df <- rmst.sim(
  n              = 200,
  model          = "aft_lognormal",
  baseline       = list(mu = 2.5, sigma = 0.6),
  treat_effect   = -0.25,
  covariates     = list(
    covar_continuous("age",  mean = 62, sd = 10),
    covar_binary("sex",      p = 0.45),
    covar_continuous("x",    dist = "lognormal", meanlog = 0, sdlog = 0.5)
  ),
  target_censoring = 0.25,
  L    = 36,
  seed = 42
)

print(df)
── Simulated RMST Dataset ────────────────────────────────────
  Model          : AFT Log-Normal 
  N (total)      : 200  |  Arm 0: 108  |  Arm 1: 92
  Events         : 150 (75.0%)
  Censored       : 50 (25.0%)
  Truncation time: 36  (stored as attribute)

First 6 rows:
       time status arm      age sex         x
1  7.731940      1   1 55.73546   1 1.5633592
2 23.370037      1   1 63.83643   0 0.5923551
3 16.726338      1   0 53.64371   1 2.6796031
4  5.139254      0   1 77.95281   1 0.8254587
5 11.223345      1   0 65.29508   1 2.2866152
6  6.159279      1   0 53.79532   1 2.1299667

rmst.power(Surv(time, status) ~ age + sex + x,
           data = df, arm = "arm",
           sample_sizes = c(100, 200, 300), L = 36)

covs <- list(
  list(name="age",   type="continuous",  dist="normal",     params=list(mean=62, sd=10),
       transform=c("center(60)","scale(10)")),
  list(name="sex",   type="categorical", dist="bernoulli",  params=list(p=0.45)),
  list(name="stage", type="categorical", dist="ordinal",
       params=list(prob=c(0.3,0.5,0.2), labels=c("I","II","III"))),
  list(name="x",     type="continuous",  dist="lognormal",  params=list(meanlog=0, sdlog=0.6))
)

tr_rand <- list(assignment="randomization", allocation="1:1")

tr_strat <- list(assignment="stratified", allocation="2:1", stratify_by=c("stage"))

tr_ps <- list(
  assignment = "logistic_ps",
  ps_model  = list(
    formula = "~ 1 + x + sex",
    beta    = c(-0.3, 1.2, -0.6)  # (Intercept), x, sex
  )
)

effects = list(
  intercept  = 0,                      # default is 0
  treatment  = -0.25,
  covariates = list(age = 0.01, sex = -0.2)
  # or: formula="~ age + sex", beta=c(0.01, -0.2)
)

# Covariates (sex will be numeric 0/1 here)
covs <- list(
  list(name="age", type="continuous",  dist="normal",    params=list(mean=62, sd=10)),
  list(name="sex", type="categorical", dist="bernoulli", params=list(p=0.45))
)

# Censoring: single covariate-dependent mechanism using a positive base rate
cz_dep <- list(
  mode = "explicit",
  dependent = list(
    formula = "~ 0 + age + sex",  # NO intercept; sex is numeric 0/1
    base    = 0.03,               # baseline censoring rate (>0)
    beta    = c(0.012, 0.35)      # (age, sex) on log-rate scale
  ),
  administrative = list(time = 48)
)

# Quick sanity check (optional)
mm   <- model.matrix(~ 0 + age + sex, data.frame(age=c(50,70), sex=c(0,1)))
rate <- cz_dep$dependent$base * exp(mm %*% matrix(cz_dep$dependent$beta, ncol=1))
stopifnot(all(rate > 0 & is.finite(rate)))

# Recipe
rec <- list(
  n = 300,
  covariates = list(defs = covs),
  treatment  = list(assignment="randomization", allocation="1:1"),
  event_time = list(
    model    = "ph_pwexp",
    baseline = list(rates = c(0.05), cuts = numeric(0)), # exponential baseline
    effects  = list(intercept=0, treatment=-0.3, covariates=list(age=0.01, sex=-0.2))
  ),
  censoring  = cz_dep,
  seed = 2025
)

# Simulate
dat <- simulate_from_recipe(validate_recipe(rec))

# Output
knitr::kable(
  data.frame(achieved_censoring = attr(dat, "achieved_censoring")),
  caption = "Achieved censoring rate"
)

knitr::kable(utils::head(dat, 8), caption = "First 8 rows of simulated data")

# Covariates (sex numeric 0/1)
covs_f <- list(
  list(name="age", type="continuous",  dist="normal",    params=list(mean=62, sd=10)),
  list(name="sex", type="categorical", dist="bernoulli", params=list(p=0.45))
)

trt_f <- list(assignment="randomization", allocation="1:1")

# Event-time engine: AFT lognormal with formula-based covariate effects
evt_f <- list(
  model    = "aft_lognormal",
  baseline = list(mu = 3.1, sigma = 0.55),
  effects  = list(
    treatment  = -0.25,                 # effect of treatment (log-time scale)
    formula    = "~ 0 + age + sex",     # covariate effects via formula (no intercept)
    beta       = c(0.010, -0.20)        # (age, sex) -- match order in formula
  )
)

# Censoring: covariate-dependent via log-rate model (single mechanism)
cz_f <- list(
  mode = "explicit",
  dependent = list(
    formula = "~ 0 + age + sex",  # NO intercept; sex numeric 0/1
    base    = 0.03,               # positive rate
    beta    = c(0.012, 0.35)      # (age, sex) on log-rate scale
  ),
  administrative = list(time = 48)  # optional admin cutoff
)

# Full recipe
rec_f <- list(
  n = 350,
  covariates = list(defs = covs_f),
  treatment  = trt_f,
  event_time = evt_f,
  censoring  = cz_f,
  seed = 777
)

