Estimates the runtimes of jobs using the random forest implemented in ranger. Observed runtimes are retrieved from the Registry and runtimes are predicted for unfinished jobs.

The estimated remaining time is calculated in the print method. You may also pass n here to determine the number of parallel jobs which is then used in a simple Longest Processing Time (LPT) algorithm to give an estimate for the parallel runtime.

estimateRuntimes(tab, ..., reg = getDefaultRegistry())

# S3 method for RuntimeEstimate
print(x, n = 1L, ...)

Arguments

tab

[data.table]
Table with column “job.id” and additional columns to predict the runtime. Observed runtimes will be looked up in the registry and serve as dependent variable. All columns in tab except “job.id” will be passed to ranger as independent variables to fit the model.

...

[ANY]
Additional parameters passed to ranger. Ignored for the print method.

reg

[Registry]
Registry. If not explicitly passed, uses the default registry (see setDefaultRegistry).

x

[RuntimeEstimate]
Object to print.

n

[integer(1)]
Number of parallel jobs to assume for runtime estimation.

Value

[RuntimeEstimate] which is a list with two named elements: “runtimes” is a data.table with columns “job.id”, “runtime” (in seconds) and “type” (“estimated” if runtime is estimated, “observed” if runtime was observed). The other element of the list named “model”] contains the fitted random forest object.

See also

binpack and lpt to chunk jobs according to their estimated runtimes.

