External validation on new data — external_validate • rmorie

External validation on new data

Usage

external_validate(predict_fn, X_external, y_external, X_development = NULL)

Arguments

predict_fn: A function (X) -> probability vector (model already bound by closure).
X_external: Matrix or data frame of features.
y_external: Outcome vector.
X_development: Optional development-data features for KS-based domain-shift diagnostics.

Value

An object of class "class_name".

Examples

set.seed(1)
X <- matrix(rnorm(200 * 3), 200, 3)
y <- as.integer(plogis(X[, 1] - 0.5 * X[, 2]) > runif(200))
mdl <- suppressWarnings(
  glm(y ~ ., data = data.frame(y = y, X), family = binomial()))
predict_fn <- function(X) predict(mdl, newdata = data.frame(X),
                                  type = "response")
res <- external_validate(predict_fn, X, y)
res$discrimination$auroc
#> [1] 0.7827131