colRowAnyMissings_subset

matrixStats: Benchmark report

---

colAnyMissings() and rowAnyMissings() benchmarks on subsetted computation

This report benchmark the performance of colAnyMissings() and rowAnyMissings() on subsetted computation.

Data type "integer"

Data

> rmatrix <- function(nrow, ncol, mode = c("logical", "double", "integer", "index"), range = c(-100, 
+     +100), na_prob = 0) {
+     mode <- match.arg(mode)
+     n <- nrow * ncol
+     if (mode == "logical") {
+         x <- sample(c(FALSE, TRUE), size = n, replace = TRUE)
+     }     else if (mode == "index") {
+         x <- seq_len(n)
+         mode <- "integer"
+     }     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
+     dim(x) <- c(nrow, ncol)
+     x
+ }
> rmatrices <- function(scale = 10, seed = 1, ...) {
+     set.seed(seed)
+     data <- list()
+     data[[1]] <- rmatrix(nrow = scale * 1, ncol = scale * 1, ...)
+     data[[2]] <- rmatrix(nrow = scale * 10, ncol = scale * 10, ...)
+     data[[3]] <- rmatrix(nrow = scale * 100, ncol = scale * 1, ...)
+     data[[4]] <- t(data[[3]])
+     data[[5]] <- rmatrix(nrow = scale * 10, ncol = scale * 100, ...)
+     data[[6]] <- t(data[[5]])
+     names(data) <- sapply(data, FUN = function(x) paste(dim(x), collapse = "x"))
+     data
+ }
> data <- rmatrices(mode = mode)

Results

10x10 matrix

> X <- data[["10x10"]]
> rows <- sample.int(nrow(X), size = nrow(X) * 0.7)
> cols <- sample.int(ncol(X), size = ncol(X) * 0.7)
> X_S <- X[rows, cols]
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3065936 163.8    5709258 305.0  5709258 305.0
Vcells 5341036  40.8   22267496 169.9 56666022 432.4
> colStats <- microbenchmark(colAnyMissings_X_S = colAnyMissings(X_S), `colAnyMissings(X, rows, cols)` = colAnyMissings(X, 
+     rows = rows, cols = cols), `colAnyMissings(X[rows, cols])` = colAnyMissings(X[rows, cols]), unit = "ms")
> X <- t(X)
> X_S <- t(X_S)
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3065230 163.8    5709258 305.0  5709258 305.0
Vcells 5339141  40.8   22267496 169.9 56666022 432.4
> rowStats <- microbenchmark(rowAnyMissings_X_S = rowAnyMissings(X_S), `rowAnyMissings(X, cols, rows)` = rowAnyMissings(X, 
+     rows = cols, cols = rows), `rowAnyMissings(X[cols, rows])` = rowAnyMissings(X[cols, rows]), unit = "ms")

Table: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on integer+10x10 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	0.001909	0.0019595	0.0037601	0.0020160	0.0021555	0.170367
2	colAnyMissings(X, rows, cols)	0.002069	0.0021475	0.0022611	0.0021930	0.0023560	0.003318
3	colAnyMissings(X[rows, cols])	0.002522	0.0027580	0.0029657	0.0028885	0.0030180	0.007057

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.0000000	1.000000	1.000000	1.0000000
2	colAnyMissings(X, rows, cols)	1.083813	1.095943	0.6013409	1.087798	1.093018	0.0194756
3	colAnyMissings(X[rows, cols])	1.321111	1.407502	0.7887252	1.432788	1.400139	0.0414223

Table: Benchmarking of rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on integer+10x10 data (transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	0.001856	0.0019250	0.0020304	0.0019705	0.0021025	0.003570
2	rowAnyMissings(X, cols, rows)	0.002044	0.0021135	0.0041019	0.0021665	0.0023205	0.188377
3	rowAnyMissings(X[cols, rows])	0.002513	0.0026915	0.0029238	0.0028200	0.0029870	0.006586

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	rowAnyMissings(X, cols, rows)	1.101293	1.097922	2.020217	1.099467	1.103686	52.766667
3	rowAnyMissings(X[cols, rows])	1.353987	1.398182	1.439971	1.431109	1.420690	1.844818

Figure: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on integer+10x10 data as well as rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on the same data transposed. Outliers are displayed as crosses. Times are in milliseconds.

Table: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on integer+10x10 data (original and transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
2	rowAnyMissings_X_S	1.856	1.9250	2.03043	1.9705	2.1025	3.570
1	colAnyMissings_X_S	1.909	1.9595	3.76008	2.0160	2.1555	170.367

	expr	min	lq	mean	median	uq	max
2	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.00000
1	colAnyMissings_X_S	1.028556	1.017922	1.851864	1.023091	1.025208	47.72185

Figure: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on integer+10x10 data (original and transposed). Outliers are displayed as crosses. Times are in milliseconds.

