Filter using the Boruta algorithm for feature selection.
If keep = "tentative", confirmed and tentative features are returned.
Note that there is no ordering in the selected features.
Selected features get a score of 1, deselected features get a score of 0.
The order of selected features is random.
In combination with mlr3pipelines, only the filter criterion cutoff makes sense.
References
Kursa MB, Rudnicki WR (2010). “Feature Selection with the Boruta Package.” Journal of Statistical Software, 36(11), 1-13.
See also
PipeOpFilter for filter-based feature selection.
Other Filter:
Filter,
mlr_filters,
mlr_filters_anova,
mlr_filters_auc,
mlr_filters_carscore,
mlr_filters_carsurvscore,
mlr_filters_cmim,
mlr_filters_correlation,
mlr_filters_disr,
mlr_filters_find_correlation,
mlr_filters_importance,
mlr_filters_information_gain,
mlr_filters_jmi,
mlr_filters_jmim,
mlr_filters_kruskal_test,
mlr_filters_mim,
mlr_filters_mrmr,
mlr_filters_njmim,
mlr_filters_performance,
mlr_filters_permutation,
mlr_filters_relief,
mlr_filters_selected_features,
mlr_filters_univariate_cox,
mlr_filters_variance
Super class
mlr3filters::Filter -> FilterBoruta
Examples
# \donttest{
if (requireNamespace("Boruta")) {
task = mlr3::tsk("sonar")
filter = flt("boruta")
filter$calculate(task)
as.data.table(filter)
}
#> Loading required namespace: Boruta
#> feature score
#> <char> <num>
#> 1: V16 1
#> 2: V15 1
#> 3: V27 1
#> 4: V4 1
#> 5: V44 1
#> 6: V9 1
#> 7: V52 1
#> 8: V17 1
#> 9: V31 1
#> 10: V26 1
#> 11: V13 1
#> 12: V49 1
#> 13: V46 1
#> 14: V19 1
#> 15: V18 1
#> 16: V10 1
#> 17: V23 1
#> 18: V45 1
#> 19: V36 1
#> 20: V1 1
#> 21: V47 1
#> 22: V22 1
#> 23: V5 1
#> 24: V51 1
#> 25: V20 1
#> 26: V37 1
#> 27: V48 1
#> 28: V35 1
#> 29: V21 1
#> 30: V28 1
#> 31: V12 1
#> 32: V11 1
#> 33: V7 0
#> 34: V29 0
#> 35: V55 0
#> 36: V42 0
#> 37: V40 0
#> 38: V34 0
#> 39: V32 0
#> 40: V60 0
#> 41: V25 0
#> 42: V39 0
#> 43: V3 0
#> 44: V56 0
#> 45: V24 0
#> 46: V54 0
#> 47: V14 0
#> 48: V53 0
#> 49: V30 0
#> 50: V2 0
#> 51: V41 0
#> 52: V57 0
#> 53: V6 0
#> 54: V8 0
#> 55: V43 0
#> 56: V33 0
#> 57: V58 0
#> 58: V38 0
#> 59: V50 0
#> 60: V59 0
#> feature score
# }