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

## ----setup-data---------------------------------------------------------------
lg_start(study_id = "COHORT-001", analysis_id = "main-analysis")

# Simulate a patient registry
set.seed(42)
n <- 20L

raw <- data.frame(
  USUBJID = sprintf("PT-%03d", seq_len(n)),
  age = sample(15:75, n, replace = TRUE),
  sex = sample(c("M", "F"), n, replace = TRUE),
  diagnosis = sample(c("Y", "N", "N"), n, replace = TRUE),
  consent = sample(c("Y", "Y", "Y", "N"), n, replace = TRUE),
  prior_drug = sample(c("Y", "N", "N", "N"), n, replace = TRUE),
  biomarker = round(runif(n, 0.5, 8.5), 2),
  outcome = ifelse(runif(n) > 0.4, round(rnorm(n, 50, 12), 1), NA_real_),
  stringsAsFactors = FALSE
)

registry <- lg_tag(raw,
  dataset_id = "REGISTRY",
  label = "Patient registry — all screened"
)

cat("Screened: ", nrow(registry), "patients\n")

## ----filter-required----------------------------------------------------------
# This would error:
# lg_filter(registry, age >= 18L)
# Error: A `reason` is required.

# Correct:
adults <- lg_filter(registry,
  age >= 18L,
  reason = "Under minimum age threshold (age < 18 years)"
)

## ----filter-reason-code-------------------------------------------------------
consented <- lg_filter(adults,
  consent == "Y",
  reason = "Did not provide written informed consent",
  reason_code = "NO_CONSENT"
)

diagnosed <- lg_filter(consented,
  diagnosis == "Y",
  reason = "Does not meet diagnostic criteria per protocol section 3.1",
  reason_code = "NO_DIAGNOSIS"
)

## ----filter-population--------------------------------------------------------
no_prior <- lg_filter(diagnosed,
  prior_drug == "N",
  reason      = "Received prohibited prior medication within wash-out period",
  reason_code = "PRIOR_MED",
  population  = "ELIGIBLE_SET"
)

biomarker_pos <- lg_filter(no_prior,
  biomarker >= 2.0,
  reason = "Biomarker below threshold (< 2.0) per protocol section 4.3",
  reason_code = "LOW_BIOMARKER",
  population = "BIOMARKER_POS"
)

analysis_set <- lg_filter(biomarker_pos,
  !is.na(outcome),
  reason      = "Missing primary outcome measurement",
  reason_code = "MISSING_OUTCOME",
  population  = "ANALYSIS_SET"
)

cat("Screened:     ", nrow(registry), "\n")
cat("Adults:       ", nrow(adults), "\n")
cat("Consented:    ", nrow(consented), "\n")
cat("Diagnosed:    ", nrow(diagnosed), "\n")
cat("No prior med: ", nrow(no_prior), "\n")
cat("Biomarker+:   ", nrow(biomarker_pos), "\n")
cat("Analysis set: ", nrow(analysis_set), "\n")

## ----exclusions-all-----------------------------------------------------------
excl <- lg_exclusions()
cat("Total exclusions:", nrow(excl), "\n")
names(excl)

## ----exclusions-population----------------------------------------------------
# Only exclusions related to the final analysis set
analysis_excl <- lg_exclusions(population = "ANALYSIS_SET")
analysis_excl[, c("usubjid", "reason", "reason_code")]

## ----exclusions-dataset-------------------------------------------------------
lg_exclusions(dataset_id = "REGISTRY")[
  ,
  c("usubjid", "reason_code", "population")
]

## ----disposition-reason-------------------------------------------------------
lg_disposition(by = "reason")

## ----disposition-population---------------------------------------------------
lg_disposition(by = "population")

## ----disposition-dataset------------------------------------------------------
lg_disposition(by = "dataset")

## ----trace-excluded-----------------------------------------------------------
# Find a subject who was excluded
excluded_id <- lg_exclusions()$usubjid[[1L]]
cat("Tracing excluded subject:", excluded_id, "\n")

lg_trace(excluded_id)

## ----trace-included-----------------------------------------------------------
included_id <- analysis_set$USUBJID[[1L]]
cat("Tracing included subject:", included_id, "\n")

lg_trace(included_id)

## ----trace-notfound-----------------------------------------------------------
result <- lg_trace("PT-999", verbose = FALSE)
cat("Datasets found in:", length(result$datasets), "\n")

## ----trace-programmatic-------------------------------------------------------
result <- lg_trace(excluded_id, verbose = FALSE)

cat("Subject:       ", result$usubjid, "\n")
cat("Found in:      ", paste(result$datasets, collapse = ", "), "\n")
cat("Operations:    ", nrow(result$operations), "\n")
cat("Exclusions:    ", nrow(result$exclusions), "\n")

if (nrow(result$exclusions) > 0L) {
  cat("Excluded by:   ", result$exclusions$reason[[1L]], "\n")
  cat("Population:    ", result$exclusions$population[[1L]], "\n")
}

## ----operations---------------------------------------------------------------
ops <- lg_operations()
ops[, c(
  "op_id", "op_type", "dataset_id", "description",
  "rows_in", "rows_out"
)]

## ----operation-check----------------------------------------------------------
# Verify: total excluded == sum of (rows_in - rows_out) across FILTER ops
filter_ops <- ops[ops$op_type == "FILTER", ]
total_via_ops <- sum(filter_ops$rows_in - filter_ops$rows_out)
total_via_excl <- nrow(lg_exclusions())
cat("Excluded via ops:  ", total_via_ops, "\n")
cat("Excluded via excl: ", total_via_excl, "\n")
cat("Match:             ", total_via_ops == total_via_excl, "\n")

## ----lineage------------------------------------------------------------------
lin <- lg_lineage()
print(lin)

## ----lineage-plot, eval = FALSE-----------------------------------------------
# lg_plot(lin)

## ----cascade------------------------------------------------------------------
lg_start()

cohort <- lg_tag(
  data.frame(
    id = sprintf("S%02d", 1:10),
    enrolled = c(rep(TRUE, 8), FALSE, FALSE),
    treated = c(rep(TRUE, 6), FALSE, FALSE, FALSE, FALSE),
    complete = c(rep(TRUE, 4), FALSE, FALSE, rep(FALSE, 4)),
    stringsAsFactors = FALSE
  ),
  dataset_id = "COHORT"
)

step1 <- lg_filter(cohort, enrolled == TRUE,
  reason = "Not enrolled in study"
)
step2 <- lg_filter(step1, treated == TRUE,
  reason = "Did not receive study treatment"
)
step3 <- lg_filter(step2, complete == TRUE,
  reason = "Did not complete the study"
)

cat("Enrolled:  ", nrow(step1), "\n")
cat("Treated:   ", nrow(step2), "\n")
cat("Completed: ", nrow(step3), "\n")

lg_disposition(by = "reason")

## ----cascade-end--------------------------------------------------------------
lg_end()