100x100 matrix

> X <- data[["100x100"]]
> rows <- sample.int(nrow(X), size = nrow(X) * 0.7)
> cols <- sample.int(ncol(X), size = ncol(X) * 0.7)
> X_S <- X[rows, cols]
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3064172 163.7    5709258 305.0  5709258 305.0
Vcells 5173566  39.5   22267496 169.9 56666022 432.4
> colStats <- microbenchmark(colAnyMissings_X_S = colAnyMissings(X_S), `colAnyMissings(X, rows, cols)` = colAnyMissings(X, 
+     rows = rows, cols = cols), `colAnyMissings(X[rows, cols])` = colAnyMissings(X[rows, cols]), unit = "ms")
> X <- t(X)
> X_S <- t(X_S)
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3064166 163.7    5709258 305.0  5709258 305.0
Vcells 5178649  39.6   22267496 169.9 56666022 432.4
> rowStats <- microbenchmark(rowAnyMissings_X_S = rowAnyMissings(X_S), `rowAnyMissings(X, cols, rows)` = rowAnyMissings(X, 
+     rows = cols, cols = rows), `rowAnyMissings(X[cols, rows])` = rowAnyMissings(X[cols, rows]), unit = "ms")

Table: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on integer+100x100 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	0.003790	0.0041370	0.0043720	0.0043335	0.0044730	0.008098
2	colAnyMissings(X, rows, cols)	0.005891	0.0061995	0.0065557	0.0064130	0.0066940	0.010122
3	colAnyMissings(X[rows, cols])	0.011714	0.0120525	0.0129000	0.0122175	0.0123705	0.064254

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	colAnyMissings(X, rows, cols)	1.554354	1.498550	1.499486	1.479866	1.496535	1.249938
3	colAnyMissings(X[rows, cols])	3.090765	2.913343	2.950638	2.819315	2.765594	7.934552

Table: Benchmarking of rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on integer+100x100 data (transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	0.005676	0.0060965	0.0062394	0.0062255	0.0063330	0.008932
2	rowAnyMissings(X, cols, rows)	0.006729	0.0070995	0.0072964	0.0072915	0.0074340	0.008109
3	rowAnyMissings(X[cols, rows])	0.013574	0.0138655	0.0147486	0.0140695	0.0142865	0.065044

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.0000000
2	rowAnyMissings(X, cols, rows)	1.185518	1.164521	1.169415	1.171231	1.173851	0.9078594
3	rowAnyMissings(X[cols, rows])	2.391473	2.274338	2.363802	2.259979	2.255882	7.2821317

Figure: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on integer+100x100 data as well as rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on the same data transposed. Outliers are displayed as crosses. Times are in milliseconds.

Table: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on integer+100x100 data (original and transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	3.790	4.1370	4.37195	4.3335	4.473	8.098
2	rowAnyMissings_X_S	5.676	6.0965	6.23936	6.2255	6.333	8.932

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	rowAnyMissings_X_S	1.497625	1.473652	1.427134	1.436599	1.415828	1.102988

Figure: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on integer+100x100 data (original and transposed). Outliers are displayed as crosses. Times are in milliseconds.

1000x10 matrix

> X <- data[["1000x10"]]
> rows <- sample.int(nrow(X), size = nrow(X) * 0.7)
> cols <- sample.int(ncol(X), size = ncol(X) * 0.7)
> X_S <- X[rows, cols]
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3064927 163.7    5709258 305.0  5709258 305.0
Vcells 5177649  39.6   22267496 169.9 56666022 432.4
> colStats <- microbenchmark(colAnyMissings_X_S = colAnyMissings(X_S), `colAnyMissings(X, rows, cols)` = colAnyMissings(X, 
+     rows = rows, cols = cols), `colAnyMissings(X[rows, cols])` = colAnyMissings(X[rows, cols]), unit = "ms")
> X <- t(X)
> X_S <- t(X_S)
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3064918 163.7    5709258 305.0  5709258 305.0
Vcells 5182727  39.6   22267496 169.9 56666022 432.4
> rowStats <- microbenchmark(rowAnyMissings_X_S = rowAnyMissings(X_S), `rowAnyMissings(X, cols, rows)` = rowAnyMissings(X, 
+     rows = cols, cols = rows), `rowAnyMissings(X[cols, rows])` = rowAnyMissings(X[cols, rows]), unit = "ms")

Table: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on integer+1000x10 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	0.003337	0.0034765	0.0036353	0.0035440	0.0037090	0.007212
2	colAnyMissings(X, rows, cols)	0.005597	0.0057760	0.0063044	0.0058625	0.0059715	0.047710
3	colAnyMissings(X[rows, cols])	0.011065	0.0112440	0.0116576	0.0114140	0.0115550	0.021089

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	colAnyMissings(X, rows, cols)	1.677255	1.661441	1.734219	1.654204	1.610003	6.615363
3	colAnyMissings(X[rows, cols])	3.315853	3.234287	3.206809	3.220655	3.115395	2.924154

Table: Benchmarking of rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on integer+1000x10 data (transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	0.005047	0.005165	0.0057156	0.0052435	0.0053455	0.048233
2	rowAnyMissings(X, cols, rows)	0.007300	0.007551	0.0078297	0.0076545	0.0078965	0.020284
3	rowAnyMissings(X[cols, rows])	0.013611	0.013890	0.0144229	0.0140400	0.0142650	0.031846

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.0000000
2	rowAnyMissings(X, cols, rows)	1.446404	1.461955	1.369894	1.459807	1.477224	0.4205420
3	rowAnyMissings(X[cols, rows])	2.696850	2.689255	2.523438	2.677601	2.668600	0.6602534

Figure: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on integer+1000x10 data as well as rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on the same data transposed. Outliers are displayed as crosses. Times are in milliseconds.

