## ----setup, include=FALSE-----------------------------------------------------
knitr::opts_chunk$set(collapse = TRUE, comment = "#>", warning = FALSE, message = FALSE)
library(mudnester)

## ----cases-example------------------------------------------------------------
set.seed(1)
cases_raw <- data.frame(
  identity          = paste0("PT", 1:20),
  first_name        = sample(c("James","Sarah","Michael"), 20, TRUE),
  surname           = sample(c("Smith","Jones","Williams"), 20, TRUE),
  date_of_birth     = as.Date("1970-01-01") + sample(-5000:5000, 20),
  date_of_onset     = as.Date("2024-03-01") + sample(0:120, 20),
  disease_name      = sample(c("COVID-19","Influenza A","RSV"), 20, TRUE),
  gender            = sample(c("M","F"), 20, TRUE),
  postcode          = sample(c("4556","4557","4560"), 20, TRUE),
  medicare_no       = paste0(sample(2000:9999, 20), sample(10000:99999, 20)),
  indigenous_status = sample(c("Non-Indigenous","Aboriginal","Unknown"), 20, TRUE,
                              prob = c(0.85, 0.10, 0.05)),
  stringsAsFactors  = FALSE
)

df_cases <- clean_the_nest(
  cases_raw,
  data_type   = "cases",
  drop_eggs   = TRUE,
  id_var      = "identity",
  diagnosis   = "disease_name",
  lettername1 = "first_name",
  lettername2 = "surname",
  dob         = "date_of_birth",
  medicare    = "medicare_no",
  gender      = "gender",
  postcode    = "postcode",
  fn          = "indigenous_status",
  onset_date  = "date_of_onset"
)

head(df_cases[, c("lettername1","lettername2","dob","age","diagnosis","block1")], 4)

## ----hospital-example---------------------------------------------------------
set.seed(2)
hosp_raw <- data.frame(
  patient_id         = paste0("UR", 1:15),
  firstname          = sample(c("James","Sarah","Michael"), 15, TRUE),
  last_name          = sample(c("Smith","Jones"), 15, TRUE),
  birth_date         = as.Date("1945-01-01") + sample(0:10000, 15),
  date_of_admission  = as.Date("2024-06-01") + sample(0:180, 15),
  date_of_discharge  = as.Date("2024-06-15") + sample(0:180, 15),
  medicare_number    = paste0(sample(2000:9999, 15), sample(10000:99999, 15)),
  sex                = sample(c("M","F"), 15, TRUE),
  zip_codes          = sample(c("4556","4557"), 15, TRUE),
  icd_codes          = sample(c("J06.9","U07.1","J44.1"), 15, TRUE),
  stringsAsFactors   = FALSE
)

df_hosp <- clean_the_nest(
  hosp_raw,
  data_type      = "hospital",
  drop_eggs      = TRUE,
  id_var         = "patient_id",
  lettername1    = "firstname",
  lettername2    = "last_name",
  dob            = "birth_date",
  medicare       = "medicare_number",
  gender         = "sex",
  postcode       = "zip_codes",
  icd_code       = "icd_codes",
  admission_date = "date_of_admission",
  discharge_date = "date_of_discharge"
)

df_hosp[, c("los","admission_outcome","icd_code")] |> head(4)

## ----vax-example--------------------------------------------------------------
set.seed(3)
vax_raw <- data.frame(
  patient_id       = rep(paste0("VAX", 1:10), each = 2),
  firstname        = rep(c("Alice","Bob","Carol","Dan","Eve",
                            "Frank","Grace","Henry","Iris","Jack"), each = 2),
  last_name        = rep(c("Smith","Jones","Williams","Taylor","Brown",
                            "White","Black","Green","Blue","Red"), each = 2),
  birth_date       = rep(as.Date("1980-01-01") + sample(-2000:2000, 10), each = 2),
  gender           = rep(sample(c("M","F"), 10, TRUE), each = 2),
  postcode         = rep(sample(c("4556","4557"), 10, TRUE), each = 2),
  medicare_number  = rep(paste0(sample(2000:9999, 10), sample(10000:99999, 10)), each = 2),
  vaccine_delivered = rep(c("COVID-19 XBB.1.5","COVID-19 XBB.1.5"), 10),
  service_date     = c(rbind(
    as.Date("2024-01-15") + sample(0:30, 10),
    as.Date("2024-05-01") + sample(0:30, 10)
  )),
  stringsAsFactors = FALSE
)

df_vax <- clean_the_nest(
  vax_raw,
  data_type     = "vaccination",
  lie_nest_flat = TRUE,
  id_var        = "patient_id",
  lettername1   = "firstname",
  lettername2   = "last_name",
  dob           = "birth_date",
  medicare      = "medicare_number",
  gender        = "gender",
  postcode      = "postcode",
  vax_type      = "vaccine_delivered",
  vax_date      = "service_date"
)

df_vax[, c("id_var","vax_date_1","vax_type_1","vax_date_2","vax_type_2")] |> head(4)

## ----cohort-example, eval=FALSE-----------------------------------------------
# df_cohort <- clean_the_nest(
#   birth_cohort_data,
#   data_type         = "cases",
#   id_var            = "baby_id",
#   lettername1       = "first_name",
#   lettername2       = "last_name",
#   dob               = "babys_date_of_birth",
#   cohort_entry_date = "babys_date_of_birth",   # same column — aliased internally
#   cohort_exit_date  = "end_of_followup_date",
#   gender            = "sex"
# )

## ----medicare-----------------------------------------------------------------
mc_data <- data.frame(
  patient_id = c("PT001", "PT002", "PT003"),
  # PT001: valid 10-digit number (no IRN appended)
  # PT002: valid 11-digit number (IRN = 1)
  # PT003: invalid checksum (digit 9 is 7, should be 3)
  mcare = c("2428778132", "24287781321", "2428778172"),
  stringsAsFactors = FALSE
)

# suppressWarnings() here because PT003 has an invalid checksum —
# that's exactly what we want to demonstrate.
df_mc <- suppressWarnings(suppressMessages(
  clean_the_nest(mc_data, data_type = "cases",
                 id_var = "patient_id", medicare = "mcare")
))

df_mc[, c("id_var", "medicare08", "medicare09", "medicare10",
           "medicare_irn", "medicare_valid")]

## ----drop-eggs----------------------------------------------------------------
# Without drop_eggs — all original columns plus derived ones
df_full <- clean_the_nest(
  cases_raw, data_type = "cases",
  id_var = "identity", lettername1 = "first_name", lettername2 = "surname",
  dob = "date_of_birth", onset_date = "date_of_onset"
)
ncol(df_full)

# With drop_eggs — only the linkage and analysis essentials
df_lean <- clean_the_nest(
  cases_raw, data_type = "cases", drop_eggs = TRUE,
  id_var = "identity", lettername1 = "first_name", lettername2 = "surname",
  dob = "date_of_birth", onset_date = "date_of_onset",
  keep_vars = "disease_name"   # retain this one extra
)
ncol(df_lean)
names(df_lean)