count

matrixStats: Benchmark report

---

count() benchmarks

This report benchmark the performance of count() against alternative methods.

Alternative methods

• sum(x == value)

Data type "integer"

Data

> rvector <- function(n, mode = c("logical", "double", "integer"), range = c(-100, +100), na_prob = 0) {
+     mode <- match.arg(mode)
+     if (mode == "logical") {
+         x <- sample(c(FALSE, TRUE), size = n, replace = TRUE)
+     }     else {
+         x <- runif(n, min = range[1], max = range[2])
+     }
+     storage.mode(x) <- mode
+     if (na_prob > 0) 
+         x[sample(n, size = na_prob * n)] <- NA
+     x
+ }
> rvectors <- function(scale = 10, seed = 1, ...) {
+     set.seed(seed)
+     data <- list()
+     data[[1]] <- rvector(n = scale * 100, ...)
+     data[[2]] <- rvector(n = scale * 1000, ...)
+     data[[3]] <- rvector(n = scale * 10000, ...)
+     data[[4]] <- rvector(n = scale * 1e+05, ...)
+     data[[5]] <- rvector(n = scale * 1e+06, ...)
+     names(data) <- sprintf("n = %d", sapply(data, FUN = length))
+     data
+ }
> data <- rvectors(mode = mode)

Results

n = 1000 vector

> x <- data[["n = 1000"]]
> gc()
           used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells  3231175 172.6    5709258 305.0  5709258 305.0
Vcells 33430019 255.1   59837990 456.6 57084605 435.6
> stats <- microbenchmark(count = count(x, value), `sum(x == value)` = sum(x == value), unit = "ms")

Table: Benchmarking of count() and sum(x == value)() on integer+n = 1000 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	count	0.001668	0.001766	0.0020640	0.0018505	0.0019250	0.021897
2	sum(x == value)	0.002571	0.002667	0.0028124	0.0027235	0.0027855	0.011185

	expr	min	lq	mean	median	uq	max
1	count	1.000000	1.000000	1.000000	1.000000	1.000000	1.0000000
2	sum(x == value)	1.541367	1.510193	1.362586	1.471764	1.447013	0.5108006

Figure: Benchmarking of count() and sum(x == value)() on integer+n = 1000 data. Outliers are displayed as crosses. Times are in milliseconds.

n = 10000 vector

> x <- data[["n = 10000"]]
> gc()
           used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells  3228942 172.5    5709258 305.0  5709258 305.0
Vcells 11794763  90.0   38296314 292.2 57084605 435.6
> stats <- microbenchmark(count = count(x, value), `sum(x == value)` = sum(x == value), unit = "ms")

Table: Benchmarking of count() and sum(x == value)() on integer+n = 10000 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	count	0.001685	0.001856	0.0022827	0.0020615	0.0023060	0.020644
2	sum(x == value)	0.022238	0.022466	0.0229967	0.0225655	0.0227155	0.031721

	expr	min	lq	mean	median	uq	max
1	count	1.00000	1.00000	1.00000	1.00000	1.000000	1.000000
2	sum(x == value)	13.19763	12.10453	10.07446	10.94616	9.850607	1.536572

Figure: Benchmarking of count() and sum(x == value)() on integer+n = 10000 data. Outliers are displayed as crosses. Times are in milliseconds.

n = 100000 vector

> x <- data[["n = 100000"]]
> gc()
           used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells  3229005 172.5    5709258 305.0  5709258 305.0
Vcells 11794805  90.0   38296314 292.2 57084605 435.6
> stats <- microbenchmark(count = count(x, value), `sum(x == value)` = sum(x == value), unit = "ms")

Table: Benchmarking of count() and sum(x == value)() on integer+n = 100000 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	count	0.001679	0.0019050	0.0026980	0.002224	0.0028375	0.029385
2	sum(x == value)	0.206338	0.2172605	0.2189826	0.218022	0.2197080	0.244302

	expr	min	lq	mean	median	uq	max
1	count	1.0000	1.0000	1.00000	1.00000	1.00000	1.000000
2	sum(x == value)	122.8934	114.0475	81.16329	98.03147	77.43013	8.313834