Table: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on integer+1000x10 data (original and transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	3.337	3.4765	3.63528	3.5440	3.7090	7.212
2	rowAnyMissings_X_S	5.047	5.1650	5.71556	5.2435	5.3455	48.233

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.00000	1.000000	1.000000	1.000000	1.000000
2	rowAnyMissings_X_S	1.512436	1.48569	1.572248	1.479543	1.441224	6.687881

Figure: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on integer+1000x10 data (original and transposed). Outliers are displayed as crosses. Times are in milliseconds.

10x1000 matrix

> X <- data[["10x1000"]]
> rows <- sample.int(nrow(X), size = nrow(X) * 0.7)
> cols <- sample.int(ncol(X), size = ncol(X) * 0.7)
> X_S <- X[rows, cols]
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3065130 163.7    5709258 305.0  5709258 305.0
Vcells 5178556  39.6   22267496 169.9 56666022 432.4
> colStats <- microbenchmark(colAnyMissings_X_S = colAnyMissings(X_S), `colAnyMissings(X, rows, cols)` = colAnyMissings(X, 
+     rows = rows, cols = cols), `colAnyMissings(X[rows, cols])` = colAnyMissings(X[rows, cols]), unit = "ms")
> X <- t(X)
> X_S <- t(X_S)
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3065124 163.7    5709258 305.0  5709258 305.0
Vcells 5183639  39.6   22267496 169.9 56666022 432.4
> rowStats <- microbenchmark(rowAnyMissings_X_S = rowAnyMissings(X_S), `rowAnyMissings(X, cols, rows)` = rowAnyMissings(X, 
+     rows = cols, cols = rows), `rowAnyMissings(X[cols, rows])` = rowAnyMissings(X[cols, rows]), unit = "ms")

Table: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on integer+10x1000 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	0.005520	0.005975	0.0064180	0.0063365	0.0066215	0.010772
2	colAnyMissings(X, rows, cols)	0.008137	0.008464	0.0095423	0.0087120	0.0090540	0.054838
3	colAnyMissings(X[rows, cols])	0.014095	0.014756	0.0155108	0.0150345	0.0155315	0.027018

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	colAnyMissings(X, rows, cols)	1.474094	1.416569	1.486790	1.374891	1.367364	5.090791
3	colAnyMissings(X[rows, cols])	2.553442	2.469623	2.416756	2.372682	2.345617	2.508169

Table: Benchmarking of rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on integer+10x1000 data (transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	0.005640	0.0059070	0.0063388	0.0061085	0.0062825	0.023325
2	rowAnyMissings(X, cols, rows)	0.007668	0.0081840	0.0083983	0.0083160	0.0085730	0.009478
3	rowAnyMissings(X[cols, rows])	0.012934	0.0132615	0.0136877	0.0134640	0.0137020	0.026768

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.0000000
2	rowAnyMissings(X, cols, rows)	1.359574	1.385475	1.324898	1.361382	1.364584	0.4063451
3	rowAnyMissings(X[cols, rows])	2.293262	2.245048	2.159350	2.204142	2.180979	1.1476099

Figure: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on integer+10x1000 data as well as rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on the same data transposed. Outliers are displayed as crosses. Times are in milliseconds.

Table: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on integer+10x1000 data (original and transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
2	rowAnyMissings_X_S	5.64	5.907	6.33882	6.1085	6.2825	23.325
1	colAnyMissings_X_S	5.52	5.975	6.41804	6.3365	6.6215	10.772

	expr	min	lq	mean	median	uq	max
2	rowAnyMissings_X_S	1.0000000	1.000000	1.000000	1.000000	1.000000	1.0000000
1	colAnyMissings_X_S	0.9787234	1.011512	1.012498	1.037325	1.053959	0.4618221

Figure: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on integer+10x1000 data (original and transposed). Outliers are displayed as crosses. Times are in milliseconds.

100x1000 matrix

> X <- data[["100x1000"]]
> rows <- sample.int(nrow(X), size = nrow(X) * 0.7)
> cols <- sample.int(ncol(X), size = ncol(X) * 0.7)
> X_S <- X[rows, cols]
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3065329 163.8    5709258 305.0  5709258 305.0
Vcells 5201233  39.7   22267496 169.9 56666022 432.4
> colStats <- microbenchmark(colAnyMissings_X_S = colAnyMissings(X_S), `colAnyMissings(X, rows, cols)` = colAnyMissings(X, 
+     rows = rows, cols = cols), `colAnyMissings(X[rows, cols])` = colAnyMissings(X[rows, cols]), unit = "ms")
> X <- t(X)
> X_S <- t(X_S)
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3065323 163.8    5709258 305.0  5709258 305.0
Vcells 5251316  40.1   22267496 169.9 56666022 432.4
> rowStats <- microbenchmark(rowAnyMissings_X_S = rowAnyMissings(X_S), `rowAnyMissings(X, cols, rows)` = rowAnyMissings(X, 
+     rows = cols, cols = rows), `rowAnyMissings(X[cols, rows])` = rowAnyMissings(X[cols, rows]), unit = "ms")

