--- title: "Benchmark timings for mkin" author: "Johannes Ranke" date: Last change 17 February 2023 (rebuilt `r Sys.Date()`) output: html_document: toc: true toc_float: true code_folding: show fig_retina: null vignette: > %\VignetteEngine{knitr::rmarkdown} %\VignetteEncoding{UTF-8} --- ```{r, include = FALSE} library(knitr) opts_chunk$set(tidy = FALSE, cache = FALSE) library("mkin") ``` Each system is characterized by the operating system type, the CPU type, the mkin version, and, as in June 2022 the current R version lead to worse performance, the R version. A compiler was available, so if no analytical solution was available, compiled ODE models are used. Every fit is only performed once, so the accuracy of the benchmarks is limited. The following wrapper function for `mmkin` is used because the way the error model is specified was changed in mkin version 0.9.49.1. ```{r} if (packageVersion("mkin") > "0.9.48.1") { mmkin_bench <- function(models, datasets, error_model = "const") { mmkin(models, datasets, error_model = error_model, cores = 1, quiet = TRUE) } } else { mmkin_bench <- function(models, datasets, error_model = NULL) { mmkin(models, datasets, reweight.method = error_model, cores = 1, quiet = TRUE) } } ``` ```{r include = FALSE} cpu_model <- benchmarkme::get_cpu()$model_name # Abbreviate CPU identifiers cpu_model <- gsub("AMD ", "", cpu_model) cpu_model <- gsub("Intel\\(R\\) Core\\(TM\\) ", "", cpu_model) cpu_model <- gsub(" Eight-Core Processor", "", cpu_model) cpu_model <- gsub(" 16-Core Processor", "", cpu_model) cpu_model <- gsub(" CPU @ 2.50GHz", "", cpu_model) operating_system <- Sys.info()[["sysname"]] mkin_version <- as.character(packageVersion("mkin")) R_version <- paste0(R.version$major, ".", R.version$minor) system_string <- paste0(operating_system, ", ", cpu_model, ", mkin ", mkin_version, ", R ", R_version) if (dir.exists("~/git/mkin")) { benchmark_path = normalizePath("~/git/mkin/vignettes/web_only/mkin_benchmarks.rda") } else { benchmark_path = normalizePath("~/projects/mkin/vignettes/web_only/mkin_benchmarks.rda") } load(benchmark_path) # Used for reformatting the data on 2022-06-30 # mkin_benchmarks[, "R"] <- NA # mkin_benchmarks <- mkin_benchmarks[c(2, 1, 15, 3, 4:14)] # mkin_benchmarks[, "CPU"] <- gsub("AMD.*", "Ryzen 7 1700", mkin_benchmarks[, "CPU"]) # mkin_benchmarks[, "CPU"] <- gsub("Intel.*", "i7-4710MQ", mkin_benchmarks[, "CPU"]) # rownames(mkin_benchmarks) <- gsub("AMD Ryzen 7 1700 Eight-Core Processor", "Ryzen 7 1700", rownames(mkin_benchmarks)) # rownames(mkin_benchmarks) <- gsub("Intel\\(R\\) Core\\(TM\\) i7-4710MQ CPU @ 2.50GHz", "i7-4710MQ", rownames(mkin_benchmarks)) # rownames(mkin_benchmarks) <- gsub(" version", "", rownames(mkin_benchmarks)) mkin_benchmarks[system_string, c("CPU", "OS", "mkin", "R")] <- c(cpu_model, operating_system, mkin_version, R_version) ``` ## Test cases Parent only: ```{r parent_only, warning = FALSE} FOCUS_C <- FOCUS_2006_C FOCUS_D <- subset(FOCUS_2006_D, value != 0) parent_datasets <- list(FOCUS_C, FOCUS_D) t1 <- system.time(mmkin_bench(c("SFO", "FOMC", "DFOP", "HS"), parent_datasets))[["elapsed"]] t2 <- system.time(mmkin_bench(c("SFO", "FOMC", "DFOP", "HS"), parent_datasets, error_model = "tc"))[["elapsed"]] ``` One metabolite: ```{r one_metabolite, message = FALSE} SFO_SFO <- mkinmod( parent = mkinsub("SFO", "m1"), m1 = mkinsub("SFO")) FOMC_SFO <- mkinmod( parent = mkinsub("FOMC", "m1"), m1 = mkinsub("SFO")) DFOP_SFO <- mkinmod( parent = mkinsub("FOMC", "m1"), # erroneously used FOMC twice, not fixed for consistency m1 = mkinsub("SFO")) t3 <- system.time(mmkin_bench(list(SFO_SFO, FOMC_SFO, DFOP_SFO), list(FOCUS_D)))[["elapsed"]] t4 <- system.time(mmkin_bench(list(SFO_SFO, FOMC_SFO, DFOP_SFO), list(FOCUS_D), error_model = "tc"))[["elapsed"]] t5 <- system.time(mmkin_bench(list(SFO_SFO, FOMC_SFO, DFOP_SFO), list(FOCUS_D), error_model = "obs"))[["elapsed"]] ``` Two metabolites, synthetic data: ```{r two_metabolites, message = FALSE} m_synth_SFO_lin <- mkinmod(parent = mkinsub("SFO", "M1"), M1 = mkinsub("SFO", "M2"), M2 = mkinsub("SFO"), use_of_ff = "max", quiet = TRUE) m_synth_DFOP_par <- mkinmod(parent = mkinsub("DFOP", c("M1", "M2")), M1 = mkinsub("SFO"), M2 = mkinsub("SFO"), use_of_ff = "max", quiet = TRUE) SFO_lin_a <- synthetic_data_for_UBA_2014[[1]]$data DFOP_par_c <- synthetic_data_for_UBA_2014[[12]]$data t6 <- system.time(mmkin_bench(list(m_synth_SFO_lin), list(SFO_lin_a)))[["elapsed"]] t7 <- system.time(mmkin_bench(list(m_synth_DFOP_par), list(DFOP_par_c)))[["elapsed"]] t8 <- system.time(mmkin_bench(list(m_synth_SFO_lin), list(SFO_lin_a), error_model = "tc"))[["elapsed"]] t9 <- system.time(mmkin_bench(list(m_synth_DFOP_par), list(DFOP_par_c), error_model = "tc"))[["elapsed"]] t10 <- system.time(mmkin_bench(list(m_synth_SFO_lin), list(SFO_lin_a), error_model = "obs"))[["elapsed"]] t11 <- system.time(mmkin_bench(list(m_synth_DFOP_par), list(DFOP_par_c), error_model = "obs"))[["elapsed"]] ``` ```{r results, include = FALSE} mkin_benchmarks[system_string, paste0("t", 1:11)] <- c(t1, t2, t3, t4, t5, t6, t7, t8, t9, t10, t11) save(mkin_benchmarks, file = benchmark_path, version = 2) # Hide rownames from kable for results section rownames(mkin_benchmarks) <- NULL ``` ## Results Benchmarks for all available error models are shown. They are intended for improving mkin, not for comparing CPUs or operating systems. All trademarks belong to their respective owners. ### Parent only Constant variance (t1) and two-component error model (t2) for four models fitted to two datasets, i.e. eight fits for each test. ```{r, echo = FALSE} kable(mkin_benchmarks[, c(1:4, 5:6)]) ``` ### One metabolite Constant variance (t3), two-component error model (t4), and variance by variable (t5) for three models fitted to one dataset, i.e. three fits for each test. ```{r, echo = FALSE} kable(mkin_benchmarks[, c(1:4, 7:9)]) ``` ### Two metabolites Constant variance (t6 and t7), two-component error model (t8 and t9), and variance by variable (t10 and t11) for one model fitted to one dataset, i.e. one fit for each test. ```{r, echo = FALSE} kable(mkin_benchmarks[, c(1:4, 10:15)]) ```