Examples

batchtools:::example_push_temp(1) # Create a simple toy registry set.seed(1) tmp = makeExperimentRegistry(file.dir = NA, make.default = FALSE, seed = 1)
#> No readable configuration file found
#> Created registry in '/tmp/batchtools-example/reg' using cluster functions 'Interactive'
addProblem(name = "iris", data = iris, fun = function(data, ...) nrow(data), reg = tmp)
#> Adding problem 'iris'
addAlgorithm(name = "nrow", function(instance, ...) nrow(instance), reg = tmp)
#> Adding algorithm 'nrow'
addAlgorithm(name = "ncol", function(instance, ...) ncol(instance), reg = tmp)
#> Adding algorithm 'ncol'
addExperiments(algo.designs = list(nrow = data.table::CJ(x = 1:50, y = letters[1:5])), reg = tmp)
#> Adding 250 experiments ('iris'[1] x 'nrow'[250] x repls[1]) ...
addExperiments(algo.designs = list(ncol = data.table::CJ(x = 1:50, y = letters[1:5])), reg = tmp)
#> Adding 250 experiments ('iris'[1] x 'ncol'[250] x repls[1]) ...
# We use the job parameters to predict runtimes tab = unwrap(getJobPars(reg = tmp)) # First we need to submit some jobs so that the forest can train on some data. # Thus, we just sample some jobs from the registry while grouping by factor variables. library(data.table) ids = tab[, .SD[sample(nrow(.SD), 5)], by = c("problem", "algorithm", "y")] setkeyv(ids, "job.id") submitJobs(ids, reg = tmp)
#> Submitting 50 jobs in 50 chunks using cluster functions 'Interactive' ...
waitForJobs(reg = tmp)
#> [1] TRUE
# We "simulate" some more realistic runtimes here to demonstrate the functionality: # - Algorithm "ncol" is 5 times more expensive than "nrow" # - x has no effect on the runtime # - If y is "a" or "b", the runtimes are really high runtime = function(algorithm, x, y) { ifelse(algorithm == "nrow", 100L, 500L) + 1000L * (y %in% letters[1:2]) } tmp$status[ids, done := done + tab[ids, runtime(algorithm, x, y)]]
#> job.id def.id submitted started done error mem.used resource.id #> 1: 1 1 NA NA NA <NA> NA NA #> 2: 2 2 NA NA NA <NA> NA NA #> 3: 3 3 NA NA NA <NA> NA NA #> 4: 4 4 NA NA NA <NA> NA NA #> 5: 5 5 NA NA NA <NA> NA NA #> --- #> 496: 496 496 NA NA NA <NA> NA NA #> 497: 497 497 NA NA NA <NA> NA NA #> 498: 498 498 NA NA NA <NA> NA NA #> 499: 499 499 1603265964 1603265964 1603266464 <NA> NA 1 #> 500: 500 500 NA NA NA <NA> NA NA #> batch.id log.file job.hash job.name repl #> 1: <NA> <NA> <NA> <NA> 1 #> 2: <NA> <NA> <NA> <NA> 1 #> 3: <NA> <NA> <NA> <NA> 1 #> 4: <NA> <NA> <NA> <NA> 1 #> 5: <NA> <NA> <NA> <NA> 1 #> --- #> 496: <NA> <NA> <NA> <NA> 1 #> 497: <NA> <NA> <NA> <NA> 1 #> 498: <NA> <NA> <NA> <NA> 1 #> 499: cfInteractive <NA> joba17949c0e00e62405c8465e973297f1c <NA> 1 #> 500: <NA> <NA> <NA> <NA> 1
rjoin(sjoin(tab, ids), getJobStatus(ids, reg = tmp)[, c("job.id", "time.running")])