Table: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on integer+100x1000 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	0.017729	0.0180670	0.0185983	0.0182870	0.018740	0.026048
2	colAnyMissings(X, rows, cols)	0.039803	0.0402135	0.0414919	0.0404055	0.040672	0.131804
3	colAnyMissings(X[rows, cols])	0.089306	0.0901435	0.0912248	0.0905265	0.091298	0.109593

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.00000	1.000000	1.000000
2	colAnyMissings(X, rows, cols)	2.245079	2.225798	2.230946	2.20952	2.170331	5.060043
3	colAnyMissings(X[rows, cols])	5.037284	4.989401	4.905000	4.95032	4.871825	4.207348

Table: Benchmarking of rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on integer+100x1000 data (transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	0.029521	0.029851	0.0309257	0.0301030	0.0305360	0.068836
2	rowAnyMissings(X, cols, rows)	0.047036	0.048007	0.0486352	0.0485220	0.0488455	0.061143
3	rowAnyMissings(X[cols, rows])	0.092687	0.093354	0.0947319	0.0936185	0.0940835	0.155660

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.0000000
2	rowAnyMissings(X, cols, rows)	1.593306	1.608221	1.572648	1.611866	1.599604	0.8882416
3	rowAnyMissings(X[cols, rows])	3.139697	3.127332	3.063210	3.109939	3.081068	2.2613168

Figure: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on integer+100x1000 data as well as rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on the same data transposed. Outliers are displayed as crosses. Times are in milliseconds.

Table: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on integer+100x1000 data (original and transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	17.729	18.067	18.59834	18.287	18.740	26.048
2	rowAnyMissings_X_S	29.521	29.851	30.92570	30.103	30.536	68.836

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.00000	1.000000	1.000000	1.00000
2	rowAnyMissings_X_S	1.665125	1.652239	1.66282	1.646142	1.629456	2.64266

Figure: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on integer+100x1000 data (original and transposed). Outliers are displayed as crosses. Times are in milliseconds.

1000x100 matrix

> X <- data[["1000x100"]]
> rows <- sample.int(nrow(X), size = nrow(X) * 0.7)
> cols <- sample.int(ncol(X), size = ncol(X) * 0.7)
> X_S <- X[rows, cols]
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3065545 163.8    5709258 305.0  5709258 305.0
Vcells 5202044  39.7   22267496 169.9 56666022 432.4
> colStats <- microbenchmark(colAnyMissings_X_S = colAnyMissings(X_S), `colAnyMissings(X, rows, cols)` = colAnyMissings(X, 
+     rows = rows, cols = cols), `colAnyMissings(X[rows, cols])` = colAnyMissings(X[rows, cols]), unit = "ms")
> X <- t(X)
> X_S <- t(X_S)
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3065539 163.8    5709258 305.0  5709258 305.0
Vcells 5252127  40.1   22267496 169.9 56666022 432.4
> rowStats <- microbenchmark(rowAnyMissings_X_S = rowAnyMissings(X_S), `rowAnyMissings(X, cols, rows)` = rowAnyMissings(X, 
+     rows = cols, cols = rows), `rowAnyMissings(X[cols, rows])` = rowAnyMissings(X[cols, rows]), unit = "ms")

Table: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on integer+1000x100 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	0.016552	0.0170740	0.0175829	0.0172730	0.0174835	0.028990
2	colAnyMissings(X, rows, cols)	0.034511	0.0349505	0.0356907	0.0353990	0.0356475	0.066961
3	colAnyMissings(X[rows, cols])	0.079512	0.0805000	0.0822047	0.0808285	0.0811980	0.174185

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	colAnyMissings(X, rows, cols)	2.085005	2.047001	2.029856	2.049383	2.038922	2.309797
3	colAnyMissings(X[rows, cols])	4.803770	4.714771	4.675273	4.679471	4.644265	6.008451

Table: Benchmarking of rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on integer+1000x100 data (transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	0.035522	0.0381455	0.0384376	0.0383265	0.0385185	0.044317
2	rowAnyMissings(X, cols, rows)	0.048749	0.0495450	0.0498992	0.0497760	0.0502710	0.054800
3	rowAnyMissings(X[cols, rows])	0.107349	0.1093065	0.1110342	0.1097290	0.1102325	0.218301

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	rowAnyMissings(X, cols, rows)	1.372361	1.298843	1.298187	1.298736	1.305113	1.236546
3	rowAnyMissings(X[cols, rows])	3.022043	2.865515	2.888685	2.863006	2.861807	4.925897

Figure: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on integer+1000x100 data as well as rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on the same data transposed. Outliers are displayed as crosses. Times are in milliseconds.

Table: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on integer+1000x100 data (original and transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	16.552	17.0740	17.58287	17.2730	17.4835	28.990
2	rowAnyMissings_X_S	35.522	38.1455	38.43761	38.3265	38.5185	44.317

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.0000
2	rowAnyMissings_X_S	2.146085	2.234128	2.186083	2.218868	2.203134	1.5287

Figure: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on integer+1000x100 data (original and transposed). Outliers are displayed as crosses. Times are in milliseconds.

