inst/examples/swissmetro/plot_b10_nested_bottom.R

In rbiogeme: Interface to 'Biogeme'

#!/usr/bin/env Rscript

# b10. Nested logit with bottom normalization
#
# This example mirrors plot_b10_nested_bottom.py. The nest parameter is fixed
# to one, while the overall scale parameter is estimated in (0, 1].

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, and
# --output 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_b10_nested_bottom_model <- function(database) {
  # These 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_time <- biogeme_beta("b_time", start = 0)
  b_cost <- biogeme_beta("b_cost", start = 0)
  scale_parameter <- biogeme_beta(
    "scale_parameter",
    start = 0.5,
    lower = 0.000001,
    upper = 1
  )

  utilities <- list(
    `1` = asc_train + b_time * variable("TRAIN_TT_SCALED") +
      b_cost * variable("TRAIN_COST_SCALED"),
    `2` = asc_sm + b_time * variable("SM_TT_SCALED") +
      b_cost * variable("SM_COST_SCALED"),
    `3` = asc_car + b_time * 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")
  )

  # Bottom normalization fixes the non-trivial nest parameter at one. The
  # native lognested_mev_mu expression instead estimates scale_parameter.
  nests <- nested_nests(
    choice_set = c(1L, 2L, 3L),
    nests = list(nested_nest(1, c(1L, 3L), name = "existing"))
  )

  nested_logit_model(
    database = database,
    choice = "CHOICE",
    utilities = utilities,
    availability = availability,
    nests = nests,
    scale_parameter = scale_parameter,
    control = biogeme_control(
    output_directory = prepared$output,
      model_name = "b10_nested_bottom",
      generate_html = TRUE,
      generate_yaml = FALSE,
      save_iterations = FALSE
    )
  )
}

prepared <- prepare_swissmetro_example(
  commandArgs(trailingOnly = TRUE),
  default_model = "b10_nested_bottom"
)

# Always estimate from the expression tree. Remove only exact b10 artifacts so
# an old YAML or iteration file cannot silently be recycled.
stale_files <- c(
  "b10_nested_bottom.yaml",
  "__b10_nested_bottom.iter",
  "b10_nested_bottom.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_b10_nested_bottom_model(database)

# estimate() delegates the bottom-normalized native likelihood, derivatives,
# bounded optimization, and reporting to Biogeme.
fit <- estimate(
  model,
  model_name = "b10_nested_bottom",
  control = model$control
)

print(summary(fit))
print(coef(fit))
invisible(fit)