Forest-plot style comparison of benchmark results

Takes a data.frame of benchmark results and produces a forest-plot style figure comparing baseline and GNN performance per trait. Each trait appears on the y-axis; points mark RMSE (continuous/count) or accuracy (binary/categorical) for the two methods, connected by a horizontal line colour-coded by whether the GNN improves over the baseline.

Usage

plot_comparison(
  results,
  metric = NULL,
  methods = c("baseline", "pigauto"),
  ...
)

Arguments

results: A data.frame with columns trait, type, metric, method, and value. Typically the output of compare_methods, evaluate, or reshaped output from evaluate_imputation.
metric: Character. Which metric to compare. Default NULL auto-selects: "rmse" for continuous/count traits and "accuracy" for binary/categorical traits. If a single metric name is supplied, only traits with that metric are shown.
methods: Character vector of length 2: the baseline method name and the pigauto method name. Default c("baseline", "pigauto"), matching the labels returned by compare_methods and evaluate.
...: Additional arguments passed to plot().

Value

Invisible NULL. Called for its side effect (plotting).

Details

When both RMSE and accuracy metrics are present and metric is NULL, a two-panel figure is produced automatically.

Examples

# \donttest{
results <- data.frame(
  trait = rep("Mass", 2L), type = rep("continuous", 2L),
  metric = rep("rmse", 2L), method = c("baseline", "pigauto"),
  value = c(1, 0.8)
)
plot_comparison(results)

plot_comparison(results, metric = "rmse")
# }