varDiff

matrixStats: Benchmark report

---

varDiff() benchmarks

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

Alternative methods

• N/A

Data type "integer"

Data

> rvector <- function(n, mode = c("logical", "double", "integer"), range = c(-100, +100), naProb = 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 (naProb > 0) 
+         x[sample(n, size = naProb * 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)
> data <- data[1:4]

Results

n=1000 vector

All elements

> x <- data[["n=1000"]]
> stats <- microbenchmark(varDiff = varDiff(x), var = var(x), diff = diff(x), unit = "ms")

Table: Benchmarking of varDiff(), var() and diff() 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
2	var	0.0316	0.0341	0.0417	0.0377	0.0520	0.0793
3	diff	0.0316	0.0352	0.0425	0.0389	0.0512	0.0874
1	varDiff	0.0423	0.0466	0.0609	0.0518	0.0722	0.3969

	expr	min	lq	mean	median	uq	max
2	var	1.000	1.000	1.000	1.000	1.0000	1.000
3	diff	1.000	1.034	1.020	1.031	0.9852	1.102
1	varDiff	1.341	1.367	1.461	1.372	1.3889	5.005
Figure: Benchmarking of varDiff(), var() and diff() on integer+n=1000 data. Outliers are displayed as crosses. Times are in milliseconds.

n=10000 vector

All elements

> x <- data[["n=10000"]]
> stats <- microbenchmark(varDiff = varDiff(x), var = var(x), diff = diff(x), unit = "ms")

Table: Benchmarking of varDiff(), var() and diff() 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
2	var	0.0982	0.1014	0.1233	0.1055	0.1551	0.2240
1	varDiff	0.1263	0.1290	0.1547	0.1343	0.1798	0.2487
3	diff	0.2110	0.2148	0.2565	0.2181	0.3134	0.4158

	expr	min	lq	mean	median	uq	max
2	var	1.000	1.000	1.000	1.000	1.000	1.000
1	varDiff	1.286	1.271	1.254	1.274	1.159	1.110
3	diff	2.149	2.118	2.079	2.067	2.020	1.856
Figure: Benchmarking of varDiff(), var() and diff() on integer+n=10000 data. Outliers are displayed as crosses. Times are in milliseconds.

n=100000 vector

All elements

> x <- data[["n=100000"]]
> stats <- microbenchmark(varDiff = varDiff(x), var = var(x), diff = diff(x), unit = "ms")

Table: Benchmarking of varDiff(), var() and diff() 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
2	var	0.7691	0.9649	1.212	1.213	1.428	1.901
1	varDiff	0.9878	1.0284	1.427	1.547	1.602	2.553
3	diff	2.0356	2.3825	3.122	2.985	3.344	13.797

	expr	min	lq	mean	median	uq	max
2	var	1.000	1.000	1.000	1.000	1.000	1.000
1	varDiff	1.284	1.066	1.177	1.275	1.122	1.343
3	diff	2.647	2.469	2.575	2.460	2.342	7.256
Figure: Benchmarking of varDiff(), var() and diff() on integer+n=100000 data. Outliers are displayed as crosses. Times are in milliseconds.

n=1000000 vector

All elements

> x <- data[["n=1000000"]]
> stats <- microbenchmark(varDiff = varDiff(x), var = var(x), diff = diff(x), unit = "ms")

Table: Benchmarking of varDiff(), var() and diff() 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
2	var	9.672	12.62	14.80	14.88	16.45	30.25
1	varDiff	11.899	15.06	19.30	18.38	21.26	36.62
3	diff	21.382	30.02	37.36	33.40	37.69	344.88

	expr	min	lq	mean	median	uq	max
2	var	1.000	1.000	1.000	1.000	1.000	1.00
1	varDiff	1.230	1.193	1.304	1.235	1.293	1.21
3	diff	2.211	2.378	2.525	2.245	2.292	11.40
Figure: Benchmarking of varDiff(), var() and diff() on integer+n=1000000 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), naProb = 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 (naProb > 0) 
+         x[sample(n, size = naProb * 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)
> data <- data[1:4]

Results

n=1000 vector

All elements

> x <- data[["n=1000"]]
> stats <- microbenchmark(varDiff = varDiff(x), var = var(x), diff = diff(x), unit = "ms")

Table: Benchmarking of varDiff(), var() and diff() 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
3	diff	0.0262	0.0316	0.0393	0.0346	0.0479	0.1132
2	var	0.0281	0.0316	0.0414	0.0370	0.0508	0.0662
1	varDiff	0.0397	0.0420	0.0545	0.0474	0.0664	0.2067

	expr	min	lq	mean	median	uq	max
3	diff	1.000	1.000	1.000	1.000	1.000	1.000
2	var	1.073	1.000	1.053	1.067	1.060	0.585
1	varDiff	1.515	1.329	1.385	1.367	1.385	1.827
Figure: Benchmarking of varDiff(), var() and diff() on double+n=1000 data. Outliers are displayed as crosses. Times are in milliseconds.

n=10000 vector

All elements

> x <- data[["n=10000"]]
> stats <- microbenchmark(varDiff = varDiff(x), var = var(x), diff = diff(x), unit = "ms")

