Evaluate filter functions

Source: R/evaluation.R

filter_evaluate evaluates filter function with provided filter vectors.

filter_evaluate(
  ...,
  dat,
  group_ind,
  num_intervals,
  percent_overlap,
  arg_mapper = list()
)

Arguments

...

Filter objects. The classes of the objects should be filter and include an attribute filter which is the name of the corresponding filter function.
dat

Matrix or dataset where rows are data points and columns are predictive variables.
group_ind

A vector of group names each of the samples belongs to.
arg_mapper

A list for additional arguments for mapper.sta.

Value

A data.frame of Shannon indices and spread measures under given filter functions. The first column contents names of filter functions, and the second and third columns are the shannon indices and spread measures, respectively.

Examples

tp_data <- chicken_generator(1)
tp_dist <- dist(tp_data[,-1])
a <- filter_eccen(dist = tp_dist, p = 2)
b <- filter_coordinate(tp_data[,-1], 2)
c <- filter_gaussian(dist=tp_dist, sigma=1)
filter_evaluate(a,b,c,
                dat = tp_data, group_ind = tp_data$Group,
                num_intervals = 10, percent_overlap = 70)

# Add additional arguments (NOT RUN)
if(FALSE) {
  filter_evaluate(a,b,c,
                  dat = tp_data, group_ind = tp_data$Group,
                  num_intervals = 10, percent_overlap = 70,
                  arg_mapper = list(n_class = 1))
}