Skip to content

VSURF

Variable Selection Using Random Forests

v1.2.1 · Oct 21, 2025 · GPL (>= 2)

Description

Three steps variable selection procedure based on random forests. Initially developed to handle high dimensional data (for which number of variables largely exceeds number of observations), the package is very versatile and can treat most dimensions of data, for regression and supervised classification problems. First step is dedicated to eliminate irrelevant variables from the dataset. Second step aims to select all variables related to the response for interpretation purpose. Third step refines the selection by eliminating redundancy in the set of variables selected by the second step, for prediction purpose. Genuer, R. Poggi, J.-M. and Tuleau-Malot, C. (2015) <https://journal.r-project.org/articles/RJ-2015-018/>.

Downloads

521

Last 30 days

7100th

521

Last 90 days

521

Last year

CRAN Check Status

1 ERROR
13 OK
Show all 14 flavors
Flavor Status
r-devel-linux-x86_64-debian-clang OK
r-devel-linux-x86_64-debian-gcc OK
r-devel-linux-x86_64-fedora-clang OK
r-devel-linux-x86_64-fedora-gcc OK
r-devel-macos-arm64 ERROR
r-devel-windows-x86_64 OK
r-oldrel-macos-arm64 OK
r-oldrel-macos-x86_64 OK
r-oldrel-windows-x86_64 OK
r-patched-linux-x86_64 OK
r-release-linux-x86_64 OK
r-release-macos-arm64 OK
r-release-macos-x86_64 OK
r-release-windows-x86_64 OK
Check details (14 non-OK)
OK r-devel-linux-x86_64-debian-clang

*


            
OK r-devel-linux-x86_64-debian-gcc

*


            
OK r-devel-linux-x86_64-fedora-clang

*


            
OK r-devel-linux-x86_64-fedora-gcc

*


            
ERROR r-devel-macos-arm64

tests

  Running ‘testthat.R’ [2s/2s]
Running the tests in ‘tests/testthat.R’ failed.
Complete output:
  > library(testthat)
  > library(VSURF)
  > 
  > test_check("VSURF")
  Saving _problems/test_orange-35.R
  Saving _problems/test_orange-39.R
  Saving _problems/test_orange-41.R
  Saving _problems/test_orange-55.R
  Saving _problems/test_orange-56.R
  Saving _problems/test_orange-69.R
  Saving _problems/test_orange-70.R
  Saving _problems/test_orange-71.R
  [ FAIL 8 | WARN 1 | SKIP 0 | PASS 25 ]
  
  ══ Failed tests ════════════════════════════════════════════════════════════════
  ── Failure ('test_orange.R:32:5'): Variable importance ─────────────────────────
  Expected `orange.vsurf$imp.mean.dec` to equal `c(...)`.
  Differences:
  9/9 mismatches (average diff: 10.3)
  [1] 2956.4 - 2954.5 ==   1.96
  [2]  201.3 -  216.3 == -14.95
  [3]  101.2 -   75.1 ==  26.08
  [4]   13.9 -   19.9 ==  -6.06
  [5]  -13.2 -  -24.7 ==  11.55
  [6]  -29.6 -  -32.0 ==   2.37
  [7]  -29.9 -  -39.0 ==   9.13
  [8]  -36.7 -  -40.3 ==   3.59
  [9]  -37.8 -  -54.5 ==  16.73
  ── Failure ('test_orange.R:36:5'): Variable importance ─────────────────────────
  Expected `orange.vsurf$imp.sd.dec` to equal `c(...)`.
  Differences:
  9/9 mismatches (average diff: 13.9)
  [1] 266.5 - 200.8 == 65.666
  [2]  51.2 -  59.5 == -8.212
  [3]  98.2 -  65.9 == 32.241
  [4]  52.6 -  55.7 == -3.123
  [5]  61.6 -  58.0 ==  3.610
  [6]  46.8 -  44.2 ==  2.633
  [7]  57.5 -  57.1 ==  0.374
  [8]  39.1 -  46.9 == -7.797
  [9]  41.2 -  42.4 == -1.175
  ── Failure ('test_orange.R:40:5'): Variable importance ─────────────────────────
  Expected `orange.vsurf$imp.mean.dec.ind` to be identical to `c(2L, 1L, 5L, 8L, 7L, 3L, 6L, 9L, 4L)`.
  Differences:
  4/9 mismatches (average diff: 3.5)
  [5] 6 - 7 == -1
  [6] 9 - 3 ==  6
  [7] 7 - 6 ==  1
  [8] 3 - 9 == -6
  ── Failure ('test_orange.R:53:5'): OOB erros of nested models ──────────────────
  Expected `orange.vsurf$err.interp` to equal `c(723.4782, 447.9998, 779.2947)`.
  Differences:
  3/3 mismatches (average diff: 2.08)
  [1] 723 - 723 == -0.317
  [2] 447 - 448 == -1.053
  [3] 774 - 779 == -4.860
  ── Failure ('test_orange.R:56:5'): OOB erros of nested models ──────────────────
  Expected `orange.vsurf$err.pred` to equal 721.4986.
  Differences:
  1/1 mismatches
  [1] 721 - 721 == -0.483
  ── Failure ('test_orange.R:68:5'): Thresholds for the 3 steps ──────────────────
  Expected `min(orange.vsurf$pred.pruned.tree)` to equal 42.413.
  Differences:
  1/1 mismatches
  [1] 56 - 42.4 == 13.6
  ── Failure ('test_orange.R:70:5'): Thresholds for the 3 steps ──────────────────
  Expected `orange.vsurf$sd.min` to equal 16.85953.
  Differences:
  1/1 mismatches
  [1] 19 - 16.9 == 2.13
  ── Failure ('test_orange.R:71:5'): Thresholds for the 3 steps ──────────────────
  Expected `orange.vsurf$mean.jump` to equal 331.2949.
  Differences:
  1/1 mismatches
  [1] 327 - 331 == -3.81
  
  [ FAIL 8 | WARN 1 | SKIP 0 | PASS 25 ]
  Error:
  ! Test failures.
  Execution halted
OK r-devel-windows-x86_64

*


            
OK r-oldrel-macos-arm64

*


            
OK r-oldrel-macos-x86_64

*


            
OK r-oldrel-windows-x86_64

*


            
OK r-patched-linux-x86_64

*


            
OK r-release-linux-x86_64

*


            
OK r-release-macos-arm64

*


            
OK r-release-macos-x86_64

*


            
OK r-release-windows-x86_64

*


            

Check History

ERROR 13 OK · 0 NOTE · 0 WARNING · 1 ERROR · 0 FAILURE Mar 9, 2026
ERROR r-devel-macos-arm64

tests

  Running ‘testthat.R’ [2s/2s]
Running the tests in ‘tests/testthat.R’ failed.
Complete output:
  > library(testthat)
  > library(VSURF)
  > 
  > test_check("VSURF")
  Saving _problems/test_orange-35.R
  Saving _problems/test_orange-39.R
  Saving _problems/test_orange-41.R
  Saving _problems/test_orange-55.R
  Saving _problems/test_orange-56.R
  Saving _problems/test_orange-69.R
  Saving _problems/test_orange-70.R
  Saving _problems/test_orange-71.R
  [ FAIL 8 | WARN 1 | SKIP 0 | PASS 25 ]
  
  

Reverse Dependencies (2)

imports

suggests

Dependency Network

Dependencies Reverse dependencies doParallel foreach randomForest rpart SAiVE MSclassifR VSURF

Version History

new 1.2.1 Mar 10, 2026