Generate a tree from a feature matrix

Fits a classification tree (or tree ensemble) with the taxon column as the response and every other column as a feature.

Usage

generateTree(
  data,
  target_col,
  method = c("rpart", "randomForest", "gbm"),
  params = list()
)

Arguments

data

A data frame containing the feature matrix.

target_col

Name of the target/response column.

method

"rpart", "randomForest" (requires the 'randomForest' package), or "gbm" (requires the 'gbm' package; "multinomial" distribution unless the response is numeric 0/1, which uses "bernoulli").

params

Optional list of arguments passed to the fitting function, overriding the defaults.

Value

A fitted rpart, randomForest or gbm object.

Examples

features <- data.frame(
  family = factor(c("A", "B", "C", "A", "B", "C")),
  fin = factor(c("x", "y", "y", "x", "y", "y")),
  head = factor(c("p", "p", "q", "p", "p", "q"))
)
generateTree(features, "family",
  params = list(control = rpart::rpart.control(minsplit = 2, minbucket = 1))
)
#> n= 6 
#> 
#> node), split, n, loss, yval, (yprob)
#>       * denotes terminal node
#> 
#> 1) root 6 4 A (0.3333333 0.3333333 0.3333333)  
#>   2) fin=x 2 0 A (1.0000000 0.0000000 0.0000000) *
#>   3) fin=y 4 2 B (0.0000000 0.5000000 0.5000000)  
#>     6) head=p 2 0 B (0.0000000 1.0000000 0.0000000) *
#>     7) head=q 2 0 C (0.0000000 0.0000000 1.0000000) *