Detect Model Extrapolation

Checks whether prediction locations fall outside the environmental envelope of training data. Uses per-variable range checks and multivariate Mahalanobis distance.

Usage

borg_extrapolation(train, new, predictors = NULL, coords = NULL)

Arguments

train

Data frame of training data.

new

Data frame of prediction data (same predictor columns).

predictors

Character vector. Predictor column names. If NULL, uses all shared numeric columns.

coords

Character vector of length 2. Coordinate columns in new for spatial mapping. Optional.

Value

A data frame with class "borg_extrapolation" containing:

mahal_dist

Mahalanobis distance to training centroid

n_vars_outside

Number of variables outside training range

vars_outside

Comma-separated names of out-of-range variables

extrapolating

Logical. TRUE if any variable is out of range

x, y

Coordinates (if provided)

Examples

set.seed(42)
train <- data.frame(a = rnorm(80), b = rnorm(80))
new <- data.frame(a = c(rnorm(10), rnorm(10, mean = 5)),
                   b = c(rnorm(10), rnorm(10, mean = 5)))
ext <- borg_extrapolation(train, new)
table(ext$extrapolating)