Figure: Benchmarking of count() and sum(x == value)() on integer+n = 100000 data. Outliers are displayed as crosses. Times are in milliseconds.

n = 1000000 vector

> x <- data[["n = 1000000"]]
> gc()
           used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells  3229068 172.5    5709258 305.0  5709258 305.0
Vcells 11795360  90.0   38296314 292.2 57084605 435.6
> stats <- microbenchmark(count = count(x, value), `sum(x == value)` = sum(x == value), unit = "ms")

Table: Benchmarking of count() and sum(x == value)() on integer+n = 1000000 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	count	0.001668	0.002062	0.0092437	0.0088085	0.016791	0.03742
2	sum(x == value)	2.738796	3.213318	3.4531879	3.2412525	3.285109	15.69834

	expr	min	lq	mean	median	uq	max
1	count	1.000	1.00	1.0000	1.0000	1.000	1.0000
2	sum(x == value)	1641.964	1558.35	373.5716	367.9687	195.647	419.5172

Figure: Benchmarking of count() and sum(x == value)() on integer+n = 1000000 data. Outliers are displayed as crosses. Times are in milliseconds.

n = 10000000 vector

> x <- data[["n = 10000000"]]
> gc()
           used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells  3229131 172.5    5709258 305.0  5709258 305.0
Vcells 11795402  90.0   38296314 292.2 57084605 435.6
> stats <- microbenchmark(count = count(x, value), `sum(x == value)` = sum(x == value), unit = "ms")

Table: Benchmarking of count() and sum(x == value)() on integer+n = 10000000 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	count	0.001711	0.002137	0.0126709	0.0034835	0.0227455	0.052068
2	sum(x == value)	31.990870	32.284979	36.0097863	32.8202760	34.2459520	55.251011

	expr	min	lq	mean	median	uq	max
1	count	1.00	1.00	1.000	1.000	1.000	1.000
2	sum(x == value)	18697.18	15107.62	2841.939	9421.638	1505.614	1061.132

Figure: Benchmarking of count() and sum(x == value)() on integer+n = 10000000 data. Outliers are displayed as crosses. Times are in milliseconds.

Data type "double"

Data

> rvector <- function(n, mode = c("logical", "double", "integer"), range = c(-100, +100), na_prob = 0) {
+     mode <- match.arg(mode)
+     if (mode == "logical") {
+         x <- sample(c(FALSE, TRUE), size = n, replace = TRUE)
+     }     else {
+         x <- runif(n, min = range[1], max = range[2])
+     }
+     storage.mode(x) <- mode
+     if (na_prob > 0) 
+         x[sample(n, size = na_prob * n)] <- NA
+     x
+ }
> rvectors <- function(scale = 10, seed = 1, ...) {
+     set.seed(seed)
+     data <- list()
+     data[[1]] <- rvector(n = scale * 100, ...)
+     data[[2]] <- rvector(n = scale * 1000, ...)
+     data[[3]] <- rvector(n = scale * 10000, ...)
+     data[[4]] <- rvector(n = scale * 1e+05, ...)
+     data[[5]] <- rvector(n = scale * 1e+06, ...)
+     names(data) <- sprintf("n = %d", sapply(data, FUN = length))
+     data
+ }
> data <- rvectors(mode = mode)

Results

n = 1000 vector

> x <- data[["n = 1000"]]
> gc()
           used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells  3229194 172.5    5709258 305.0  5709258 305.0
Vcells 17351273 132.4   38296314 292.2 57084605 435.6
> stats <- microbenchmark(count = count(x, value), `sum(x == value)` = sum(x == value), unit = "ms")

