## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(collapse = TRUE, comment = "#>", fig.width = 6,
                      fig.height = 4)
library(simOutrank)

## ----base---------------------------------------------------------------------
traces <- as_traces(illustrative_log, "case_id", "activity", "timestamp")
criteria <- list(
  crit_activity_profile(weight = 0.2, indifference = 0.7, similarity = 0.8,
                        veto = 0.4),
  crit_edit_distance(weight = 0.2, similarity = 2, indifference = 3, veto = 6),
  crit_nominal("status", weight = 0.3),
  crit_nominal("satisfaction", weight = 0.3)
)
sim <- outrank_similarity(traces, criteria)
run1 <- cluster_traces(sim, k = 4, seed = 42)$memberships

## ----run1-mix-----------------------------------------------------------------
tier <- illustrative_log$status[match(names(run1), illustrative_log$case_id)]
table(cluster = run1, tier = tier)

## ----run2---------------------------------------------------------------------
sim$S["1", "11"]                     # a GOLD-NORMAL pair, before
sim2 <- cannot_link(sim, "status")
sim2$S["1", "11"]                    # severed to 0
run2 <- cluster_traces(sim2, k = 4, seed = 42)$memberships
table(cluster = run2,
      tier = illustrative_log$status[match(names(run2), illustrative_log$case_id)])

## ----mustlink-----------------------------------------------------------------
sim_ml <- must_link(sim, cbind("24", "25"), reward = 2)   # the two outliers
sim_ml$S["24", "25"]

## ----trim---------------------------------------------------------------------
trimmed <- trim_outliers(sim, prop = 0.04)   # remove floor(0.04 * 25) = 1 case
attr(trimmed, "trimmed")

## ----trim-lp------------------------------------------------------------------
identical(attr(trim_outliers(sim, prop = 0.04, method = "lp"), "trimmed"),
          attr(trim_outliers(sim, prop = 0.04, method = "greedy"), "trimmed"))

## ----trim-cluster-------------------------------------------------------------
run3 <- cluster_traces(trimmed, k = 4, seed = 42)$memberships
split(names(run3), run3)

## ----compose------------------------------------------------------------------
final <- cluster_traces(cannot_link(trimmed, "status"), k = 4, seed = 42)
if (requireNamespace("clValid", quietly = TRUE)) validate_clusters(final)