R/RcppExports.R

In scNPM: Single-Cell Network Propensity Matching

# Generated by using Rcpp::compileAttributes() -> do not edit by hand
# Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393

set_scNPM_threads <- function(threads) {
    .Call(`_scNPM_set_scNPM_threads`, threads)
}

sampler_thread_info <- function() {
    .Call(`_scNPM_sampler_thread_info`)
}

calculate_edge_probability <- function(omega, v0, v1, xi) {
    .Call(`_scNPM_calculate_edge_probability`, omega, v0, v1, xi)
}

calculate_propensity_score <- function(X, treatment_status) {
    .Call(`_scNPM_calculate_propensity_score`, X, treatment_status)
}

calculate_reference_quadratic_forms <- function(theta_t, mu_treat, mu_ctrl, invcov_treat, invcov_ctrl) {
    .Call(`_scNPM_calculate_reference_quadratic_forms`, theta_t, mu_treat, mu_ctrl, invcov_treat, invcov_ctrl)
}

network_propensity_matching_by_difficulty <- function(theta_t, cell_t, group_treat, group_ctrl, treat_idx, ctrl_idx, invcov_treat, invcov_ctrl, G, K, mu_treat = NULL, mu_ctrl = NULL, network_covariates = "legacy", propensity_ridge = 1e-6, matching_method = "greedy") {
    .Call(`_scNPM_network_propensity_matching_by_difficulty`, theta_t, cell_t, group_treat, group_ctrl, treat_idx, ctrl_idx, invcov_treat, invcov_ctrl, G, K, mu_treat, mu_ctrl, network_covariates, propensity_ridge, matching_method)
}

paired_column_diagnostic <- function(draws = 25000L) {
    .Call(`_scNPM_paired_column_diagnostic`, draws)
}

MCMC_with_difficulty_based_matching <- function(num_iter, num_save, theta_t, ind_zero, mu_treat, mu_ctrl, invcov_treat, cov_treat, invcov_ctrl, cov_ctrl, edge_treat, edge_ctrl, group_treat, group_ctrl, lambda0_t, lambda1_t, pi_treat, pi_ctrl, gam, cell_t, G, N_int, K, ssp_v0, ssp_v1, ssp_l, ssp_xi, epsilon_theta = 0.2, num_step_theta = 20L, eta_mu = 0.0, tau_sq_mu = 1.0, lam0_0 = 2.0, lam1_0 = -2.0, sigma2_lam0 = 0.25, sigma2_lam1 = 0.25, edge_prob_threshold = 0.6, edge_prob_adj = 0.75, epsilon_lam = 0.01, num_step_lam = 10L, edge_prior = NULL, network_covariates = "all_reference", propensity_ridge = 1e-6, inference_mode = "coupled", adapt_min = 1L, adapt_max = 1L, freeze_patience = 2L, final_burnin = 1L, diagnostic_every = 10L, matching_method = "greedy", verbose = FALSE, freeze_policy = "consensus", freeze_window = 100L, matching_cost_function = NULL, progress_every = 60.0, progress_callback = NULL, network_prior = "independent", paired_base = 0.05, paired_discordance = 0.75, shared_edge_correlation = 0.995, ppi_reference = "control") {
    .Call(`_scNPM_MCMC_with_difficulty_based_matching`, num_iter, num_save, theta_t, ind_zero, mu_treat, mu_ctrl, invcov_treat, cov_treat, invcov_ctrl, cov_ctrl, edge_treat, edge_ctrl, group_treat, group_ctrl, lambda0_t, lambda1_t, pi_treat, pi_ctrl, gam, cell_t, G, N_int, K, ssp_v0, ssp_v1, ssp_l, ssp_xi, epsilon_theta, num_step_theta, eta_mu, tau_sq_mu, lam0_0, lam1_0, sigma2_lam0, sigma2_lam1, edge_prob_threshold, edge_prob_adj, epsilon_lam, num_step_lam, edge_prior, network_covariates, propensity_ridge, inference_mode, adapt_min, adapt_max, freeze_patience, final_burnin, diagnostic_every, matching_method, verbose, freeze_policy, freeze_window, matching_cost_function, progress_every, progress_callback, network_prior, paired_base, paired_discordance, shared_edge_correlation, ppi_reference)
}

update_mu_R <- function(theta_t, invcov_t, group_t, G, K, eta_mu = 0, tau_sq_mu = 1) {
    .Call(`_scNPM_update_mu_R`, theta_t, invcov_t, group_t, G, K, eta_mu, tau_sq_mu)
}

update_pi_R <- function(group_t, gam, K) {
    .Call(`_scNPM_update_pi_R`, group_t, gam, K)
}

staged_assignment <- function(cost) {
    .Call(`_scNPM_staged_assignment`, cost)
}

lexicographic_assignment <- function(cost) {
    .Call(`_scNPM_lexicographic_assignment`, cost)
}