#> job.id problem algorithm x y time.running #> 1: 32 iris nrow 7 b 1100.0026 secs #> 2: 42 iris nrow 9 b 1100.0024 secs #> 3: 47 iris nrow 10 b 1100.0023 secs #> 4: 66 iris nrow 14 a 1100.0052 secs #> 5: 73 iris nrow 15 c 100.0023 secs #> 6: 75 iris nrow 15 e 100.0024 secs #> 7: 86 iris nrow 18 a 1100.0025 secs #> 8: 100 iris nrow 20 e 100.0026 secs #> 9: 101 iris nrow 21 a 1100.0024 secs #> 10: 103 iris nrow 21 c 100.0024 secs #> 11: 123 iris nrow 25 c 100.0024 secs #> 12: 125 iris nrow 25 e 100.0028 secs #> 13: 161 iris nrow 33 a 1100.0026 secs #> 14: 165 iris nrow 33 e 100.0026 secs #> 15: 169 iris nrow 34 d 100.0026 secs #> 16: 183 iris nrow 37 c 100.0027 secs #> 17: 184 iris nrow 37 d 100.0027 secs #> 18: 203 iris nrow 41 c 100.0036 secs #> 19: 207 iris nrow 42 b 1100.0024 secs #> 20: 209 iris nrow 42 d 100.0029 secs #> 21: 220 iris nrow 44 e 100.0023 secs #> 22: 227 iris nrow 46 b 1100.0024 secs #> 23: 229 iris nrow 46 d 100.0023 secs #> 24: 231 iris nrow 47 a 1100.0023 secs #> 25: 244 iris nrow 49 d 100.0022 secs #> 26: 260 iris ncol 2 e 500.0024 secs #> 27: 276 iris ncol 6 a 1500.0025 secs #> 28: 278 iris ncol 6 c 500.0025 secs #> 29: 279 iris ncol 6 d 500.0024 secs #> 30: 296 iris ncol 10 a 1500.0025 secs #> 31: 320 iris ncol 14 e 500.0023 secs #> 32: 340 iris ncol 18 e 500.0023 secs #> 33: 347 iris ncol 20 b 1500.0023 secs #> 34: 363 iris ncol 23 c 500.0023 secs #> 35: 369 iris ncol 24 d 500.0023 secs #> 36: 373 iris ncol 25 c 500.0025 secs #> 37: 387 iris ncol 28 b 1500.0023 secs #> 38: 410 iris ncol 32 e 500.0024 secs #> 39: 421 iris ncol 35 a 1500.0024 secs #> 40: 436 iris ncol 38 a 1500.0024 secs #> 41: 444 iris ncol 39 d 500.0022 secs #> 42: 448 iris ncol 40 c 500.0022 secs #> 43: 456 iris ncol 42 a 1500.0023 secs #> 44: 459 iris ncol 42 d 500.0023 secs #> 45: 467 iris ncol 44 b 1500.0023 secs #> 46: 468 iris ncol 44 c 500.0023 secs #> 47: 475 iris ncol 45 e 500.0024 secs #> 48: 482 iris ncol 47 b 1500.0023 secs #> 49: 492 iris ncol 49 b 1500.0023 secs #> 50: 499 iris ncol 50 d 500.0023 secs #> job.id problem algorithm x y time.running
# Estimate runtimes: est = estimateRuntimes(tab, reg = tmp) print(est)
#> Runtime Estimate for 500 jobs with 1 CPUs #> Done : 0d 09h 43m 20.1s #> Remaining: 3d 17h 37m 8.0s #> Total : 4d 03h 20m 28.1s
rjoin(tab, est$runtimes)
#> job.id problem algorithm x y type runtime #> 1: 1 iris nrow 1 a estimated 1107.0568 #> 2: 2 iris nrow 1 b estimated 1090.8508 #> 3: 3 iris nrow 1 c estimated 338.2092 #> 4: 4 iris nrow 1 d estimated 318.6349 #> 5: 5 iris nrow 1 e estimated 317.3189 #> --- #> 496: 496 iris ncol 50 a estimated 1381.9162 #> 497: 497 iris ncol 50 b estimated 1389.1659 #> 498: 498 iris ncol 50 c estimated 614.0596 #> 499: 499 iris ncol 50 d observed 500.0023 #> 500: 500 iris ncol 50 e estimated 574.7851
print(est, n = 10)
#> Runtime Estimate for 500 jobs with 10 CPUs #> Done : 0d 09h 43m 20.1s #> Remaining: 3d 17h 37m 8.0s #> Parallel : 0d 08h 58m 21.4s #> Total : 4d 03h 20m 28.1s
# Submit jobs with longest runtime first: ids = est$runtimes[type == "estimated"][order(runtime, decreasing = TRUE)] print(ids)
#> job.id type runtime #> 1: 466 estimated 1420.0934 #> 2: 461 estimated 1418.7001 #> 3: 462 estimated 1415.5134 #> 4: 457 estimated 1414.7134 #> 5: 487 estimated 1413.4847 #> --- #> 446: 194 estimated 133.0456 #> 447: 185 estimated 133.0030 #> 448: 204 estimated 131.6954 #> 449: 174 estimated 131.5901 #> 450: 179 estimated 130.4434
if (FALSE) { submitJobs(ids, reg = tmp) } # Group jobs into chunks with runtime < 1h ids = est$runtimes[type == "estimated"] ids[, chunk := binpack(runtime, 3600)]
