Skip to contents

Summarise an ensemble across samples

Source: R/solve_by_sample.R
sample_summary.Rd

Median and quantiles of a variable across the samples of a solve_by_sample() ensemble — the input for range plots of capacity.

Each sample estimates the whole year, so these are quantiles of repeated estimates, not of a partitioned total.

mean is weighted by each sample's year_fraction, because samples need not cover equal shares of the year — method = "sequential" folds a trailing singleton block into its predecessor, so one sample can be larger than the rest. The quantiles are unweighted order statistics of the replicates; a message says so whenever the coverage varies.

Usage

sample_summary(x, name, probs = c(0.05, 0.5, 0.95), by = NULL, ...)

Arguments

x

a by_sample result.

name

character, the variable to summarise (e.g. "vTechCap").

probs

numeric, quantiles to report.

by

character, columns to group by; defaults to every key column the variable carries apart from sample and value.

...

passed to getData().

Value

a data.frame with the grouping columns, n, mean (coverage-weighted) and one column per requested quantile (unweighted).

See also

solve_by_sample()

Examples

if (FALSE) { # \dontrun{
open_project(tempdir())

ek  <- topia$modules$electricity$R3
mod <- newModel("TOPIA", data = ek$repo,
                calendar = topia$modules$calendars$s4_h24,
                region = ek$regions,
                horizon = topia$modules$horizons$base,
                discount = 0.05)
mod <- setGeoscale(mod, ek$geoscale)
res <- solve_by_sample(mod, name = "BY_SAMPLE", level = "SEASON",
                       sample_size = 2, n = 2, method = "random", seed = 1,
                       solver = solver_options$glpk)

sample_summary(res, "vTechCap", by = "tech")

# a wider band, by region as well
sample_summary(res, "vTechNewCap", probs = c(0.1, 0.5, 0.9),
               by = c("tech", "region"))
} # }