mlr3filters
Package website: release | dev
{mlr3filters} adds filters, feature selection methods and embedded feature selection methods of algorithms to {mlr3}.
Installation
CRAN version
install.packages("mlr3filters")
Development version
remotes::install_github("mlr-org/mlr3filters")
Filters
Filter Example
set.seed(1)
library("mlr3")
library("mlr3filters")
task = tsk("pima")
filter = flt("auc")
as.data.table(filter$calculate(task))
## feature score
## 1: glucose 0.2927906
## 2: insulin 0.2316288
## 3: mass 0.1870358
## 4: age 0.1869403
## 5: triceps 0.1625115
## 6: pregnant 0.1195149
## 7: pressure 0.1075760
## 8: pedigree 0.1062015
Implemented Filters
Name | Task Type | Feature Types | Package |
---|---|---|---|
anova | Classif | Integer, Numeric | stats |
auc | Classif | Integer, Numeric | mlr3measures |
carscore | Regr | Numeric | care |
cmim | Classif & Regr | Integer, Numeric, Factor, Ordered | praznik |
correlation | Regr | Integer, Numeric | stats |
disr | Classif | Integer, Numeric, Factor, Ordered | praznik |
find_correlation | Classif & Regr | Integer, Numeric | stats |
importance | Universal | Logical, Integer, Numeric, Factor, Ordered | rpart |
information_gain | Classif & Regr | Integer, Numeric, Factor, Ordered | FSelectorRcpp |
jmi | Classif | Integer, Numeric, Factor, Ordered | praznik |
jmim | Classif | Integer, Numeric, Factor, Ordered | praznik |
kruskal_test | Classif | Integer, Numeric | stats |
mim | Classif | Integer, Numeric, Factor, Ordered | praznik |
mrmr | Classif | Integer, Numeric, Factor, Ordered | praznik |
njmim | Classif | Integer, Numeric, Factor, Ordered | praznik |
performance | Universal | Logical, Integer, Numeric, Factor, Ordered | |
permutation | Universal | Logical, Integer, Numeric, Factor, Ordered | |
variance | Classif & Regr | Integer, Numeric | stats |
Variable Importance Filters
The following learners allow the extraction of variable importance and
therefore are supported by FilterImportance
:
## [1] "classif.featureless" "classif.ranger" "classif.rpart"
## [4] "classif.xgboost" "regr.featureless" "regr.ranger"
## [7] "regr.rpart" "regr.xgboost"
If your learner is not listed here but capable of extracting variable importance from the fitted model, the reason is most likely that it is not yet integrated in the package mlr3learners or the extra learner organization. Please open an issue so we can add your package.
Some learners need to have their variable importance measure “activated” during learner creation. For example, to use the “impurity” measure of Random Forest via the {ranger} package:
task = tsk("iris")
lrn = lrn("classif.ranger")
lrn$param_set$values = list(importance = "impurity")
filter = flt("importance", learner = lrn)
filter$calculate(task)
head(as.data.table(filter), 3)
## feature score
## 1: Petal.Width 43.66496
## 2: Petal.Length 43.10837
## 3: Sepal.Length 10.21944
Performance Filter
FilterPerformance
is a univariate filter method which calls
resample()
with every predictor variable in the dataset and ranks the
final outcome using the supplied measure. Any learner can be passed to
this filter with classif.rpart
being the default. Of course, also
regression learners can be passed if the task is of type “regr”.