Prints as text the detail on a given experiment along with summarized results (if computed)

This function takes a population of models and makes three plots, feature prevalence in population, feature abundance by class and feature prevalence by class

Usage

analyzePopulationFeatures(
  pop,
  X,
  y,
  res_clf,
  makeplot = TRUE,
  name = "",
  ord.feat = "importance",
  make.network = TRUE,
  network.layout = "circular",
  network.alpha = 1e-04,
  verbose = TRUE,
  pdf.dims = c(width = 25, height = 20),
  filter.perc = 0.05,
  k_penalty = 0.75/100,
  k_max = 0
)

Arguments

pop:

a population of models

X:

the X dataset where to compute the abundance and prevalence

y:

the target class

res_clf:

the results of the classifier as well as the config object

makeplot:

make a pdf file with the resulting plots (default:TRUE)

name:

the suffix of the pdf file (default:"")

ord.feat:

which ordering approch to use for the features (default:importance) in the models, anything else will compute automatic hierarchical ordering based on the manhattan distance

make.network:

build a network and print it out in the pdf

network.layout:

the network layout by default is circular (layout_in_circle) and will be a weighted Fruchterman-Reingold otherwise

network.alpha:

threshold of significance for the network (default:1e-4)

verbose:

print out informaiton

pdf.dims:

dimensions of the pdf object (default: c(w = 25, h = 20))

filter.perc:

filter by prevalence percentage in the population between 0 and 1 (default:0.05)

k_penalty:

the sparsity penalty needed to select the best models of the population (default:0.75/100).

k_max:

select the best population below a given threshold. If (default:0) no selection is performed.

Value

plots if makeplot is FALSE