Plot overall validation metrics by adjustment method — plot_validation

Builds a method-by-metric matrix from validate_flow_overall() results or a data frame containing one row per method. Cell fill is scaled within each metric so unlike metrics are not forced onto a common raw scale, while cell labels show the original metric values.

Usage

plot_validation_metrics(
  metrics,
  error_measures = c("mae", "rmse", "mape"),
  metric_cols = NULL,
  comparisons = "adjusted_vs_benchmark",
  methods = NULL,
  method_col = "method",
  method_family_col = NULL,
  method_labels = NULL,
  palette = NULL,
  relative_error_breaks = seq(0, 100, by = 10)
)

plot_validate_flow_metrics(...)

Arguments

metrics: A data frame, one validate_flow_overall() result, or a named list of validate_flow_overall() results.
error_measures: Character vector of error measure IDs or labels to plot. Defaults to c("mae", "rmse", "mape"). Common labels such as "MAE", "RMSE", "MAPE", and "Mean absolute error" are accepted.
metric_cols: Compatibility alias for error_measures.
comparisons: Flow comparison(s) to plot. Defaults to "adjusted_vs_benchmark". Use "all" when metrics contains rows for all supported comparisons. When "raw_vs_benchmark" is included, it is shown as a single unadjusted raw MPD baseline row.
methods: Optional character vector of method identifiers or display labels to include. Default NULL includes all methods.
method_col: Column containing the method identifier. Default "method".
method_family_col: Optional column containing method-family labels. Retained for compatibility with earlier prototypes; the metric matrix is organised by method and metric.
method_labels: Optional named character vector used to relabel methods.
palette: Optional character vector of colours for the relative-error fill scale. Defaults to a yellow-green-blue sequence suitable for ordered error intensity.
relative_error_breaks: Numeric percentage cut points used to bin the within-metric relative-error fill scale. Default seq(0, 100, by = 10) produces legend ranges such as 0-10, 11-20, and 91-100.

Value

A ggplot object.