inst/examples/swissmetro/plot_b17a_lognormal_mixture.R

In rbiogeme: Interface to 'Biogeme'

#!/usr/bin/env Rscript

# b17a. Mixture with a lognormal random coefficient
#
# This example mirrors plot_b17a_lognormal_mixture.py. The time coefficient is
# negative lognormally distributed: -exp(b_time + b_time_s * NORMAL draw).
# Native Biogeme performs the logit kernel evaluation, Monte Carlo integration,
# derivatives, optimization, and reporting.

library(rbiogeme)

# prepare_swissmetro_example() is defined in example_utils.R. It parses the
# command line, validates the data/Python paths, configures the bridge, reads
# the data, and creates a fresh output directory. The --data, --python,
# --output, --draws, and --seed options work from any current working directory.
script_path <- commandArgs(trailingOnly = FALSE)
script_path <- sub("^--file=", "", script_path[startsWith(script_path, "--file=")][[1L]])
source(file.path(dirname(normalizePath(script_path)), "example_utils.R"))

build_b17a_lognormal_mixture_model <- function(
    database,
    number_of_draws = 10000L,
    seed = 1223L
) {
  # Parameter names, starts, bounds, and the fixed Swissmetro ASC match the
  # native Python example exactly.
  asc_car <- biogeme_beta("asc_car", start = 0)
  asc_train <- biogeme_beta("asc_train", start = 0)
  asc_sm <- biogeme_beta("asc_sm", start = 0, fixed = TRUE)
  b_cost <- biogeme_beta("b_cost", start = 0)
  b_time <- biogeme_beta("b_time", start = 0)
  b_time_s <- biogeme_beta("b_time_s", start = 1, lower = -2, upper = 2)

  # exp() creates a native exponential node. The leading minus sign preserves
  # the negative lognormal time coefficient used by native b17a.
  b_time_rnd <- -exp(b_time + b_time_s * draw("b_time_rnd", "NORMAL"))

  utilities <- list(
    `1` = asc_train + b_time_rnd * variable("TRAIN_TT_SCALED") +
      b_cost * variable("TRAIN_COST_SCALED"),
    `2` = asc_sm + b_time_rnd * variable("SM_TT_SCALED") +
      b_cost * variable("SM_COST_SCALED"),
    `3` = asc_car + b_time_rnd * variable("CAR_TT_SCALED") +
      b_cost * variable("CAR_CO_SCALED")
  )
  availability <- list(
    `1` = variable("TRAIN_AV_SP"),
    `2` = variable("SM_AV"),
    `3` = variable("CAR_AV_SP")
  )
  conditional_probability <- logit_probability(
    utilities = utilities,
    availability = availability,
    alternative = variable("CHOICE")
  )
  log_probability <- log(monte_carlo(conditional_probability))
  draws <- biogeme_draws(
    name = "b_time_rnd",
    draw_type = "NORMAL",
    number_of_draws = number_of_draws,
    seed = seed
  )

  biogeme_model(
    database = database,
    formula = log_probability,
    draws = draws,
    control = biogeme_control(
    output_directory = prepared$output,
      model_name = "b17a_lognormal_mixture",
      number_of_draws = number_of_draws,
      seed = seed,
      analytical_hessian_mode = "automatic",
      generate_html = TRUE,
      generate_yaml = FALSE,
      save_iterations = FALSE
    )
  )
}

prepared <- prepare_swissmetro_example(
  commandArgs(trailingOnly = TRUE),
  default_model = "b17a_lognormal_mixture"
)

number_of_draws <- if (!is.null(prepared$options$draws) && nzchar(prepared$options$draws)) {
  example_integer(prepared$options$draws, "draws")
} else {
  10000L
}
seed <- if (!is.null(prepared$options$seed) && nzchar(prepared$options$seed)) {
  example_integer(prepared$options$seed, "seed")
} else {
  1223L
}

# Always estimate afresh. Remove only exact b17a artifacts so an old YAML or
# iteration file cannot silently supply the estimates.
stale_files <- c(
  "b17a_lognormal_mixture.yaml",
  "__b17a_lognormal_mixture.iter",
  "b17a_lognormal_mixture.html"
)
stale_files <- file.path(prepared$output, stale_files)
stale_files <- stale_files[file.exists(stale_files)]
if (length(stale_files) > 0L) unlink(stale_files, force = TRUE)

database <- swissmetro_data(prepared$data)
model <- build_b17a_lognormal_mixture_model(
  database,
  number_of_draws = number_of_draws,
  seed = seed
)

cat(sprintf("Number of draws: %s\n", format(number_of_draws, big.mark = "_")))

# The complete lognormal expression graph is compiled once. Native Biogeme
# performs the Monte Carlo integration and estimation.
fit <- estimate(
  model,
  model_name = "b17a_lognormal_mixture",
  control = model$control
)
print(summary(fit))
print(coef(fit))

invisible(fit)