Create a new DGP (data-generating process)

Create a DGP which can generate() data in an Experiment.

Usage

create_dgp(.dgp_fun, .name = NULL, ...)

Arguments

.dgp_fun: The user-defined data-generating process function.
.name: (Optional) An optional name for the DGP, helpful for later identification.
...: User-defined default arguments to pass to .dgp_fun() when DGP$generate() is called.

Value

A new DGP object.

Examples

# create an example DGP function
dgp_fun <- function(n, beta, rho, sigma) {
  cov_mat <- matrix(c(1, rho, rho, 1), byrow = TRUE, nrow = 2, ncol = 2)
  X <- MASS::mvrnorm(n = n, mu = rep(0, 2), Sigma = cov_mat)
  y <- X %*% beta + rnorm(n, sd = sigma)
  return(list(X = X, y = y))
}

# create DGP (with uncorrelated features)
dgp <- create_dgp(.dgp_fun = dgp_fun,
                  .name = "Linear Gaussian DGP",
                  # additional named parameters to pass to dgp_fun() by default
                  n = 50, beta = c(1, 0), rho = 0, sigma = 1)

print(dgp)
#> DGP Name: Linear Gaussian DGP 
#>    Function: function (n, beta, rho, sigma)  
#>    Parameters: List of 4
#>      $ n    : num 50
#>      $ beta : num [1:2] 1 0
#>      $ rho  : num 0
#>      $ sigma: num 1

data_uncorr <- dgp$generate()
cor(data_uncorr$X)
#>           [,1]      [,2]
#> [1,] 1.0000000 0.2131148
#> [2,] 0.2131148 1.0000000

data_corr <- dgp$generate(rho = 0.7)
cor(data_corr$X)
#>           [,1]      [,2]
#> [1,] 1.0000000 0.7815758
#> [2,] 0.7815758 1.0000000