P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2026-05-31 18:21:44 +02:00
Code Releases Activity

unit tests

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends
2026-04-30 01:28:58 +02:00
parent 61b6c26834
commit cd70349e8c
1 changed files with 94 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

171
tests/testthat/test-sir.R
View File

@@ -441,94 +441,111 @@ test_that("test-sir.R", {
# Tests must pass even when only 1 core is available; parallel = TRUE then # Tests must pass even when only 1 core is available; parallel = TRUE then
# silently falls back to sequential, but results must still be identical. # silently falls back to sequential, but results must still be identical.
set.seed(42) if (AMR:::pkg_is_available("future.apply")) {
n_par <- 200 set.seed(42)
df_par <- data.frame( n_par <- 200
mo = "B_ESCHR_COLI", df_par <- data.frame(
AMC = as.mic(sample(c("0.25", "0.5", "1", "2", "4", "8", "16", "32"), n_par, TRUE)), mo = "B_ESCHR_COLI",
GEN = as.mic(sample(c("0.5", "1", "2", "4", "8", "16", "32", "64"), n_par, TRUE)), AMC = as.mic(sample(c("0.25", "0.5", "1", "2", "4", "8", "16", "32"), n_par, TRUE)),
CIP = as.mic(sample(c("0.001", "0.002", "0.004", "0.008", "0.016", "0.032"), n_par, TRUE)), GEN = as.mic(sample(c("0.5", "1", "2", "4", "8", "16", "32", "64"), n_par, TRUE)),
PEN = sample(c("S", "I", "R", NA_character_), n_par, TRUE), CIP = as.mic(sample(c("0.001", "0.002", "0.004", "0.008", "0.016", "0.032"), n_par, TRUE)),
stringsAsFactors = FALSE PEN = sample(c("S", "I", "R", NA_character_), n_par, TRUE),
) stringsAsFactors = FALSE
)
# clear any existing history before comparing # clear any existing history before comparing
sir_interpretation_history(clean = TRUE) sir_interpretation_history(clean = TRUE)
sir_seq <- suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE)) sir_seq <- suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE))
log_seq <- sir_interpretation_history(clean = TRUE) log_seq <- sir_interpretation_history(clean = TRUE)
sir_par <- suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE, parallel = TRUE)) future::plan(future::multicore)
log_par <- sir_interpretation_history(clean = TRUE) n_max_workers <- future::nbrOfWorkers()
# 1. parallel = TRUE gives identical SIR results to sequential sir_par <- suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE, parallel = TRUE))
expect_identical(sir_seq[["AMC"]], sir_par[["AMC"]]) log_par <- sir_interpretation_history(clean = TRUE)
expect_identical(sir_seq[["GEN"]], sir_par[["GEN"]])
expect_identical(sir_seq[["CIP"]], sir_par[["CIP"]])
expect_identical(sir_seq[["PEN"]], sir_par[["PEN"]])
# 2. same number of log rows as sequential # 1. parallel = TRUE gives identical SIR results to sequential
expect_equal(nrow(log_seq), nrow(log_par)) expect_identical(sir_seq[["AMC"]], sir_par[["AMC"]])
expect_identical(sir_seq[["GEN"]], sir_par[["GEN"]])
expect_identical(sir_seq[["CIP"]], sir_par[["CIP"]])
expect_identical(sir_seq[["PEN"]], sir_par[["PEN"]])
# 3. pre-existing log entries must not be duplicated # 2. same number of log rows as sequential
# run sequential once to populate the history, then run parallel and expect_equal(nrow(log_seq), nrow(log_par))
# verify the new parallel run adds exactly as many rows as sequential
sir_interpretation_history(clean = TRUE)
suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE)) # populate history
pre_n <- nrow(sir_interpretation_history())
suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE, parallel = TRUE))
post_n <- nrow(sir_interpretation_history())
expect_equal(post_n - pre_n, nrow(log_seq)) # exactly one run's worth of new rows
sir_interpretation_history(clean = TRUE)
# 4. two sequential runs and two parallel runs yield identical results # 3. pre-existing log entries must not be duplicated
sir_par2 <- suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE, parallel = TRUE)) # run sequential once to populate the history, then run parallel and
expect_identical(sir_par[["AMC"]], sir_par2[["AMC"]]) # verify the new parallel run adds exactly as many rows as sequential
expect_identical(sir_par[["GEN"]], sir_par2[["GEN"]]) sir_interpretation_history(clean = TRUE)
future::plan(future::sequential)
suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE)) # populate history
pre_n <- nrow(sir_interpretation_history())
future::plan(future::multicore)
suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE, parallel = TRUE))
post_n <- nrow(sir_interpretation_history())
expect_equal(post_n - pre_n, nrow(log_seq)) # exactly one run's worth of new rows
sir_interpretation_history(clean = TRUE)
# 5. max_cores = 1 gives same results as default sequential # 4. two sequential runs and two parallel runs yield identical results
sir_mc1 <- suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE, parallel = TRUE, max_cores = 1L)) sir_par2 <- suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE, parallel = TRUE))
