tests/testthat/test-swissmetro-b23a.R

In rbiogeme: Interface to 'Biogeme'

native_swissmetro_b23a <- 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)
  bridge <- rbiogeme:::biogeme_bridge()

  database <- database_module$Database(
    "swissmetro_native_b23a",
    reticulate::r_to_py(data)
  )
  variable <- expressions$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)

  database$remove(
    ((choice == 2) + (car_av_sp == 0) + (train_av_sp == 0)) > 0
  )

  beta <- expressions$Beta
  asc_car <- beta("asc_car", 0, NULL, NULL, 0)
  b_time_car <- beta("b_time_car", 0, NULL, NULL, 0)
  b_time_train <- beta("b_time_train", 0, NULL, NULL, 0)
  b_cost_car <- beta("b_cost_car", 0, NULL, NULL, 0)
  b_cost_train <- beta("b_cost_train", 0, NULL, NULL, 0)
  v_train <- b_time_train * train_tt_scaled + b_cost_train * train_cost_scaled
  v_car <- asc_car + b_time_car * car_tt_scaled + b_cost_car * car_co_scaled
  log_probability <- models$loglogit(
    reticulate::dict(`1` = v_train, `3` = v_car),
    reticulate::dict(`1` = train_av_sp, `3` = car_av_sp),
    choice
  )

  biogeme <- biogeme_module$BIOGEME(
    database,
    log_probability,
    generate_html = FALSE,
    generate_yaml = FALSE,
    save_iterations = FALSE
  )
  biogeme$model_name <- "b23a_logit_native"
  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("b23a Swissmetro binary 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)
  database <- biogeme_database_remove(
    database,
    variable("CHOICE") == 2 |
      variable("CAR_AV_SP") == 0 |
      variable("TRAIN_AV_SP") == 0
  )
  parameters <- list(
    asc_car = biogeme_beta("asc_car", start = 0),
    b_time_car = biogeme_beta("b_time_car", start = 0),
    b_time_train = biogeme_beta("b_time_train", start = 0),
    b_cost_car = biogeme_beta("b_cost_car", start = 0),
    b_cost_train = biogeme_beta("b_cost_train", start = 0)
  )
  log_probability <- logit_log_probability(
    utilities = list(
      `1` = parameters$b_time_train * variable("TRAIN_TT_SCALED") +
        parameters$b_cost_train * variable("TRAIN_COST_SCALED"),
      `3` = parameters$asc_car + parameters$b_time_car * variable("CAR_TT_SCALED") +
        parameters$b_cost_car * variable("CAR_CO_SCALED")
    ),
    availability = list(
      `1` = variable("TRAIN_AV_SP"),
      `3` = variable("CAR_AV_SP")
    ),
    alternative = variable("CHOICE")
  )
  model <- biogeme_model(database, formula = log_probability)

  temporary_directory <- tempfile("rbiogeme-b23a-")
  dir.create(temporary_directory, recursive = TRUE)
  original_directory <- getwd()
  setwd(temporary_directory)
  on.exit(setwd(original_directory), add = TRUE)
  controls <- biogeme_control(
    model_name = "b23a_logit",
    generate_html = FALSE,
    generate_yaml = FALSE,
    save_iterations = FALSE
  )
  r_fit <- estimate(
    model,
    model_name = "b23a_logit",
    control = controls
  )
  native <- native_swissmetro_b23a(data)
  native_results <- native$results

  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))
})