tests/testthat/test-swissmetro-b02.R

In rbiogeme: Interface to 'Biogeme'

native_swissmetro_b02 <- 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)

  database <- database_module$Database(
    "swissmetro_native_b02",
    reticulate::r_to_py(data)
  )
  variable <- expressions$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$Beta
  asc_car <- beta("asc_car", 0, NULL, NULL, 0)
  asc_train <- beta("asc_train", 0, NULL, NULL, 0)
  asc_sm <- beta("asc_sm", 0, NULL, NULL, 1)
  b_time <- beta("b_time", 0, NULL, NULL, 0)
  b_cost <- beta("b_cost", 0, NULL, NULL, 0)
  utilities <- reticulate::dict(
    `1` = asc_train + b_time * train_tt_scaled + b_cost * train_cost_scaled,
    `2` = asc_sm + b_time * sm_tt_scaled + b_cost * sm_cost_scaled,
    `3` = asc_car + b_time * car_tt_scaled + b_cost * car_co_scaled
  )
  availability <- reticulate::dict(
    `1` = train_av_sp,
    `2` = variable("SM_AV"),
    `3` = car_av_sp
  )
  log_probability <- models$loglogit(utilities, availability, choice)
  weight <- 8.890991e-01 * (variable("GROUP") == 2) +
    1.2 * (variable("GROUP") == 3)
  # Build the Python formula mapping explicitly. Using convert=FALSE keeps
  # native Biogeme expression nodes as values rather than asking reticulate
  # to inspect their Python classes while constructing the mapping.
  formulas <- reticulate::dict(
    list(log_like = log_probability, weight = weight),
    convert = FALSE
  )
  biogeme <- biogeme_module$BIOGEME(
    database,
    formulas,
    generate_html = FALSE,
    generate_yaml = FALSE,
    save_iterations = FALSE
  )
  biogeme$model_name <- "b02_native"
  biogeme$calculate_null_loglikelihood(availability)
  results <- biogeme$estimate()
  bridge <- rbiogeme:::biogeme_bridge()
  list(
    results = reticulate::py_to_r(bridge$extract_estimation_results(results)),
    number_of_rows = nrow(reticulate::py_to_r(database$dataframe))
  )
}

test_that("b02 Swissmetro WESML 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)
  model <- local({
    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)
    logit_model(
      database = database,
      choice = "CHOICE",
      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")
      ),
      weight = 8.890991e-01 * (variable("GROUP") == 2) +
        1.2 * (variable("GROUP") == 3)
    )
  })

  temporary_directory <- tempfile("rbiogeme-b02-")
  dir.create(temporary_directory, recursive = TRUE)
  original_directory <- getwd()
  setwd(temporary_directory)
  on.exit(setwd(original_directory), add = TRUE)

  control <- biogeme_control(
    model_name = "b02_r",
    generate_html = FALSE,
    generate_yaml = FALSE,
    save_iterations = FALSE
  )
  r_fit <- estimate(model, model_name = "b02_r", control = control)
  native <- native_swissmetro_b02(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$number_of_excluded_data)
  expect_true(isTRUE(r_fit$derivatives_available))
  native_vcov <- matrix(
    as.numeric(unlist(native_results$variance_covariance, use.names = FALSE)),
    nrow = length(native_results$beta_names)
  )
  expect_equal(unname(vcov(r_fit)), native_vcov, tolerance = 1e-8)
  expect_identical(isTRUE(r_fit$convergence), isTRUE(native_results$convergence))
})