Data type "double"

Data

> rmatrix <- function(nrow, ncol, mode = c("logical", "double", "integer", "index"), range = c(-100, 
+     +100), na_prob = 0) {
+     mode <- match.arg(mode)
+     n <- nrow * ncol
+     if (mode == "logical") {
+         x <- sample(c(FALSE, TRUE), size = n, replace = TRUE)
+     }     else if (mode == "index") {
+         x <- seq_len(n)
+         mode <- "integer"
+     }     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
+     dim(x) <- c(nrow, ncol)
+     x
+ }
> rmatrices <- function(scale = 10, seed = 1, ...) {
+     set.seed(seed)
+     data <- list()
+     data[[1]] <- rmatrix(nrow = scale * 1, ncol = scale * 1, ...)
+     data[[2]] <- rmatrix(nrow = scale * 10, ncol = scale * 10, ...)
+     data[[3]] <- rmatrix(nrow = scale * 100, ncol = scale * 1, ...)
+     data[[4]] <- t(data[[3]])
+     data[[5]] <- rmatrix(nrow = scale * 10, ncol = scale * 100, ...)
+     data[[6]] <- t(data[[5]])
+     names(data) <- sapply(data, FUN = function(x) paste(dim(x), collapse = "x"))
+     data
+ }
> data <- rmatrices(mode = mode)

Results

10x10 matrix

> X <- data[["10x10"]]
> rows <- sample.int(nrow(X), size = nrow(X) * 0.7)
> cols <- sample.int(ncol(X), size = ncol(X) * 0.7)
> X_S <- X[rows, cols]
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3065763 163.8    5709258 305.0  5709258 305.0
Vcells 5293175  40.4   22267496 169.9 56666022 432.4
> colStats <- microbenchmark(colAnyMissings_X_S = colAnyMissings(X_S), `colAnyMissings(X, rows, cols)` = colAnyMissings(X, 
+     rows = rows, cols = cols), `colAnyMissings(X[rows, cols])` = colAnyMissings(X[rows, cols]), unit = "ms")
> X <- t(X)
> X_S <- t(X_S)
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3065748 163.8    5709258 305.0  5709258 305.0
Vcells 5293343  40.4   22267496 169.9 56666022 432.4
> rowStats <- microbenchmark(rowAnyMissings_X_S = rowAnyMissings(X_S), `rowAnyMissings(X, cols, rows)` = rowAnyMissings(X, 
+     rows = cols, cols = rows), `rowAnyMissings(X[cols, rows])` = rowAnyMissings(X[cols, rows]), unit = "ms")

Table: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on double+10x10 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	0.001948	0.0020155	0.0024903	0.0020750	0.0022520	0.036719
2	colAnyMissings(X, rows, cols)	0.002164	0.0022700	0.0024112	0.0023315	0.0024785	0.005347
3	colAnyMissings(X[rows, cols])	0.002686	0.0029695	0.0031934	0.0030695	0.0032235	0.010134

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.0000000	1.000000	1.000000	1.0000000
2	colAnyMissings(X, rows, cols)	1.110883	1.126271	0.9682526	1.123614	1.100577	0.1456194
3	colAnyMissings(X[rows, cols])	1.378850	1.473332	1.2823618	1.479277	1.431394	0.2759879

Table: Benchmarking of rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on double+10x10 data (transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	0.001837	0.0018920	0.0020309	0.0019375	0.0020740	0.004130
2	rowAnyMissings(X, cols, rows)	0.002025	0.0020890	0.0025987	0.0021775	0.0023310	0.039935
3	rowAnyMissings(X[cols, rows])	0.002446	0.0026765	0.0029030	0.0027715	0.0029345	0.008181

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	rowAnyMissings(X, cols, rows)	1.102341	1.104123	1.279616	1.123871	1.123915	9.669491
3	rowAnyMissings(X[cols, rows])	1.331519	1.414641	1.429463	1.430452	1.414899	1.980872

Figure: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on double+10x10 data as well as rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on the same data transposed. Outliers are displayed as crosses. Times are in milliseconds.

Table: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on double+10x10 data (original and transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
2	rowAnyMissings_X_S	1.837	1.8920	2.03086	1.9375	2.074	4.130
1	colAnyMissings_X_S	1.948	2.0155	2.49028	2.0750	2.252	36.719

	expr	min	lq	mean	median	uq	max
2	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
1	colAnyMissings_X_S	1.060425	1.065275	1.226219	1.070968	1.085824	8.890799

Figure: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on double+10x10 data (original and transposed). Outliers are displayed as crosses. Times are in milliseconds.

