Trying to work around Random forest in R.
rf<- randomForest(train$Loan_Status~., data=train, mtry=5,importance=TRUE, ntree=200,na.action=rfImpute(train$Loan_Status ~., train),allowParallel=TRUE)
Trying to work around Random forest in R.
rf<- randomForest(train$Loan_Status~., data=train, mtry=5,importance=TRUE, ntree=200,na.action=rfImpute(train$Loan_Status ~., train),allowParallel=TRUE)
na.action does not work like that, it takes a function such as na.fail or na.omit as input.
Try to use rfImpute as in documented example
data(iris)
iris.na <- iris
set.seed(111)
## artificially drop some data values.
for (i in 1:4) iris.na[sample(150, sample(20)), i] <- NA
set.seed(222)
iris.imputed <- rfImpute(Species ~ ., iris.na)
set.seed(333)
iris.rf <- randomForest(Species ~ ., iris.imputed)
print(iris.rf)