Simulate a binomial target and some features

sim_binom.R

sim_binom <- function(n_samples = 1000, n_features = 2,
                      true_target_prob = 0.5, beta = NULL, seed = NULL) {

  if(!is.null(seed)) {
    set.seed(seed)
  }

  x = matrix(rnorm(n_samples * n_features),
             nrow = n_samples, ncol = n_features)

  b0 = log(true_target_prob / (1 - true_target_prob))

  if(is.null(beta)) {
    beta = rnorm(n_features, mean = 0, sd = 0.5)
  } else {
    stopifnot(length(beta) == n_features, is.vector(beta), is.numeric(beta))
  }

  z = b0 + beta %*% t(x)

  prob = as.vector(1 / (1 + exp(-z)))

  y = rbinom(n_samples, 1, prob = prob)

  df = as.data.frame(x)
  df$y = y
  df$prob = prob

  list(df = df,
       beta_0 = b0,
       beta = beta)
}