.1
Check: examples
Result: ERROR
    Running examples in ‘penalizedSVM-Ex.R’ failed
    The error most likely occurred in:
    
    > base::assign(".ptime", proc.time(), pos = "CheckExEnv")
    > ### Name: predict
    > ### Title: Predict Method for Feature Selection SVM
    > ### Aliases: predict.penSVM
    >
    > ### ** Examples
    >
    >
    > seed<- 123
    > train<-sim.data(n = 200, ng = 100, nsg = 10, corr=FALSE, seed=seed )
    > print(str(train))
    List of 3
     $ x : num [1:100, 1:200] 0.547 0.635 -0.894 0.786 2.028 ...
     ..- attr(*, "dimnames")=List of 2
     .. ..$ : chr [1:100] "pos1" "pos2" "pos3" "pos4" ...
     .. ..$ : chr [1:200] "1" "2" "3" "4" ...
     $ y : Named num [1:200] 1 -1 -1 1 -1 -1 1 -1 -1 -1 ...
     ..- attr(*, "names")= chr [1:200] "1" "2" "3" "4" ...
     $ seed: num 123
    NULL
    >
    > #train standard svm
    > my.svm<-svm(x=t(train$x), y=train$y, kernel="linear")
    >
    > # test with other data
    > test<- sim.data(n = 200, ng = 100, nsg = 10, seed=(seed+1) )
    >
    > # Check accuracy standard SVM
    > my.pred <-ifelse( predict(my.svm, t(test$x)) >0,1,-1)
    > # Check accuracy:
    > table(my.pred, test$y)
    
    my.pred -1 1
     -1 81 23
     1 30 66
    >
    > # define set values of tuning parameter lambda1 for SCAD
    > lambda1.scad <- c (seq(0.01 ,0.05, .01), seq(0.1,0.5, 0.2), 1 )
    > # for presentation don't check all lambdas : time consuming!
    > # computation intensive; for demostration reasons only for the first 100 features
    > # and only for 10 Iterations maxIter=10, default maxIter=700
    >
    > system.time(fit.scad<- svm.fs(x=t(train$x)[,1:100],y=train$y, fs.method="scad", cross.outer= 0,
    + grid.search = "discrete", lambda1.set=lambda1.scad[1:3], show="none",
    + parms.coding = "none", maxIter=10,
    + inner.val.method = "cv", cross.inner= 5, seed=seed, verbose=FALSE))
    Error in UseMethod("svm.fs") :
     no applicable method for 'svm.fs' applied to an object of class "c('matrix', 'double', 'numeric')"
    Calls: system.time -> svm.fs
    Timing stopped at: 0.001 0 0.001
    Execution halted
Flavor: r-devel-linux-x86_64-debian-clang

Version: 1.1
Check: examples
Result: ERROR
    Running examples in ‘penalizedSVM-Ex.R’ failed
    The error most likely occurred in:
    
    > base::assign(".ptime", proc.time(), pos = "CheckExEnv")
    > ### Name: predict
    > ### Title: Predict Method for Feature Selection SVM
    > ### Aliases: predict.penSVM
    >
    > ### ** Examples
    >
    >
    > seed<- 123
    > train<-sim.data(n = 200, ng = 100, nsg = 10, corr=FALSE, seed=seed )
    > print(str(train))
    List of 3
     $ x : num [1:100, 1:200] 0.547 0.635 -0.894 0.786 2.028 ...
     ..- attr(*, "dimnames")=List of 2
     .. ..$ : chr [1:100] "pos1" "pos2" "pos3" "pos4" ...
     .. ..$ : chr [1:200] "1" "2" "3" "4" ...
     $ y : Named num [1:200] 1 -1 -1 1 -1 -1 1 -1 -1 -1 ...
     ..- attr(*, "names")= chr [1:200] "1" "2" "3" "4" ...
     $ seed: num 123
    NULL
    >
    > #train standard svm
    > my.svm<-svm(x=t(train$x), y=train$y, kernel="linear")
    >
    > # test with other data
    > test<- sim.data(n = 200, ng = 100, nsg = 10, seed=(seed+1) )
    >
    > # Check accuracy standard SVM
    > my.pred <-ifelse( predict(my.svm, t(test$x)) >0,1,-1)
    > # Check accuracy:
    > table(my.pred, test$y)
    
    my.pred -1 1
     -1 81 23
     1 30 66
    >
    > # define set values of tuning parameter lambda1 for SCAD
    > lambda1.scad <- c (seq(0.01 ,0.05, .01), seq(0.1,0.5, 0.2), 1 )
    > # for presentation don't check all lambdas : time consuming!
    > # computation intensive; for demostration reasons only for the first 100 features
    > # and only for 10 Iterations maxIter=10, default maxIter=700
    >
    > system.time(fit.scad<- svm.fs(x=t(train$x)[,1:100],y=train$y, fs.method="scad", cross.outer= 0,
    + grid.search = "discrete", lambda1.set=lambda1.scad[1:3], show="none",
    + parms.coding = "none", maxIter=10,
    + inner.val.method = "cv", cross.inner= 5, seed=seed, verbose=FALSE))
    Error in UseMethod("svm.fs") :
     no applicable method for 'svm.fs' applied to an object of class "c('matrix', 'double', 'numeric')"
    Calls: system.time -> svm.fs
    Timing stopped at: 0.001 0 0
    Execution halted
Flavor: r-devel-linux-x86_64-debian-gcc

