test-swissmetro-b11c.R
In rbiogeme: Interface to 'Biogeme'

native_swissmetro_b11c <- 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$Database(
    "swissmetro_native_b11c",
    reticulate::r_to_py(data)
  )
  variable <- expressions$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$Beta
  asc_car <- beta("asc_car", 0, NULL, NULL, 0)
  asc_train <- beta("asc_train", 0, NULL, NULL, 0)
  asc_sm <- beta("asc_sm", 0, NULL, NULL, 1)
  b_time <- beta("b_time", 0, NULL, NULL, 0)
  b_cost <- beta("b_cost", 0, NULL, NULL, 0)
  existing_nest_parameter <- beta("existing_nest_parameter", 1, 1, 5, 0)
  public_nest_parameter <- beta("public_nest_parameter", 1, 1, 5, 0)
  alpha_existing <- beta("alpha_existing", 0.5, 0, 1, 0)
  alpha_public <- 1 - alpha_existing
  utilities <- reticulate::dict(
    `1` = asc_train + b_time * train_tt_scaled + b_cost * train_cost_scaled,
    `2` = asc_sm + b_time * sm_tt_scaled + b_cost * sm_cost_scaled,
    `3` = asc_car + b_time * car_tt_scaled + b_cost * car_co_scaled
  )
  availability <- reticulate::dict(
    `1` = train_av_sp,
    `2` = variable("SM_AV"),
    `3` = car_av_sp
  )
  nest_existing <- nests_module$OneNestForCrossNestedLogit(
    nest_param = existing_nest_parameter,
    dict_of_alpha = reticulate::dict(`1` = alpha_existing, `3` = 1.0),
    name = "existing"
  )
  nest_public <- nests_module$OneNestForCrossNestedLogit(
    nest_param = public_nest_parameter,
    dict_of_alpha = reticulate::dict(`1` = alpha_public, `2` = 1.0),
    name = "public"
  )
  nests <- nests_module$NestsForCrossNestedLogit(
    choice_set = reticulate::r_to_py(as.integer(c(1L, 2L, 3L))),
    tuple_of_nests = reticulate::tuple(nest_existing, nest_public)
  )
  log_probability <- models$logcnl(utilities, availability, nests, choice)
  biogeme <- biogeme_module$BIOGEME(
    database,
    log_probability,
    generate_html = FALSE,
    generate_yaml = FALSE,
    save_iterations = FALSE
  )
  biogeme$model_name <- "b11c_cnl_sparse"
  results <- biogeme$estimate()
  list(
    results = reticulate::py_to_r(bridge$extract_estimation_results(results)),
    number_of_rows = nrow(reticulate::py_to_r(database$dataframe))
  )
}

test_that("b11c sparse CNL matches native Biogeme and dense semantics", {
  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)
  existing_nest_parameter <- biogeme_beta("existing_nest_parameter", start = 1, lower = 1, upper = 5)
  public_nest_parameter <- biogeme_beta("public_nest_parameter", start = 1, lower = 1, upper = 5)
  alpha_existing <- biogeme_beta("alpha_existing", start = 0.5, lower = 0, upper = 1)
  alpha_public <- 1 - alpha_existing
  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")
  )
  sparse_nests <- cross_nested_nests(
    choice_set = c(1L, 2L, 3L),
    sparse = TRUE,
    nests = list(
      cross_nested_nest(existing_nest_parameter, list(`1` = alpha_existing, `3` = 1), name = "existing"),
      cross_nested_nest(public_nest_parameter, list(`1` = alpha_public, `2` = 1), name = "public")
    )
  )
  dense_nests <- cross_nested_nests(
    choice_set = c(1L, 2L, 3L),
    nests = list(
      cross_nested_nest(existing_nest_parameter, list(`1` = alpha_existing, `2` = 0, `3` = 1), name = "existing"),
      cross_nested_nest(public_nest_parameter, list(`1` = alpha_public, `2` = 1, `3` = 0), name = "public")
    )
  )
  model <- cross_nested_logit_model(
    database = database,
    choice = "CHOICE",
    utilities = utilities,
    availability = availability,
    nests = sparse_nests,
    control = biogeme_control(
      model_name = "b11c_cnl_sparse",
      generate_html = FALSE,
      generate_yaml = FALSE,
      save_iterations = FALSE
    )
  )
  report <- cross_nested_sparsity_report(sparse_nests)
  expect_equal(report$stored_memberships, c(2L, 2L))
  expect_equal(report$active_memberships, c(2L, 2L))
  expect_equal(report$omitted_memberships, c(1L, 1L))
  expect_equal(report$density, c(2 / 3, 2 / 3))

  temporary_directory <- tempfile("rbiogeme-b11c-")
  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 = "b11c_cnl_sparse", control = model$control)
  native <- native_swissmetro_b11c(data)
  expect_equal(nobs(r_fit), native$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$final_log_likelihood, tolerance = 1e-8)
  native_beta_values <- as.numeric(native$results$beta_values)
  names(native_beta_values) <- native$results$beta_names

  sparse_log <- cross_nested_log_probability(
    utilities, availability, sparse_nests, variable("CHOICE")
  )
  dense_log <- cross_nested_log_probability(
    utilities, availability, dense_nests, variable("CHOICE")
  )
  sparse_model <- biogeme_model(database = database, formula = sparse_log)
  dense_model <- biogeme_model(database = database, formula = dense_log)
  sparse_values <- simulate(
    sparse_model,
    expressions = list(contribution = sparse_log),
    beta = native_beta_values,
    control = biogeme_control(model_name = "b11c_sparse_contributions")
  )
  dense_values <- simulate(
    dense_model,
    expressions = list(contribution = dense_log),
    beta = native_beta_values,
    control = biogeme_control(model_name = "b11c_dense_contributions")
  )
  expect_equal(
    sparse_values$values$contribution,
    dense_values$values$contribution,
    tolerance = 1e-12
  )
})