tests/testthat/test-swissmetro-b14.R

In rbiogeme: Interface to 'Biogeme'

native_swissmetro_b14 <- function(data) {
  expressions <- reticulate::import("biogeme.expressions", convert = FALSE)
  database_module <- reticulate::import("biogeme.database", convert = FALSE)
  biogeme_module <- reticulate::import("biogeme.biogeme", convert = FALSE)
  models <- reticulate::import("biogeme.models", convert = FALSE)
  nests_module <- reticulate::import("biogeme.nests", convert = FALSE)
  bridge <- rbiogeme:::biogeme_bridge()

  database <- database_module$Database(
    "swissmetro_native_b14",
    reticulate::r_to_py(data)
  )
  variable <- expressions$Variable
  purpose <- variable("PURPOSE")
  choice <- variable("CHOICE")
  database$remove(((purpose != 1) * (purpose != 3) + (choice == 0)) > 0)

  ga <- variable("GA")
  sp <- variable("SP")
  sm_cost <- database$define_variable("SM_COST", variable("SM_CO") * (ga == 0))
  train_cost <- database$define_variable("TRAIN_COST", variable("TRAIN_CO") * (ga == 0))
  car_av_sp <- database$define_variable("CAR_AV_SP", variable("CAR_AV") * (sp != 0))
  train_av_sp <- database$define_variable("TRAIN_AV_SP", variable("TRAIN_AV") * (sp != 0))
  train_tt_scaled <- database$define_variable("TRAIN_TT_SCALED", variable("TRAIN_TT") / 100)
  train_cost_scaled <- database$define_variable("TRAIN_COST_SCALED", train_cost / 100)
  sm_tt_scaled <- database$define_variable("SM_TT_SCALED", variable("SM_TT") / 100)
  sm_cost_scaled <- database$define_variable("SM_COST_SCALED", sm_cost / 100)
  car_tt_scaled <- database$define_variable("CAR_TT_SCALED", variable("CAR_TT") / 100)
  car_co_scaled <- database$define_variable("CAR_CO_SCALED", variable("CAR_CO") / 100)

  beta <- expressions$Beta
  asc_car <- beta("asc_car", 0, NULL, NULL, 0)
  asc_train <- beta("asc_train", 0, NULL, NULL, 0)
  asc_sm <- beta("asc_sm", 0, NULL, NULL, 1)
  b_time <- beta("b_time", 0, NULL, NULL, 0)
  b_cost <- beta("b_cost", 0, NULL, NULL, 0)
  nest_parameter <- beta("nest_parameter", 1, 1, 10, 0)
  utilities <- reticulate::dict(
    `1` = asc_train + b_time * train_tt_scaled + b_cost * train_cost_scaled,
    `2` = asc_sm + b_time * sm_tt_scaled + b_cost * sm_cost_scaled,
    `3` = asc_car + b_time * car_tt_scaled + b_cost * car_co_scaled
  )
  availability <- reticulate::dict(
    `1` = train_av_sp,
    `2` = variable("SM_AV"),
    `3` = car_av_sp
  )
  existing <- nests_module$OneNestForNestedLogit(
    nest_param = nest_parameter,
    list_of_alternatives = reticulate::r_to_py(as.integer(c(1L, 3L))),
    name = "existing"
  )
  nests <- nests_module$NestsForNestedLogit(
    choice_set = reticulate::r_to_py(as.integer(c(1L, 2L, 3L))),
    tuple_of_nests = reticulate::tuple(existing)
  )
  log_gi <- models$get_mev_for_nested(utilities, availability, nests)
  correction <- reticulate::dict(
    `1` = log(4.42e-2),
    `2` = log(3.36e-3),
    `3` = log(7.5e-3)
  )
  log_probability <- models$logmev_endogenous_sampling(
    utilities,
    log_gi,
    availability,
    correction,
    choice
  )
  biogeme <- biogeme_module$BIOGEME(
    database,
    log_probability,
    generate_html = FALSE,
    generate_yaml = FALSE,
    save_iterations = FALSE
  )
  biogeme$model_name <- "b14_nested_endogenous_sampling"
  results <- biogeme$estimate()
  list(
    results = reticulate::py_to_r(bridge$extract_estimation_results(results)),
    number_of_rows = nrow(reticulate::py_to_r(database$dataframe))
  )
}

test_that("b14 endogenous-sampling nested logit matches native Biogeme", {
  skip_if_not(
    identical(Sys.getenv("RBIOGEME_RUN_INTEGRATION"), "1"),
    "Set RBIOGEME_RUN_INTEGRATION=1 to run full Swissmetro equivalence tests"
  )
  skip_if_not(
    rbiogeme_test_configure_python(),
    "Set RBIOGEME_PYTHON to a compatible native Biogeme interpreter"
  )
  data_path <- rbiogeme_test_swissmetro_path()
  skip_if(!nzchar(data_path), "Set RBIOGEME_SWISSMETRO_DATA to the Swissmetro .dat file")

  data <- read.delim(data_path, check.names = FALSE, stringsAsFactors = FALSE)
  database <- swissmetro_data(data)
  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)
  nest_parameter <- biogeme_beta("nest_parameter", start = 1, lower = 1, upper = 10)
  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")
  )
  nests <- nested_nests(
    choice_set = c(1L, 2L, 3L),
    nests = list(nested_nest(nest_parameter, c(1L, 3L), name = "existing"))
  )
  log_probability <- nested_endogenous_sampling_log_probability(
    utilities = utilities,
    availability = availability,
    nests = nests,
    correction = list(`1` = log(4.42e-2), `2` = log(3.36e-3), `3` = log(7.5e-3)),
    alternative = variable("CHOICE")
  )
  model <- biogeme_model(
    database = database,
    formula = log_probability,
    control = biogeme_control(
      model_name = "b14_nested_endogenous_sampling",
      generate_html = FALSE,
      generate_yaml = FALSE,
      save_iterations = FALSE
    )
  )

  temporary_directory <- tempfile("rbiogeme-b14-")
  dir.create(temporary_directory, recursive = TRUE)
  original_directory <- getwd()
  setwd(temporary_directory)
  on.exit(setwd(original_directory), add = TRUE)

  r_fit <- estimate(
    model,
    model_name = "b14_nested_endogenous_sampling",
    control = model$control
  )
  native <- native_swissmetro_b14(data)
  expect_equal(nobs(r_fit), native$number_of_rows)
  expect_identical(r_fit$beta_names, native$results$beta_names)
  expect_equal(unname(coef(r_fit)), native$results$beta_values, tolerance = 1e-8)
  expect_equal(as.numeric(logLik(r_fit)), native$results$final_log_likelihood, tolerance = 1e-8)
  expect_equal(r_fit$number_of_excluded_data, native$results$number_of_excluded_data)
  expect_identical(isTRUE(r_fit$convergence), isTRUE(native$results$convergence))
})