differential_evolution {niarules} | R Documentation |
Implementation of Differential Evolution metaheuristic algorithm.
Description
This function uses Differential Evolution, a stochastic population-based optimization algorithm, to find the optimal numerical association rule.
Usage
differential_evolution(
d = 10,
np = 10,
f = 0.5,
cr = 0.9,
nfes = 1000,
features,
data,
is_time_series = FALSE
)
Arguments
d |
Dimension of the problem (default: 10). |
np |
Population size (default: 10). |
f |
The differential weight, controlling the amplification of the difference vector (default: 0.5). |
cr |
The crossover probability, determining the probability of a component being replaced (default: 0.9). |
nfes |
The maximum number of function evaluations (default: 1000). |
features |
A list containing information about features, including type and bounds. |
data |
A data frame representing instances in the dataset. |
is_time_series |
A boolean indicating whether the dataset is time series. |
Value
A list containing the best solution, its fitness value, and the number of function evaluations and list of identified association rules.