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

## ----start--------------------------------------------------------------------
lg_start(study_id = "PROJECT-001", analysis_id = "primary")

## ----tag-basic----------------------------------------------------------------
patients <- data.frame(
  USUBJID = c("P001", "P002", "P003", "P004", "P005", "P006"),
  age = c(34L, 19L, 52L, 28L, 61L, 44L),
  group = c("A", "B", "A", "B", "A", "B"),
  eligible = c(TRUE, FALSE, TRUE, TRUE, FALSE, TRUE),
  stringsAsFactors = FALSE
)

tagged <- lg_tag(patients,
  dataset_id = "PATIENTS",
  label = "Patient registry"
)

tagged

## ----tag-multiple-------------------------------------------------------------
labs <- data.frame(
  USUBJID = c("P001", "P001", "P003", "P004", "P006"),
  test = c("ALT", "AST", "ALT", "ALT", "ALT"),
  value = c(28.4, 31.2, 45.1, 22.8, 38.6),
  stringsAsFactors = FALSE
)

labs_tagged <- lg_tag(labs, dataset_id = "LABS", label = "Laboratory results")

cat("Patients tagged:", nrow(tagged), "rows\n")
cat("Labs tagged:    ", nrow(labs_tagged), "rows\n")

## ----derive-basic-------------------------------------------------------------
derived <- lg_derive(tagged,
  age_group = ifelse(age >= 40L, ">=40", "<40"),
  adult = age >= 18L,
  description = "age_group: >=40 vs <40 from age; adult: age >= 18"
)

derived[, c("USUBJID", "age", "age_group", "adult")]

## ----lid-check----------------------------------------------------------------
all(derived[["lineage_id"]] == tagged[["lineage_id"]])

## ----derive-chain-------------------------------------------------------------
derived2 <- lg_derive(derived,
  label = paste0(USUBJID, " (", group, ")"),
  description = "Display label combining USUBJID and group"
)

derived2[, c("lineage_id", "USUBJID", "group", "label")]

## ----join-left----------------------------------------------------------------
joined <- lg_join(tagged, labs_tagged,
  by          = "USUBJID",
  type        = "left",
  description = "Merge ALT lab values from LABS onto PATIENTS"
)

joined[, c("lineage_id", "USUBJID", "eligible", "test", "value", "lineage_id_y")]

## ----join-types, eval = FALSE-------------------------------------------------
# lg_join(x, y, by = "USUBJID", type = "left") # all rows of x
# lg_join(x, y, by = "USUBJID", type = "inner") # only matching rows
# lg_join(x, y, by = "USUBJID", type = "full") # all rows of both
# lg_join(x, y, by = "USUBJID", type = "right") # all rows of y

## ----filter-basic-------------------------------------------------------------
eligible_only <- lg_filter(tagged,
  eligible == TRUE,
  reason = "Not eligible for analysis (eligible != TRUE)"
)

cat("Before:", nrow(tagged), "\n")
cat("After: ", nrow(eligible_only), "\n")

## ----filter-enriched----------------------------------------------------------
# reason_code and population enrich the exclusion record
step1 <- lg_filter(tagged,
  eligible == TRUE,
  reason = "Screening criteria not met (eligible != TRUE)",
  reason_code = "SCREEN_FAIL",
  population = "ELIGIBLE_SET"
)

step2 <- lg_filter(step1,
  age >= 18L,
  reason = "Under minimum age threshold (age < 18)",
  reason_code = "UNDERAGE",
  population = "ADULT_SET"
)

cat("Enrolled: ", nrow(tagged), "\n")
cat("Eligible: ", nrow(step1), "\n")
cat("Adult:    ", nrow(step2), "\n")

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

## ----history------------------------------------------------------------------
lg_history(step2)

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

## ----complete-----------------------------------------------------------------
lg_start(study_id = "DEMO")

# Source data
raw <- data.frame(
  id = sprintf("P%03d", 1:8),
  value = c(12.4, NA, 8.1, 15.2, 9.8, NA, 11.3, 7.4),
  group = rep(c("treatment", "control"), 4),
  include = c(TRUE, TRUE, FALSE, TRUE, TRUE, TRUE, FALSE, TRUE),
  stringsAsFactors = FALSE
)

# Tag, derive, filter
ds <- lg_tag(raw, dataset_id = "RAW", label = "Raw analysis dataset")

ds <- lg_derive(ds,
  log_value = log(value),
  value_cat = ifelse(!is.na(value) & value >= 10, "high", "low/missing"),
  description = "Log-transform value; categorise as high (>=10) vs low/missing"
)

ds_clean <- ds |>
  lg_filter(include == TRUE,
    reason = "Excluded by study protocol (include != TRUE)"
  ) |>
  lg_filter(!is.na(value),
    reason = "Missing primary endpoint value"
  )

cat("Rows after cleaning:", nrow(ds_clean), "\n")

# Visualise the pipeline
lin <- lg_lineage()
print(lin)

lg_end()

## ----lineage-demo-------------------------------------------------------------
lg_start()
raw <- lg_tag(
  data.frame(
    USUBJID = sprintf("P%02d", 1:6),
    group = rep(c("A", "B"), 3L),
    flag = c(TRUE, TRUE, FALSE, TRUE, FALSE, TRUE),
    stringsAsFactors = FALSE
  ),
  dataset_id = "RAW"
)
raw <- lg_derive(raw,
  group_n = ifelse(group == "A", 1L, 2L),
  description = "Numeric group code"
)
lg_filter(raw, flag == TRUE, reason = "Flag not set")

lin <- lg_lineage()
print(lin)
lg_end()

## ----lineage-plot, eval = FALSE-----------------------------------------------
# # Render inline (requires DiagrammeR)
# lg_plot(lin)
# 
# # Export DOT file for Graphviz / online renderers
# lg_plot(lin, output = "outputs/pipeline.dot")