Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/alexplatasl/dplbnde/llms.txt

Use this file to discover all available pages before exploring further.

shadeils combines SHADE (adaptive DE) with an iterative Solis-Wets local search. After every ls_freq DE generations, a local search is applied to the best individual. A partial restart is triggered when stagnation is detected.

​
Usage

shadeils(
  NP = 40,
  G = 100,
  data,
  class.name,
  c = 0.1,
  structure = c("nb", "tancl", "tan", "hc"),
  pB = 0.05,
  edgelist = NULL,
  ls_budget_ratio = 0.3,
  ls_freq = 5,
  threshold_improvement = 0.01,
  max_iters_no_improve = 3,
  verbose = 25,
  ...
)

​
Parameters

​
NP
integer
default:"40"
Population size.
​
G
integer
default:"100"
Maximum generations.
​
data
data.frame
required
Training data frame.
​
class.name
character
required
Class variable column name.
​
c
numeric
default:"0.1"
SHADE memory adaptation rate. Range [0, 0.2].
​
structure
character
default:"nb"
BN structure: "nb", "tan", "tancl", "hc".
​
pB
numeric
default:"0.05"
Fraction of best individuals for mutation.
​
edgelist
matrix
Optional custom BN topology (edges × 2 matrix).
​
ls_budget_ratio
numeric
default:"0.3"
Fraction of NP used as local search evaluation budget per call.
​
ls_freq
integer
default:"5"
Apply local search every this many generations.
​
threshold_improvement
numeric
default:"0.01"
Minimum relative improvement before incrementing the stagnation counter.
​
max_iters_no_improve
integer
default:"3"
Consecutive stagnation cycles before a partial population restart.
​
verbose
integer
default:"25"
Print progress every this many generations.
​
...
Extra arguments for bnclassify::tan_cl or bnclassify::tan_hc.

​
Return value

Object of class DE: Best, BestCLL, pobFinal, CLLPobFinal, N.evals, convergence, evaluations.

​
Example

library(dplbnDE)
data(car)

result <- shadeils(
  NP = 20, G = 25,
  data = car,
  class.name = names(car)[7],
  structure = "tan",
  ls_freq = 5,
  verbose = 5
)
print(result)

Build docs developers (and LLMs) love

Get started for freeTalk to us