Version: 1.1
Check: examples
Result: ERROR
    Running examples in ‘penalizedSVM-Ex.R’ failed
    The error most likely occurred in:
    
    > base::assign(".ptime", proc.time(), pos = "CheckExEnv")
    > ### Name: predict
    > ### Title: Predict Method for Feature Selection SVM
    > ### Aliases: predict.penSVM
    >
    > ### ** Examples
    >
    >
    > seed<- 123
    > train<-sim.data(n = 200, ng = 100, nsg = 10, corr=FALSE, seed=seed )
    > print(str(train))
    List of 3
     $ x : num [1:100, 1:200] 0.547 0.635 -0.894 0.786 2.028 ...
     ..- attr(*, "dimnames")=List of 2
     .. ..$ : chr [1:100] "pos1" "pos2" "pos3" "pos4" ...
     .. ..$ : chr [1:200] "1" "2" "3" "4" ...
     $ y : Named num [1:200] 1 -1 -1 1 -1 -1 1 -1 -1 -1 ...
     ..- attr(*, "names")= chr [1:200] "1" "2" "3" "4" ...
     $ seed: num 123
    NULL
    >
    > #train standard svm
    > my.svm<-svm(x=t(train$x), y=train$y, kernel="linear")
    >
    > # test with other data
    > test<- sim.data(n = 200, ng = 100, nsg = 10, seed=(seed+1) )
    >
    > # Check accuracy standard SVM
    > my.pred <-ifelse( predict(my.svm, t(test$x)) >0,1,-1)
    > # Check accuracy:
    > table(my.pred, test$y)
    
    my.pred -1 1
     -1 81 23
     1 30 66
    >
    > # define set values of tuning parameter lambda1 for SCAD
    > lambda1.scad <- c (seq(0.01 ,0.05, .01), seq(0.1,0.5, 0.2), 1 )
    > # for presentation don't check all lambdas : time consuming!
    > # computation intensive; for demostration reasons only for the first 100 features
    > # and only for 10 Iterations maxIter=10, default maxIter=700
    >
    > system.time(fit.scad<- svm.fs(x=t(train$x)[,1:100],y=train$y, fs.method="scad", cross.outer= 0,
    + grid.search = "discrete", lambda1.set=lambda1.scad[1:3], show="none",
    + parms.coding = "none", maxIter=10,
    + inner.val.method = "cv", cross.inner= 5, seed=seed, verbose=FALSE))
    Error in UseMethod("svm.fs") :
     no applicable method for 'svm.fs' applied to an object of class "c('matrix', 'double', 'numeric')"
    Calls: system.time -> svm.fs
    Timing stopped at: 0 0 0
    Execution halted
Flavor: r-patched-linux-x86_64

Version: 1.1
Check: examples
Result: ERROR
    Running examples in ‘penalizedSVM-Ex.R’ failed
    The error most likely occurred in:
    
    > base::assign(".ptime", proc.time(), pos = "CheckExEnv")
    > ### Name: predict
    > ### Title: Predict Method for Feature Selection SVM
    > ### Aliases: predict.penSVM
    >
    > ### ** Examples
    >
    >
    > seed<- 123
    > train<-sim.data(n = 200, ng = 100, nsg = 10, corr=FALSE, seed=seed )
    > print(str(train))
    List of 3
     $ x : num [1:100, 1:200] 0.547 0.635 -0.894 0.786 2.028 ...
     ..- attr(*, "dimnames")=List of 2
     .. ..$ : chr [1:100] "pos1" "pos2" "pos3" "pos4" ...
     .. ..$ : chr [1:200] "1" "2" "3" "4" ...
     $ y : Named num [1:200] 1 -1 -1 1 -1 -1 1 -1 -1 -1 ...
     ..- attr(*, "names")= chr [1:200] "1" "2" "3" "4" ...
     $ seed: num 123
    NULL
    >
    > #train standard svm
    > my.svm<-svm(x=t(train$x), y=train$y, kernel="linear")
    >
    > # test with other data
    > test<- sim.data(n = 200, ng = 100, nsg = 10, seed=(seed+1) )
    >
    > # Check accuracy standard SVM
    > my.pred <-ifelse( predict(my.svm, t(test$x)) >0,1,-1)
    > # Check accuracy:
    > table(my.pred, test$y)
    
    my.pred -1 1
     -1 81 23
     1 30 66
    >
    > # define set values of tuning parameter lambda1 for SCAD
    > lambda1.scad <- c (seq(0.01 ,0.05, .01), seq(0.1,0.5, 0.2), 1 )
    > # for presentation don't check all lambdas : time consuming!
    > # computation intensive; for demostration reasons only for the first 100 features
    > # and only for 10 Iterations maxIter=10, default maxIter=700
    >
    > system.time(fit.scad<- svm.fs(x=t(train$x)[,1:100],y=train$y, fs.method="scad", cross.outer= 0,
    + grid.search = "discrete", lambda1.set=lambda1.scad[1:3], show="none",
    + parms.coding = "none", maxIter=10,
    + inner.val.method = "cv", cross.inner= 5, seed=seed, verbose=FALSE))
    Error in UseMethod("svm.fs") :
     no applicable method for 'svm.fs' applied to an object of class "c('matrix', 'double', 'numeric')"
    Calls: system.time -> svm.fs
    Timing stopped at: 0 0 0.001
    Execution halted
Flavor: r-release-linux-x86_64