100x100 matrix

> X <- data[["100x100"]]
> rows <- sample.int(nrow(X), size = nrow(X) * 0.7)
> cols <- sample.int(ncol(X), size = ncol(X) * 0.7)
> X_S <- X[rows, cols]
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3065965 163.8    5709258 305.0  5709258 305.0
Vcells 5299161  40.5   22267496 169.9 56666022 432.4
> colStats <- microbenchmark(colAnyMissings_X_S = colAnyMissings(X_S), `colAnyMissings(X, rows, cols)` = colAnyMissings(X, 
+     rows = rows, cols = cols), `colAnyMissings(X[rows, cols])` = colAnyMissings(X[rows, cols]), unit = "ms")
> X <- t(X)
> X_S <- t(X_S)
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3065959 163.8    5709258 305.0  5709258 305.0
Vcells 5309244  40.6   22267496 169.9 56666022 432.4
> rowStats <- microbenchmark(rowAnyMissings_X_S = rowAnyMissings(X_S), `rowAnyMissings(X, cols, rows)` = rowAnyMissings(X, 
+     rows = cols, cols = rows), `rowAnyMissings(X[cols, rows])` = rowAnyMissings(X[cols, rows]), unit = "ms")

Table: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on double+100x100 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	0.004635	0.0049965	0.0052026	0.005118	0.0052700	0.009944
2	colAnyMissings(X, rows, cols)	0.007557	0.0079585	0.0083626	0.008119	0.0082595	0.020535
3	colAnyMissings(X[rows, cols])	0.020516	0.0209150	0.0218574	0.021080	0.0213025	0.074657

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	colAnyMissings(X, rows, cols)	1.630421	1.592815	1.607395	1.586362	1.567268	2.065064
3	colAnyMissings(X[rows, cols])	4.426322	4.185930	4.201261	4.118796	4.042220	7.507743

Table: Benchmarking of rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on double+100x100 data (transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	0.004956	0.0053805	0.0055589	0.0054995	0.0056570	0.009329
2	rowAnyMissings(X, cols, rows)	0.007678	0.0082480	0.0084524	0.0084380	0.0085520	0.012560
3	rowAnyMissings(X[cols, rows])	0.012345	0.0129325	0.0136767	0.0131115	0.0133365	0.067858

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	rowAnyMissings(X, cols, rows)	1.549233	1.532943	1.520507	1.534321	1.511755	1.346339
3	rowAnyMissings(X[cols, rows])	2.490920	2.403587	2.460315	2.384126	2.357522	7.273877

Figure: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on double+100x100 data as well as rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on the same data transposed. Outliers are displayed as crosses. Times are in milliseconds.

Table: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on double+100x100 data (original and transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	4.635	4.9965	5.20259	5.1180	5.270	9.944
2	rowAnyMissings_X_S	4.956	5.3805	5.55891	5.4995	5.657	9.329

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.0000000
2	rowAnyMissings_X_S	1.069256	1.076854	1.068489	1.074541	1.073435	0.9381537

Figure: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on double+100x100 data (original and transposed). Outliers are displayed as crosses. Times are in milliseconds.

1000x10 matrix

> X <- data[["1000x10"]]
> rows <- sample.int(nrow(X), size = nrow(X) * 0.7)
> cols <- sample.int(ncol(X), size = ncol(X) * 0.7)
> X_S <- X[rows, cols]
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3066174 163.8    5709258 305.0  5709258 305.0
Vcells 5300620  40.5   22267496 169.9 56666022 432.4
> colStats <- microbenchmark(colAnyMissings_X_S = colAnyMissings(X_S), `colAnyMissings(X, rows, cols)` = colAnyMissings(X, 
+     rows = rows, cols = cols), `colAnyMissings(X[rows, cols])` = colAnyMissings(X[rows, cols]), unit = "ms")
> X <- t(X)
> X_S <- t(X_S)
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3066168 163.8    5709258 305.0  5709258 305.0
Vcells 5310703  40.6   22267496 169.9 56666022 432.4
> rowStats <- microbenchmark(rowAnyMissings_X_S = rowAnyMissings(X_S), `rowAnyMissings(X, cols, rows)` = rowAnyMissings(X, 
+     rows = cols, cols = rows), `rowAnyMissings(X[cols, rows])` = rowAnyMissings(X[cols, rows]), unit = "ms")

Table: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on double+1000x10 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	0.004123	0.0043245	0.0045103	0.0044505	0.0045635	0.009336
2	colAnyMissings(X, rows, cols)	0.007219	0.0074250	0.0080249	0.0075595	0.0077200	0.052019
3	colAnyMissings(X[rows, cols])	0.020077	0.0203155	0.0205638	0.0204295	0.0205430	0.028397

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	colAnyMissings(X, rows, cols)	1.750909	1.716962	1.779241	1.698573	1.691684	5.571872
3	colAnyMissings(X[rows, cols])	4.869512	4.697768	4.559287	4.590383	4.501589	3.041667

Table: Benchmarking of rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on double+1000x10 data (transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	0.004964	0.005149	0.0056016	0.0052620	0.0053795	0.034969
2	rowAnyMissings(X, cols, rows)	0.008852	0.009071	0.0096919	0.0092185	0.0093375	0.043440
3	rowAnyMissings(X[cols, rows])	0.014473	0.014720	0.0150551	0.0148750	0.0150685	0.020760

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.0000000
2	rowAnyMissings(X, cols, rows)	1.783239	1.761701	1.730213	1.751900	1.735756	1.2422431
3	rowAnyMissings(X[cols, rows])	2.915592	2.858808	2.687663	2.826872	2.801097	0.5936687

Figure: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on double+1000x10 data as well as rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on the same data transposed. Outliers are displayed as crosses. Times are in milliseconds.