# Simulate
dat_f <- simulate_from_recipe(validate_recipe(rec_f))

# Display
knitr::kable(
  data.frame(achieved_censoring = attr(dat_f, "achieved_censoring")),
  caption = "Achieved censoring rate (formula-based example)"
)

knitr::kable(utils::head(dat_f, 8), caption = "First 8 rows — formula-based example")

# Build a base recipe here (self-contained)
base <- validate_recipe(list(
  n = 200,
  covariates = list(defs = list(
    list(name="age", type="continuous",  dist="normal", params=list(mean=62, sd=10)),
    list(name="sex", type="categorical", dist="bernoulli", params=list(p=0.45)),
    list(name="x",   type="continuous",  dist="lognormal", params=list(meanlog=0, sdlog=0.6))
  )),
  treatment  = list(assignment="randomization", allocation="1:1"),
  event_time = list(
    model    = "aft_weibull",
    baseline = list(shape=1.3, scale=12),
    effects  = list(intercept=0, treatment=-0.20, covariates=list(age=0.008, x=0.04))
  ),
  censoring  = list(mode="target_overall", target=0.25, admin_time=36),
  seed = 3026
))

out_dir <- file.path(tempdir(), "rmstss-manifest-demo")
unlink(out_dir, recursive = TRUE, force = TRUE)

man <- generate_recipe_sets(
  base_recipe = base,
  vary = list(n = c(200, 400),
              "event_time.effects.treatment" = c(-0.15, -0.25)),
  out_dir  = out_dir,
  formats  = c("rds","csv"),
  n_reps   = 1,
  seed_base = 2025
)

# Inspect the first row's compact metadata (fields only; no file paths)
m <- readRDS(file.path(out_dir, "manifest.rds"))
names(m)
 [1] "scenario_id"                     "rep"                            
 [3] "seed"                            "achieved_censoring"             
 [5] "n"                               "file_txt"                       
 [7] "file_csv"                        "file_rds"                       
 [9] "file_rdata"                      "p__n"                           
[11] "p__event_time.effects.treatment" "meta"                           
if ("meta" %in% names(m) && length(m$meta[[1]]) > 0) {
  list(model = m$meta[[1]]$model,
       baseline = m$meta[[1]]$baseline,
       effects = m$meta[[1]]$effects,
       achieved_censoring = m$meta[[1]]$achieved_censoring,
       n = m$meta[[1]]$n)
} else {
  "Manifest is minimal (older run); use rebuild_manifest() to enrich."
}
$model
[1] "aft_weibull"

$baseline
$baseline$shape
[1] 1.3

$baseline$scale
[1] 12


$effects
$effects$intercept
[1] 0

$effects$treatment
[1] -0.15

$effects$covariates
$effects$covariates$age
[1] 0.008

$effects$covariates$x
[1] 0.04



$achieved_censoring
[1] 0.275

$n
[1] 200

# Load datasets back
sets <- load_recipe_sets(file.path(out_dir, "manifest.rds"))
attr(sets[[1]]$data, "achieved_censoring")
[1] 0.275
str(sets[[1]]$meta)
List of 19
 $ dataset_id        : chr "sc001_r01"
 $ scenario_id       : int 1
 $ rep               : int 1
 $ seed_used         : int 3026
 $ n                 : int 200
 $ n_treat           : int 98
 $ n_control         : int 102
 $ event_rate        : num 0.725
 $ achieved_censoring: num 0.275
 $ model             : chr "aft_weibull"
 $ baseline          :List of 2
  ..$ shape: num 1.3
  ..$ scale: num 12
 $ effects           :List of 3
  ..$ intercept : num 0
  ..$ treatment : num -0.15
  ..$ covariates:List of 2
  .. ..$ age: num 0.008
  .. ..$ x  : num 0.04
 $ treatment         :List of 2
  ..$ assignment: chr "randomization"
  ..$ allocation: chr "1:1"
 $ censoring         :List of 3
  ..$ mode      : chr "target_overall"
  ..$ target    : num 0.25
  ..$ admin_time: num 36
 $ covariates        :List of 3
  ..$ :List of 4
  .. ..$ name  : chr "age"
  .. ..$ type  : chr "continuous"
  .. ..$ dist  : chr "normal"
  .. ..$ params:List of 2
  .. .. ..$ mean: num 62
  .. .. ..$ sd  : num 10
  ..$ :List of 4
  .. ..$ name  : chr "sex"
  .. ..$ type  : chr "categorical"
  .. ..$ dist  : chr "bernoulli"
  .. ..$ params:List of 1
  .. .. ..$ p: num 0.45
  ..$ :List of 4
  .. ..$ name  : chr "x"
  .. ..$ type  : chr "continuous"
  .. ..$ dist  : chr "lognormal"
  .. ..$ params:List of 2
  .. .. ..$ meanlog: num 0
  .. .. ..$ sdlog  : num 0.6
 $ allocation        : chr "1:1"
 $ params            :List of 2
  ..$ n                           : num 200
  ..$ event_time.effects.treatment: num -0.15
 $ files             :List of 4
  ..$ txt  : chr NA
  ..$ csv  : chr "C:\\Users\\arnab\\AppData\\Local\\Temp\\RtmpkrcmkA/rmstss-manifest-demo/sc1_r1.csv"
  ..$ rds  : chr "C:\\Users\\arnab\\AppData\\Local\\Temp\\RtmpkrcmkA/rmstss-manifest-demo/sc1_r1.rds"
  ..$ rdata: chr NA
 $ created_at        : chr "2026-04-26 15:51:24.433331"