Table: Benchmarking of count() and sum(x == value)() on double+n = 1000 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	count	0.001683	0.0017205	0.0023145	0.0018620	0.0020020	0.043659
2	sum(x == value)	0.002109	0.0022205	0.0024306	0.0022905	0.0023675	0.015180

	expr	min	lq	mean	median	uq	max
1	count	1.000000	1.000000	1.000000	1.000000	1.000000	1.0000000
2	sum(x == value)	1.253119	1.290613	1.050184	1.230129	1.182567	0.3476946

Figure: Benchmarking of count() and sum(x == value)() on double+n = 1000 data. Outliers are displayed as crosses. Times are in milliseconds.

n = 10000 vector

> x <- data[["n = 10000"]]
> gc()
           used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells  3229257 172.5    5709258 305.0  5709258 305.0
Vcells 17351314 132.4   38296314 292.2 57084605 435.6
> stats <- microbenchmark(count = count(x, value), `sum(x == value)` = sum(x == value), unit = "ms")

Table: Benchmarking of count() and sum(x == value)() on double+n = 10000 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	count	0.001677	0.0019015	0.0025086	0.0021490	0.0023955	0.038174
2	sum(x == value)	0.017422	0.0176605	0.0182435	0.0177825	0.0179710	0.028087

	expr	min	lq	mean	median	uq	max
1	count	1.00000	1.000000	1.000000	1.000000	1.000000	1.0000000
2	sum(x == value)	10.38879	9.287668	7.272254	8.274779	7.501983	0.7357626

Figure: Benchmarking of count() and sum(x == value)() on double+n = 10000 data. Outliers are displayed as crosses. Times are in milliseconds.

n = 100000 vector

> x <- data[["n = 100000"]]
> gc()
           used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells  3229320 172.5    5709258 305.0  5709258 305.0
Vcells 17351639 132.4   38296314 292.2 57084605 435.6
> stats <- microbenchmark(count = count(x, value), `sum(x == value)` = sum(x == value), unit = "ms")

Table: Benchmarking of count() and sum(x == value)() on double+n = 100000 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	count	0.001681	0.0018845	0.0026881	0.0022020	0.0028000	0.028854
2	sum(x == value)	0.167430	0.1688190	0.1710085	0.1694525	0.1707535	0.205628

	expr	min	lq	mean	median	uq	max
1	count	1.00000	1.00000	1.0000	1.00000	1.00000	1.000000
2	sum(x == value)	99.60143	89.58291	63.6164	76.95391	60.98339	7.126499

Figure: Benchmarking of count() and sum(x == value)() on double+n = 100000 data. Outliers are displayed as crosses. Times are in milliseconds.

n = 1000000 vector

> x <- data[["n = 1000000"]]
> gc()
           used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells  3229383 172.5    5709258 305.0  5709258 305.0
Vcells 17352014 132.4   38296314 292.2 57084605 435.6
> stats <- microbenchmark(count = count(x, value), `sum(x == value)` = sum(x == value), unit = "ms")

Table: Benchmarking of count() and sum(x == value)() on double+n = 1000000 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	count	0.001665	0.0020285	0.0078366	0.007264	0.012295	0.025685
2	sum(x == value)	1.730855	2.7169495	3.0016203	2.744386	2.806246	14.117200

	expr	min	lq	mean	median	uq	max
1	count	1.000	1.000	1.0000	1.0000	1.0000	1.0000
2	sum(x == value)	1039.553	1339.388	383.0278	377.8064	228.2429	549.6282

Figure: Benchmarking of count() and sum(x == value)() on double+n = 1000000 data. Outliers are displayed as crosses. Times are in milliseconds.

n = 10000000 vector

> x <- data[["n = 10000000"]]
> gc()
           used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells  3229446 172.5    5709258 305.0  5709258 305.0
Vcells 17352056 132.4   38296314 292.2 57084605 435.6
> stats <- microbenchmark(count = count(x, value), `sum(x == value)` = sum(x == value), unit = "ms")

Table: Benchmarking of count() and sum(x == value)() on double+n = 10000000 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	count	0.00170	0.0021225	0.0117215	0.0030785	0.0215545	0.036833
2	sum(x == value)	27.04751	27.3330855	30.7959116	27.8625050	28.7366065	44.825225

	expr	min	lq	mean	median	uq	max
1	count	1.0	1.00	1.000	1.000	1.000	1.000
2	sum(x == value)	15910.3	12877.78	2627.301	9050.676	1333.207	1216.985

Figure: Benchmarking of count() and sum(x == value)() on double+n = 10000000 data. Outliers are displayed as crosses. Times are in milliseconds.