#> job.id type runtime chunk #> 1: 1 estimated 1107.0568 47 #> 2: 2 estimated 1090.8508 51 #> 3: 3 estimated 338.2092 37 #> 4: 4 estimated 318.6349 33 #> 5: 5 estimated 317.3189 70 #> --- #> 446: 495 estimated 581.7197 17 #> 447: 496 estimated 1381.9162 20 #> 448: 497 estimated 1389.1659 15 #> 449: 498 estimated 614.0596 4 #> 450: 500 estimated 574.7851 26
print(ids)
#> job.id type runtime chunk #> 1: 1 estimated 1107.0568 47 #> 2: 2 estimated 1090.8508 51 #> 3: 3 estimated 338.2092 37 #> 4: 4 estimated 318.6349 33 #> 5: 5 estimated 317.3189 70 #> --- #> 446: 495 estimated 581.7197 17 #> 447: 496 estimated 1381.9162 20 #> 448: 497 estimated 1389.1659 15 #> 449: 498 estimated 614.0596 4 #> 450: 500 estimated 574.7851 26
print(ids[, list(runtime = sum(runtime)), by = chunk])
#> chunk runtime #> 1: 47 3493.187 #> 2: 51 3593.783 #> 3: 37 3598.573 #> 4: 33 3599.900 #> 5: 70 3493.489 #> 6: 53 3598.723 #> 7: 71 3491.366 #> 8: 48 3491.841 #> 9: 52 3597.483 #> 10: 54 3587.877 #> 11: 68 3499.779 #> 12: 72 3489.223 #> 13: 55 3583.526 #> 14: 69 3496.272 #> 15: 73 3483.829 #> 16: 46 3519.591 #> 17: 50 3599.943 #> 18: 38 3597.396 #> 19: 65 3512.646 #> 20: 43 3571.763 #> 21: 62 3522.617 #> 22: 66 3511.003 #> 23: 39 3599.908 #> 24: 35 3599.575 #> 25: 61 3533.407 #> 26: 40 3598.645 #> 27: 56 3571.361 #> 28: 57 3565.133 #> 29: 49 3481.931 #> 30: 42 3583.160 #> 31: 58 3555.775 #> 32: 60 3535.954 #> 33: 41 3588.180 #> 34: 36 3599.425 #> 35: 59 3545.174 #> 36: 44 3541.279 #> 37: 34 3599.586 #> 38: 64 3514.492 #> 39: 45 3540.479 #> 40: 63 3517.610 #> 41: 67 3507.819 #> 42: 27 3598.911 #> 43: 24 3599.823 #> 44: 25 3590.607 #> 45: 26 3598.511 #> 46: 23 3599.593 #> 47: 28 3573.496 #> 48: 75 3599.916 #> 49: 12 3559.937 #> 50: 74 3474.824 #> 51: 8 3593.188 #> 52: 20 3521.159 #> 53: 31 3599.784 #> 54: 7 3595.855 #> 55: 5 3594.254 #> 56: 11 3563.352 #> 57: 10 3575.839 #> 58: 6 3599.450 #> 59: 32 3598.576 #> 60: 80 3492.129 #> 61: 82 3471.066 #> 62: 83 3599.780 #> 63: 79 3501.372 #> 64: 76 3593.842 #> 65: 85 3588.259 #> 66: 89 3553.760 #> 67: 91 2151.522 #> 68: 81 3481.753 #> 69: 78 3513.014 #> 70: 87 3570.795 #> 71: 88 3563.106 #> 72: 77 3529.443 #> 73: 3 3599.295 #> 74: 86 3578.904 #> 75: 90 3529.605 #> 76: 2 3599.210 #> 77: 84 3596.381 #> 78: 1 3599.788 #> 79: 4 3595.377 #> 80: 9 3583.777 #> 81: 29 3558.408 #> 82: 18 3572.866 #> 83: 15 3583.955 #> 84: 21 3599.004 #> 85: 19 3567.117 #> 86: 16 3582.283 #> 87: 30 3550.130 #> 88: 17 3578.532 #> 89: 22 3599.427 #> 90: 13 3599.265 #> 91: 14 3595.019 #> chunk runtime
if (FALSE) { submitJobs(ids, reg = tmp) } # Group jobs into 10 chunks with similar runtime ids = est$runtimes[type == "estimated"] ids[, chunk := lpt(runtime, 10)]
#> job.id type runtime chunk #> 1: 1 estimated 1107.0568 4 #> 2: 2 estimated 1090.8508 9 #> 3: 3 estimated 338.2092 4 #> 4: 4 estimated 318.6349 8 #> 5: 5 estimated 317.3189 6 #> --- #> 446: 495 estimated 581.7197 2 #> 447: 496 estimated 1381.9162 9 #> 448: 497 estimated 1389.1659 2 #> 449: 498 estimated 614.0596 2 #> 450: 500 estimated 574.7851 1
print(ids[, list(runtime = sum(runtime)), by = chunk])
#> chunk runtime #> 1: 4 32227.40 #> 2: 9 32226.68 #> 3: 8 32231.22 #> 4: 6 32293.22 #> 5: 1 32226.47 #> 6: 3 32292.92 #> 7: 10 32227.16 #> 8: 5 32301.32 #> 9: 2 32301.36 #> 10: 7 32300.22