Table: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on double+1000x10 data (original and transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	4.123	4.3245	4.51031	4.4505	4.5635	9.336
2	rowAnyMissings_X_S	4.964	5.1490	5.60157	5.2620	5.3795	34.969

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.00000	1.000000
2	rowAnyMissings_X_S	1.203978	1.190658	1.241948	1.182339	1.17881	3.745608

Figure: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on double+1000x10 data (original and transposed). Outliers are displayed as crosses. Times are in milliseconds.

10x1000 matrix

> X <- data[["10x1000"]]
> rows <- sample.int(nrow(X), size = nrow(X) * 0.7)
> cols <- sample.int(ncol(X), size = ncol(X) * 0.7)
> X_S <- X[rows, cols]
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3066380 163.8    5709258 305.0  5709258 305.0
Vcells 5300757  40.5   22267496 169.9 56666022 432.4
> colStats <- microbenchmark(colAnyMissings_X_S = colAnyMissings(X_S), `colAnyMissings(X, rows, cols)` = colAnyMissings(X, 
+     rows = rows, cols = cols), `colAnyMissings(X[rows, cols])` = colAnyMissings(X[rows, cols]), unit = "ms")
> X <- t(X)
> X_S <- t(X_S)
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3066374 163.8    5709258 305.0  5709258 305.0
Vcells 5310840  40.6   22267496 169.9 56666022 432.4
> rowStats <- microbenchmark(rowAnyMissings_X_S = rowAnyMissings(X_S), `rowAnyMissings(X, cols, rows)` = rowAnyMissings(X, 
+     rows = cols, cols = rows), `rowAnyMissings(X[cols, rows])` = rowAnyMissings(X[cols, rows]), unit = "ms")

Table: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on double+10x1000 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	0.005969	0.0062765	0.0065605	0.0064860	0.0067145	0.010070
2	colAnyMissings(X, rows, cols)	0.010097	0.0105125	0.0112457	0.0106505	0.0108455	0.061931
3	colAnyMissings(X[rows, cols])	0.015696	0.0160795	0.0164897	0.0162740	0.0166875	0.022871

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	colAnyMissings(X, rows, cols)	1.691573	1.674898	1.714166	1.642075	1.615236	6.150050
3	colAnyMissings(X[rows, cols])	2.629586	2.561858	2.513495	2.509097	2.485293	2.271202

Table: Benchmarking of rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on double+10x1000 data (transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	0.005782	0.0061200	0.0065552	0.0062550	0.0064965	0.026689
2	rowAnyMissings(X, cols, rows)	0.008904	0.0092125	0.0095146	0.0094825	0.0096375	0.013595
3	rowAnyMissings(X[cols, rows])	0.013701	0.0141780	0.0146415	0.0144220	0.0146505	0.028200

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.0000000
2	rowAnyMissings(X, cols, rows)	1.539952	1.505310	1.451461	1.515987	1.483491	0.5093859
3	rowAnyMissings(X[cols, rows])	2.369595	2.316667	2.233576	2.305675	2.255137	1.0566151

Figure: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on double+10x1000 data as well as rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on the same data transposed. Outliers are displayed as crosses. Times are in milliseconds.

Table: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on double+10x1000 data (original and transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
2	rowAnyMissings_X_S	5.782	6.1200	6.55518	6.255	6.4965	26.689
1	colAnyMissings_X_S	5.969	6.2765	6.56046	6.486	6.7145	10.070

	expr	min	lq	mean	median	uq	max
2	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.00000	1.000000	1.000000
1	colAnyMissings_X_S	1.032342	1.025572	1.000806	1.03693	1.033556	0.377309

Figure: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on double+10x1000 data (original and transposed). Outliers are displayed as crosses. Times are in milliseconds.

100x1000 matrix

> X <- data[["100x1000"]]
> rows <- sample.int(nrow(X), size = nrow(X) * 0.7)
> cols <- sample.int(ncol(X), size = ncol(X) * 0.7)
> X_S <- X[rows, cols]
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3066579 163.8    5709258 305.0  5709258 305.0
Vcells 5346251  40.8   22267496 169.9 56666022 432.4
> colStats <- microbenchmark(colAnyMissings_X_S = colAnyMissings(X_S), `colAnyMissings(X, rows, cols)` = colAnyMissings(X, 
+     rows = rows, cols = cols), `colAnyMissings(X[rows, cols])` = colAnyMissings(X[rows, cols]), unit = "ms")
> X <- t(X)
> X_S <- t(X_S)
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3066573 163.8    5709258 305.0  5709258 305.0
Vcells 5446334  41.6   22267496 169.9 56666022 432.4
> rowStats <- microbenchmark(rowAnyMissings_X_S = rowAnyMissings(X_S), `rowAnyMissings(X, cols, rows)` = rowAnyMissings(X, 
+     rows = cols, cols = rows), `rowAnyMissings(X[cols, rows])` = rowAnyMissings(X[cols, rows]), unit = "ms")

Table: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on double+100x1000 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	0.025480	0.0261915	0.0272354	0.0265800	0.0271455	0.041650
2	colAnyMissings(X, rows, cols)	0.054747	0.0552735	0.0574334	0.0557780	0.0566840	0.176827
3	colAnyMissings(X[rows, cols])	0.174996	0.1778275	0.1819949	0.1803625	0.1838225	0.246418