Appendix

Session information

R version 3.6.1 Patched (2019-08-27 r77078)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 18.04.3 LTS

Matrix products: default
BLAS:   /home/hb/software/R-devel/R-3-6-branch/lib/R/lib/libRblas.so
LAPACK: /home/hb/software/R-devel/R-3-6-branch/lib/R/lib/libRlapack.so

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
 [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
 [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
 [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
 [9] LC_ADDRESS=C               LC_TELEPHONE=C            
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] microbenchmark_1.4-6    matrixStats_0.55.0-9000 ggplot2_3.2.1          
[4] knitr_1.24              R.devices_2.16.0        R.utils_2.9.0          
[7] R.oo_1.22.0             R.methodsS3_1.7.1       history_0.0.0-9002     

loaded via a namespace (and not attached):
 [1] Biobase_2.45.0       bit64_0.9-7          splines_3.6.1       
 [4] network_1.15         assertthat_0.2.1     highr_0.8           
 [7] stats4_3.6.1         blob_1.2.0           robustbase_0.93-5   
[10] pillar_1.4.2         RSQLite_2.1.2        backports_1.1.4     
[13] lattice_0.20-38      glue_1.3.1           digest_0.6.20       
[16] colorspace_1.4-1     sandwich_2.5-1       Matrix_1.2-17       
[19] XML_3.98-1.20        lpSolve_5.6.13.3     pkgconfig_2.0.2     
[22] genefilter_1.66.0    purrr_0.3.2          ergm_3.10.4         
[25] xtable_1.8-4         mvtnorm_1.0-11       scales_1.0.0        
[28] tibble_2.1.3         annotate_1.62.0      IRanges_2.18.2      
[31] TH.data_1.0-10       withr_2.1.2          BiocGenerics_0.30.0 
[34] lazyeval_0.2.2       mime_0.7             survival_2.44-1.1   
[37] magrittr_1.5         crayon_1.3.4         statnet.common_4.3.0
[40] memoise_1.1.0        laeken_0.5.0         R.cache_0.13.0      
[43] MASS_7.3-51.4        R.rsp_0.43.1         tools_3.6.1         
[46] multcomp_1.4-10      S4Vectors_0.22.1     trust_0.1-7         
[49] munsell_0.5.0        AnnotationDbi_1.46.1 compiler_3.6.1      
[52] rlang_0.4.0          grid_3.6.1           RCurl_1.95-4.12     
[55] cwhmisc_6.6          rappdirs_0.3.1       labeling_0.3        
[58] bitops_1.0-6         base64enc_0.1-3      boot_1.3-23         
[61] gtable_0.3.0         codetools_0.2-16     DBI_1.0.0           
[64] markdown_1.1         R6_2.4.0             zoo_1.8-6           
[67] dplyr_0.8.3          bit_1.1-14           zeallot_0.1.0       
[70] parallel_3.6.1       Rcpp_1.0.2           vctrs_0.2.0         
[73] DEoptimR_1.0-8       tidyselect_0.2.5     xfun_0.9            
[76] coda_0.19-3         

Total processing time was 19.52 secs.

Reproducibility

To reproduce this report, do:

html <- matrixStats:::benchmark('count')

---

Copyright Henrik Bengtsson. Last updated on 2019-09-10 20:57:56 (-0700 UTC). Powered by RSP.

<script> var link = document.createElement('link'); link.rel = 'icon'; link.href = "data:image/png;base64,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" document.getElementsByTagName('head')[0].appendChild(link); </script>