Table: Benchmarking of varDiff(), var() and diff() 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
2	var	0.0820	0.0847	0.1035	0.0907	0.1313	0.2383
1	varDiff	0.1101	0.1141	0.1286	0.1166	0.1215	0.2029
3	diff	0.1532	0.1669	0.1956	0.1769	0.2412	0.3026

	expr	min	lq	mean	median	uq	max
2	var	1.000	1.000	1.000	1.000	1.0000	1.0000
1	varDiff	1.343	1.348	1.242	1.287	0.9252	0.8514
3	diff	1.869	1.970	1.890	1.951	1.8372	1.2698
Figure: Benchmarking of varDiff(), var() and diff() on double+n=10000 data. Outliers are displayed as crosses. Times are in milliseconds.

n=100000 vector

All elements

> x <- data[["n=100000"]]
> stats <- microbenchmark(varDiff = varDiff(x), var = var(x), diff = diff(x), unit = "ms")

Table: Benchmarking of varDiff(), var() and diff() 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
2	var	0.5998	0.6296	0.8676	0.9362	1.010	1.321
1	varDiff	0.7992	1.0149	1.2725	1.2948	1.508	2.005
3	diff	1.6207	2.1910	2.6907	2.4173	2.763	13.277

	expr	min	lq	mean	median	uq	max
2	var	1.000	1.000	1.000	1.000	1.000	1.000
1	varDiff	1.333	1.612	1.467	1.383	1.493	1.518
3	diff	2.702	3.480	3.101	2.582	2.737	10.050
Figure: Benchmarking of varDiff(), var() and diff() on double+n=100000 data. Outliers are displayed as crosses. Times are in milliseconds.

n=1000000 vector

All elements

> x <- data[["n=1000000"]]
> stats <- microbenchmark(varDiff = varDiff(x), var = var(x), diff = diff(x), unit = "ms")

Table: Benchmarking of varDiff(), var() and diff() 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
2	var	7.138	7.39	9.509	9.68	10.67	14.78
1	varDiff	10.347	12.24	16.218	15.50	17.09	35.92
3	diff	21.823	26.80	32.124	30.88	35.89	46.96

	expr	min	lq	mean	median	uq	max
2	var	1.000	1.000	1.000	1.000	1.000	1.000
1	varDiff	1.450	1.656	1.706	1.601	1.601	2.430
3	diff	3.057	3.627	3.378	3.190	3.362	3.177
Figure: Benchmarking of varDiff(), var() and diff() on double+n=1000000 data. Outliers are displayed as crosses. Times are in milliseconds.

Appendix

Session information

R Under development (unstable) (2015-02-27 r67909)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 7 x64 (build 7601) Service Pack 1

locale:
[1] LC_COLLATE=English_United States.1252 
[2] LC_CTYPE=English_United States.1252   
[3] LC_MONETARY=English_United States.1252
[4] LC_NUMERIC=C                          
[5] LC_TIME=English_United States.1252    

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

other attached packages:
[1] markdown_0.7.7          microbenchmark_1.4-2    matrixStats_0.14.0-9000
[4] ggplot2_1.0.0           knitr_1.9.3             R.devices_2.13.0       
[7] R.utils_2.0.0           R.oo_1.19.0             R.methodsS3_1.7.0      

loaded via a namespace (and not attached):
 [1] Rcpp_0.11.4           GenomeInfoDb_1.3.13   formatR_1.0.3        
 [4] plyr_1.8.1            base64enc_0.1-3       tools_3.2.0          
 [7] digest_0.6.8          RSQLite_1.0.0         annotate_1.45.2      
[10] evaluate_0.5.7        gtable_0.1.2          R.cache_0.11.1-9000  
[13] lattice_0.20-30       DBI_0.3.1             parallel_3.2.0       
[16] mvtnorm_1.0-2         proto_0.3-10          R.rsp_0.20.0         
[19] genefilter_1.49.2     stringr_0.6.2         IRanges_2.1.41       
[22] S4Vectors_0.5.21      stats4_3.2.0          grid_3.2.0           
[25] Biobase_2.27.2        AnnotationDbi_1.29.17 XML_3.98-1.1         
[28] survival_2.38-1       multcomp_1.3-9        TH.data_1.0-6        
[31] reshape2_1.4.1        scales_0.2.4          MASS_7.3-39          
[34] splines_3.2.0         BiocGenerics_0.13.6   xtable_1.8-0         
[37] mime_0.2.1            colorspace_1.2-4      labeling_0.3         
[40] sandwich_2.3-2        munsell_0.4.2         Cairo_1.5-6          
[43] zoo_1.7-12           

Total processing time was 26.27 secs.

Reproducibility

To reproduce this report, do:

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

---

Copyright Henrik Bengtsson. Last updated on 2015-03-02 17:38:42 (-0800 UTC). Powered by RSP.

<script> var link = document.createElement('link'); link.rel = 'icon'; link.href = "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACAAAAAgCAMAAABEpIrGAAAADFBMVEX9/v0AAP/9/v3//wBEQjoBAAAABHRSTlP//wD//gy7CwAAAGJJREFUOI3N0rESwCAIA9Ag///PXdoiBk0HhmbNO49DMETQCexNCSyFgdlGoO5DYOr9ThLgPosA7osIQP0sHuDOog8UI/ALa988wzdwXJRctf4s+d36YPTJ6aMd8ux3+QO4ABTtB85yDAh9AAAAAElFTkSuQmCC" document.getElementsByTagName('head')[0].appendChild(link); </script>