test-swissmetro-b20.R
In rbiogeme: Interface to 'Biogeme'

native_swissmetro_b20 <- 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)
  catalog_module <- reticulate::import("biogeme.catalog", convert = FALSE)
  segmentation_module <- reticulate::import("biogeme.segmentation", convert = FALSE)
  models <- reticulate::import("biogeme.models", convert = FALSE)
  results_processing <- reticulate::import(
    "biogeme.results_processing",
    convert = FALSE
  )
  bridge <- rbiogeme:::biogeme_bridge()

  database <- database_module$Database(
    "swissmetro_native_b20",
    reticulate::r_to_py(data)
  )
  variable <- expressions$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)

  gender <- database$generate_segmentation(
    variable = variable("MALE"),
    mapping = reticulate::dict(`0` = "female", `1` = "male")
  )
  beta <- expressions$Beta
  asc_car <- beta("asc_car", 0, NULL, NULL, 0)
  asc_train <- beta("asc_train", 0, NULL, NULL, 0)
  b_time <- beta("b_time", 0, NULL, NULL, 0)
  b_cost <- beta("b_cost", 0, NULL, NULL, 0)
  asc_controller <- catalog_module$Controller(
    controller_name = "asc",
    specification_names = reticulate::r_to_py(c("no_seg", "MALE"))
  )
  asc_train_catalog <- catalog_module$Catalog$from_dict(
    catalog_name = "segmented_asc_train",
    dict_of_expressions = reticulate::dict(
      no_seg = asc_train,
      MALE = segmentation_module$Segmentation(asc_train, list(gender))$segmented_beta()
    ),
    controlled_by = asc_controller
  )
  asc_car_catalog <- catalog_module$Catalog$from_dict(
    catalog_name = "segmented_asc_car",
    dict_of_expressions = reticulate::dict(
      no_seg = asc_car,
      MALE = segmentation_module$Segmentation(asc_car, list(gender))$segmented_beta()
    ),
    controlled_by = asc_controller
  )
  time_controller <- catalog_module$Controller(
    controller_name = "train_tt_catalog",
    specification_names = reticulate::r_to_py(c("linear", "log"))
  )
  train_tt_catalog <- catalog_module$Catalog$from_dict(
    catalog_name = "train_tt_catalog",
    dict_of_expressions = reticulate::dict(
      linear = train_tt_scaled,
      log = expressions$log(train_tt_scaled)
    ),
    controlled_by = time_controller
  )
  sm_tt_catalog <- catalog_module$Catalog$from_dict(
    catalog_name = "sm_tt_catalog",
    dict_of_expressions = reticulate::dict(
      linear = sm_tt_scaled,
      log = expressions$log(sm_tt_scaled)
    ),
    controlled_by = time_controller
  )
  utilities <- reticulate::dict(
    `1` = asc_train_catalog + b_time * train_tt_catalog + b_cost * train_cost_scaled,
    `2` = b_time * sm_tt_catalog + b_cost * sm_cost_scaled,
    `3` = asc_car_catalog + 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
  )
  estimator <- biogeme_module$BIOGEME(
    database,
    models$loglogit(utilities, availability, choice),
    generate_html = FALSE,
    generate_yaml = FALSE,
    save_iterations = FALSE
  )
  estimator$model_name <- "b20multiple_models_native"
  native_results <- estimator$estimate_catalog()
  keys <- vapply(
    reticulate::iterate(native_results$keys()),
    as.character,
    character(1)
  )
  serialized <- lapply(keys, function(key) {
    result <- reticulate::py_get_item(native_results, key)
    reticulate::py_to_r(bridge$extract_estimation_results(result))
  })
  names(serialized) <- keys
  non_dominated <- results_processing$pareto_optimal(native_results)
  list(
    results = serialized,
    non_dominated = vapply(
      reticulate::iterate(non_dominated$keys()),
      as.character,
      character(1)
    ),
    number_of_rows = nrow(reticulate::py_to_r(database$dataframe))
  )
}

test_that("b20 Swissmetro catalog models match 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)
  gender <- biogeme_database_segmentation(
    database,
    "MALE",
    c(`0` = "female", `1` = "male")
  )
  asc_car <- biogeme_beta("asc_car", start = 0)
  asc_train <- biogeme_beta("asc_train", start = 0)
  b_time <- biogeme_beta("b_time", start = 0)
  b_cost <- biogeme_beta("b_cost", start = 0)
  asc_controller <- catalog_controller("asc", c("no_seg", "MALE"))
  asc_train_catalog <- catalog(
    "segmented_asc_train",
    list(no_seg = asc_train, MALE = segment_beta(asc_train, list(gender))),
    asc_controller
  )
  asc_car_catalog <- catalog(
    "segmented_asc_car",
    list(no_seg = asc_car, MALE = segment_beta(asc_car, list(gender))),
    asc_controller
  )
  time_controller <- catalog_controller("train_tt_catalog", c("linear", "log"))
  train_tt_catalog <- catalog(
    "train_tt_catalog",
    list(linear = variable("TRAIN_TT_SCALED"), log = log(variable("TRAIN_TT_SCALED"))),
    time_controller
  )
  sm_tt_catalog <- catalog(
    "sm_tt_catalog",
    list(linear = variable("SM_TT_SCALED"), log = log(variable("SM_TT_SCALED"))),
    time_controller
  )
  log_probability <- logit_log_probability(
    utilities = list(
      `1` = asc_train_catalog + b_time * train_tt_catalog +
        b_cost * variable("TRAIN_COST_SCALED"),
      `2` = b_time * sm_tt_catalog + b_cost * variable("SM_COST_SCALED"),
      `3` = asc_car_catalog + 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")
    ),
    alternative = variable("CHOICE")
  )
  model <- biogeme_model(database, formula = log_probability)

  temporary_directory <- tempfile("rbiogeme-b20-")
  dir.create(temporary_directory, recursive = TRUE)
  original_directory <- getwd()
  setwd(temporary_directory)
  on.exit(setwd(original_directory), add = TRUE)
  control <- biogeme_control(
    model_name = "b20multiple_models",
    generate_html = FALSE,
    generate_yaml = FALSE,
    save_iterations = FALSE
  )
  r_fit <- estimate_catalog(
    model,
    model_name = "b20multiple_models",
    control = control,
    force = TRUE
  )
  native <- native_swissmetro_b20(data)

  expect_equal(length(r_fit$results), 4L)
  expect_equal(length(r_fit$results), length(native$results))
  expect_equal(nobs(r_fit$results[[1L]]), native$number_of_rows)
  expect_setequal(names(r_fit$results), names(native$results))
  for (configuration in names(native$results)) {
    r_result <- r_fit$results[[configuration]]
    native_result <- native$results[[configuration]]
    expect_identical(r_result$beta_names, native_result$beta_names)
    expect_equal(
      unname(coef(r_result)),
      native_result$beta_values,
      tolerance = 1e-7
    )
    expect_equal(
      as.numeric(logLik(r_result)),
      native_result$final_log_likelihood,
      tolerance = 1e-7
    )
  }
  expect_setequal(r_fit$non_dominated, native$non_dominated)
  expect_equal(nrow(r_fit$summary), 13L)
  expect_true(nzchar(r_fit$latex))
})