## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment  = "#>",
  fig.width  = 7,
  fig.height = 4
)

## ----derive, message = FALSE--------------------------------------------------
library(PTSDdiag)
library(dplyr)

data("simulated_ptsd")
vet <- rename_ptsd_columns(simulated_ptsd[1:120, ],
                           id_col = c("patient_id", "age", "sex"))

comp_vet <- compare_optimizations(
  vet,
  n_top         = 10,
  score_by      = "balanced_accuracy",
  show_progress = FALSE
)

## ----figure, fig.alt = "Heatmap of PCL-5 symptom selection frequency in the veteran sample"----
plot_symptom_frequency(comp_vet, type = "relative")

## ----definitions--------------------------------------------------------------
definitions <- extract_definitions(comp_vet, n = 5)

# The shared object: only symptom numbers and the rule to apply them
lapply(definitions, function(d) d$symptoms)

## ----share-json---------------------------------------------------------------
json_file <- tempfile(fileext = ".json")
write_combinations(
  definitions[["4/6 Hierarchical"]]$symptoms, json_file,
  n_required  = 4,
  clusters    = list(B = 1:5, C = 6:7, D = 8:14, E = 15:20),
  label       = "4/6 Hierarchical",
  description = "Top 5 hierarchical combinations, veteran derivation sample"
)

## ----json-roundtrip-----------------------------------------------------------
received <- as_definitions(read_combinations(json_file))

all.equal(received[["4/6 Hierarchical"]]$symptoms,
          definitions[["4/6 Hierarchical"]]$symptoms)

## ----perf-derivation----------------------------------------------------------
evaluate_definitions(vet, definitions, include_icd11 = TRUE)

## ----perf-validation----------------------------------------------------------
data("simulated_ptsd_genpop")

# simulated_ptsd_genpop also carries paired CAPS-5 columns (C1..C20); here we
# use only the PCL-5 items, so we select those before standardising.
genpop <- rename_ptsd_columns(
  simulated_ptsd_genpop[, c("patient_id", "age", "sex", paste0("S", 1:20))],
  id_col = c("patient_id", "age", "sex")
)

evaluate_definitions(genpop, definitions, include_icd11 = TRUE)

## ----tidy-table---------------------------------------------------------------
tidy_gp <- evaluate_definitions(genpop, definitions, tidy = TRUE)
head(tidy_gp)