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	colAnyMissings(X, rows, cols)	2.148626	2.110360	2.108780	2.098495	2.088155	4.245546
3	colAnyMissings(X[rows, cols])	6.867975	6.789512	6.682299	6.785647	6.771749	5.916399

Table: Benchmarking of rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on double+100x1000 data (transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	0.030262	0.0309365	0.0345776	0.0319325	0.0349330	0.065825
2	rowAnyMissings(X, cols, rows)	0.061381	0.0617900	0.0659395	0.0624655	0.0653245	0.106891
3	rowAnyMissings(X[cols, rows])	0.098686	0.1004695	0.1091581	0.1031840	0.1077745	0.179930

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	rowAnyMissings(X, cols, rows)	2.028319	1.997317	1.907001	1.956173	1.869994	1.623866
3	rowAnyMissings(X[cols, rows])	3.261054	3.247604	3.156904	3.231316	3.085177	2.733460

Figure: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on double+100x1000 data as well as rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on the same data transposed. Outliers are displayed as crosses. Times are in milliseconds.

Table: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on double+100x1000 data (original and transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	25.480	26.1915	27.23537	26.5800	27.1455	41.650
2	rowAnyMissings_X_S	30.262	30.9365	34.57757	31.9325	34.9330	65.825

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.00000	1.000000
2	rowAnyMissings_X_S	1.187677	1.181166	1.269583	1.201373	1.28688	1.580432

Figure: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on double+100x1000 data (original and transposed). Outliers are displayed as crosses. Times are in milliseconds.

1000x100 matrix

> X <- data[["1000x100"]]
> rows <- sample.int(nrow(X), size = nrow(X) * 0.7)
> cols <- sample.int(ncol(X), size = ncol(X) * 0.7)
> X_S <- X[rows, cols]
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3066795 163.8    5709258 305.0  5709258 305.0
Vcells 5346398  40.8   22267496 169.9 56666022 432.4
> colStats <- microbenchmark(colAnyMissings_X_S = colAnyMissings(X_S), `colAnyMissings(X, rows, cols)` = colAnyMissings(X, 
+     rows = rows, cols = cols), `colAnyMissings(X[rows, cols])` = colAnyMissings(X[rows, cols]), unit = "ms")
> X <- t(X)
> X_S <- t(X_S)
> gc()
          used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells 3066789 163.8    5709258 305.0  5709258 305.0
Vcells 5446481  41.6   22267496 169.9 56666022 432.4
> rowStats <- microbenchmark(rowAnyMissings_X_S = rowAnyMissings(X_S), `rowAnyMissings(X, cols, rows)` = rowAnyMissings(X, 
+     rows = cols, cols = rows), `rowAnyMissings(X[cols, rows])` = rowAnyMissings(X[cols, rows]), unit = "ms")

Table: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on double+1000x100 data. The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	0.024417	0.0246915	0.0255219	0.0249735	0.025424	0.035591
2	colAnyMissings(X, rows, cols)	0.050943	0.0512200	0.0521011	0.0513790	0.051570	0.071666
3	colAnyMissings(X[rows, cols])	0.092693	0.0938050	0.0970414	0.0947325	0.095963	0.208158

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	colAnyMissings(X, rows, cols)	2.086374	2.074398	2.041423	2.057341	2.028398	2.013599
3	colAnyMissings(X[rows, cols])	3.796248	3.799081	3.802277	3.793321	3.774504	5.848613

Table: Benchmarking of rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on double+1000x100 data (transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	0.029110	0.029517	0.0301505	0.0297810	0.0302135	0.043248
2	rowAnyMissings(X, cols, rows)	0.064299	0.064734	0.0654624	0.0649210	0.0650860	0.096013
3	rowAnyMissings(X[cols, rows])	0.103788	0.105128	0.1087878	0.1060125	0.1075830	0.258804

	expr	min	lq	mean	median	uq	max
1	rowAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	rowAnyMissings(X, cols, rows)	2.208829	2.193109	2.171188	2.179947	2.154203	2.220056
3	rowAnyMissings(X[cols, rows])	3.565373	3.561609	3.608157	3.559736	3.560759	5.984184

Figure: Benchmarking of colAnyMissings_X_S(), colAnyMissings(X, rows, cols)() and colAnyMissings(X[rows, cols])() on double+1000x100 data as well as rowAnyMissings_X_S(), rowAnyMissings(X, cols, rows)() and rowAnyMissings(X[cols, rows])() on the same data transposed. Outliers are displayed as crosses. Times are in milliseconds.

Table: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on double+1000x100 data (original and transposed). The top panel shows times in milliseconds and the bottom panel shows relative times.

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	24.417	24.6915	25.52193	24.9735	25.4240	35.591
2	rowAnyMissings_X_S	29.110	29.5170	30.15050	29.7810	30.2135	43.248

	expr	min	lq	mean	median	uq	max
1	colAnyMissings_X_S	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
2	rowAnyMissings_X_S	1.192202	1.195432	1.181357	1.192504	1.188385	1.215139

Figure: Benchmarking of colAnyMissings_X_S() and rowAnyMissings_X_S() on double+1000x100 data (original and transposed). 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 22.31 secs.

Reproducibility

To reproduce this report, do:

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

---

Copyright Dongcan Jiang. Last updated on 2019-09-10 20:35:21 (-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>