expect_identical(sir_seq[["AMC"]], sir_mc1[["AMC"]]) expect_identical(sir_par[["AMC"]], sir_par2[["AMC"]])
expect_identical(sir_seq[["GEN"]], sir_mc1[["GEN"]]) expect_identical(sir_par[["GEN"]], sir_par2[["GEN"]])
# 6. max_cores = 2 and max_cores = 3 give same results as sequential # 5. max_cores = 1 gives same results as default sequential
sir_mc2 <- suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE, parallel = TRUE, max_cores = 2L)) future::plan(future::multicore, workers = 1)
sir_mc3 <- suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE, parallel = TRUE, max_cores = 3L)) sir_mc1 <- suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE, parallel = TRUE))
expect_identical(sir_seq[["AMC"]], sir_mc2[["AMC"]]) expect_identical(sir_seq[["AMC"]], sir_mc1[["AMC"]])
expect_identical(sir_seq[["GEN"]], sir_mc3[["GEN"]]) expect_identical(sir_seq[["GEN"]], sir_mc1[["GEN"]])
# 7. single-column data frame falls back silently to sequential # 6. max_cores = 2 and max_cores = 3 give same results as sequential
df_single <- df_par[, c("mo", "AMC")] if (n_max_workers >= 3) {
sir_single_seq <- suppressMessages(as.sir(df_single, col_mo = "mo", info = FALSE)) future::plan(future::multicore, workers = 2)
sir_single_par <- suppressMessages(as.sir(df_single, col_mo = "mo", info = FALSE, parallel = TRUE)) sir_mc2 <- suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE, parallel = TRUE))
expect_identical(sir_single_seq[["AMC"]], sir_single_par[["AMC"]]) future::plan(future::multicore, workers = 3)
sir_mc3 <- suppressMessages(as.sir(df_par, col_mo = "mo", info = FALSE, parallel = TRUE))
expect_identical(sir_seq[["AMC"]], sir_mc2[["AMC"]])
expect_identical(sir_seq[["GEN"]], sir_mc3[["GEN"]])
}
# 9. row-batch mode (n_cols < n_cores): force row splitting via max_cores and # 7. single-column data frame falls back silently to sequential
# verify identical output to sequential for a dataset with 2 AB columns so df_single <- df_par[, c("mo", "AMC")]
# pieces_per_col = ceiling(max_cores / 2) >= 2 and row batching activates future::plan(future::sequential)
df_wide <- data.frame( sir_single_seq <- suppressMessages(as.sir(df_single, col_mo = "mo", info = FALSE))
mo = "B_ESCHR_COLI", future::plan(future::multicore)
AMC = as.mic(sample(c("1", "2", "4", "8"), n_par, TRUE)), sir_single_par <- suppressMessages(as.sir(df_single, col_mo = "mo", info = FALSE, parallel = TRUE))
GEN = as.mic(sample(c("1", "2", "4", "8"), n_par, TRUE)), expect_identical(sir_single_seq[["AMC"]], sir_single_par[["AMC"]])
stringsAsFactors = FALSE
)
sir_wide_seq <- suppressMessages(as.sir(df_wide, col_mo = "mo", info = FALSE))
sir_wide_par <- suppressMessages(as.sir(df_wide,
col_mo = "mo", info = FALSE,
parallel = TRUE, max_cores = 8L
))
expect_identical(sir_wide_seq[["AMC"]], sir_wide_par[["AMC"]])
expect_identical(sir_wide_seq[["GEN"]], sir_wide_par[["GEN"]])
# 8. info = TRUE with parallel does not produce per-column worker messages # 8. row-batch mode (n_cols < n_cores): force row splitting via max_cores and
# (messages should only appear in the main process, not duplicated from workers) # verify identical output to sequential for a dataset with 2 AB columns so
msgs <- capture.output( # pieces_per_col = ceiling(max_cores / 2) >= 2 and row batching activates
suppressWarnings(as.sir(df_par, col_mo = "mo", info = TRUE, parallel = TRUE)), df_wide <- data.frame(
type = "message" mo = "B_ESCHR_COLI",
) AMC = as.mic(sample(c("1", "2", "4", "8"), n_par, TRUE)),
# each AB column name should appear at most once in all messages combined GEN = as.mic(sample(c("1", "2", "4", "8"), n_par, TRUE)),
for (ab_nm in c("AMC", "GEN", "CIP", "PEN")) { stringsAsFactors = FALSE
n_mentions <- sum(grepl(ab_nm, msgs, fixed = TRUE)) )
expect_lte(n_mentions, 1L) future::plan(future::sequential)
sir_wide_seq <- suppressMessages(as.sir(df_wide, col_mo = "mo", info = FALSE))
future::plan(future::multicore)
sir_wide_par <- suppressMessages(as.sir(df_wide,
col_mo = "mo", info = FALSE,
parallel = TRUE, max_cores = 8L
))
expect_identical(sir_wide_seq[["AMC"]], sir_wide_par[["AMC"]])
expect_identical(sir_wide_seq[["GEN"]], sir_wide_par[["GEN"]])
# 8. info = TRUE with parallel does not produce per-column worker messages
# (messages should only appear in the main process, not duplicated from workers)
msgs <- capture.output(
suppressWarnings(as.sir(df_par, col_mo = "mo", info = TRUE, parallel = TRUE)),
type = "message"
)
# each AB column name should appear at most once in all messages combined
for (ab_nm in c("AMC", "GEN", "CIP", "PEN")) {
n_mentions <- sum(grepl(ab_nm, msgs, fixed = TRUE))
expect_lte(n_mentions, 1L)
}
future::plan(future::sequential)
} }
}) })