Skip to contents

Computes goodness-of-fit metrics from fitted(object) against the observed response, and prints them with what they are to be read against. A character or factor response is an error; a logical response is scored as 0/1.

Usage

# S3 method for class 'spatial_fit'
summary(object, ...)

Arguments

object

A spatial_fit object.

...

Not used.

Value

An object of class summary.spatial_fit: a list with class, formula, n, response_var, predictor_vars, info and in_sample (the metric data.frame, out-of-bag for an rf_fit).

What the metrics are computed on

For a GWR or a Bayesian GP fit these are in-sample metrics: fitted() returns values computed at the training locations from the model that saw them. For a random forest they are out-of-bag, because fitted() on an rf_fit returns out-of-bag predictions (see fit_rf_model()). The two are not comparable, and print() on the result says which one it holds, from $info$fitted_are_oob. Use compare_models_cv() to compare backends.

Adjusted \(R^2\) is not computed: a GWR's effective number of parameters far exceeds the global predictor count, and a GP model has no simple p.

For a GWR, print() on the result adds what the in-sample metrics are to be read against: the effective number of parameters and residual degrees of freedom, the number of local windows of deficient rank, the number of locations when observations share one, and the AICc and RMSE of one global least-squares regression on the same rows beside the fit's own AICc ($info$global_ols; see fit_gwr_model()).

MAPE and SMAPE skip rows whose denominator is zero; n_MAPE and n_SMAPE count the rows they used (see "Percentage errors on responses with zeros" in model_metrics()).

Examples

library(sf)
set.seed(1)
pts <- st_as_sf(
  data.frame(x = 5e5 + runif(60, 0, 1000), y = 5e6 + runif(60, 0, 1000),
             a = rnorm(60)),
  coords = c("x", "y"), crs = 32632
)
pts$z <- 10 + 2 * pts$a + rnorm(60, 0, 0.3)
fit <- fit_rf_model(pts, "z", "a", num_trees = 50, seed = 1)
summary(fit)            # out-of-bag metrics for a forest
#> Summary of <rf_fit> fit (n = 60)
#> 
#>   Formula: z ~ a
#> 
#>   Out-of-bag metrics (NOT in-sample; see ?fit_rf_model):
#>     RMSE    = 0.4094
#>     MAE     = 0.3270
#>     R^2     = 0.9493
#>     SMAPE   = 3.33%