[R] data.frame: data-driven column selections that vary by row??

Ista Zahn istazahn at gmail.com
Tue Mar 31 20:19:34 CEST 2015 

Hi David,

I suggest reading http://www.jstatsoft.org/v59/i10, then:

library(tidyr)
library(dplyr)
bw <- gather(bw, key = "tmp", value = "value", matches("^d[a-z]+[0-9]+"))
bw <- separate(bw, tmp, c("disc", "var"), "_", extra = "merge")
bw <- spread(bw, var, value)

Best,
Ista

On Tue, Mar 31, 2015 at 1:22 PM, David Wolfskill <r at catwhisker.org> wrote:
> On Tue, Mar 31, 2015 at 07:11:28AM -0800, John Kane wrote:
>> I think we need some data and code
>> Reproducibility
>> https://github.com/hadley/devtools/wiki/Reproducibility
>>  http://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example
>> ....
>
> I apologize for failing to provide that.
>
> Here is a quite small subset of the data (with a few edits to reduce
> excess verbosity in names of things) that still illustrates the
> challenge I perceive:
>
>> dput(bw)
> structure(list(timestamp = c(1426892400L, 1426892400L, 1426892400L,
> 1426892400L, 1426892400L, 1426892400L, 1426892460L, 1426892460L,
> 1426892460L, 1426892460L, 1426892460L, 1426892460L, 1426892520L,
> 1426892520L, 1426892520L, 1426892520L, 1426892520L, 1426892520L
> ), hostname = c("c001", "c002", "c021", "c022", "c041", "c051",
> "c001", "c002", "c021", "c022", "c041", "c051", "c001", "c002",
> "c021", "c022", "c041", "c051"), health = c(0.0549374999999983,
> 0.250585416666667, 1, 1, 0.577784167075767, 0.546805261621527,
> 0.1599375, 0.24954375, 1, 1, 0.582307554123614, 0.558298168996525,
> 0.2813125, 0.270877083333333, 1, 1, 0.579231349457365, 0.542973020177151
> ), hw = c(1.9, 1.9, 1.4, 1.4, 1.5, 1.5, 1.9, 1.9, 1.4, 1.4, 1.5,
> 1.5, 1.9, 1.9, 1.4, 1.4, 1.5, 1.5), fw = structure(c(1L, 1L,
> 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L
> ), .Label = "2015Q1.2", class = "factor"), role = structure(c(1L,
> 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
> 2L), .Label = c("control", "test"), class = "factor"), type = structure(c(3L,
> 3L, 1L, 1L, 2L, 2L, 3L, 3L, 1L, 1L, 2L, 2L, 3L, 3L, 1L, 1L, 2L,
> 2L), .Label = c("D", "F", "H"), class = "factor"), da20_busy_pct = c(79.1,
> 62.8, NA, NA, NA, NA, 75, 64.8, NA, NA, NA, NA, 72.2, 74.5, NA,
> NA, NA, NA), da20_dev_type = structure(c(2L, 2L, 1L, 1L, 1L,
> 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L), .Label = c("",
> "hdd"), class = "factor"), da20_kb_per_xfer_read = c(727.23,
> 665.81, NA, NA, NA, NA, 737.04, 691.38, NA, NA, NA, NA, 721.71,
> 668.96, NA, NA, NA, NA), da20_kb_per_xfer_write = c(0, 0, NA,
> NA, NA, NA, 0, 0, NA, NA, NA, NA, 0, 0, NA, NA, NA, NA), da20_mb_per_sec_read = c(39.77,
> 31.21, NA, NA, NA, NA, 36.71, 32.41, NA, NA, NA, NA, 35.94, 37.24,
> NA, NA, NA, NA), da20_mb_per_sec_write = c(0, 0, NA, NA, NA,
> NA, 0, 0, NA, NA, NA, NA, 0, 0, NA, NA, NA, NA), da20_ms_per_xactn_read = c(43.5,
> 31.6, NA, NA, NA, NA, 35.7, 30.2, NA, NA, NA, NA, 32.7, 34.6,
> NA, NA, NA, NA), da20_ms_per_xactn_write = c(0, 0, NA, NA, NA,
> NA, 0, 0, NA, NA, NA, NA, 0, 0, NA, NA, NA, NA), da20_Q_length = c(0,
> 0, NA, NA, NA, NA, 2, 0, NA, NA, NA, NA, 1, 1, NA, NA, NA, NA
> ), da20_xfers_per_sec_other = c(0, 0, NA, NA, NA, NA, 0, 0, NA,
> NA, NA, NA, 0, 0, NA, NA, NA, NA), da20_xfers_per_sec_read = c(56,
> 48, NA, NA, NA, NA, 51, 48, NA, NA, NA, NA, 51, 57, NA, NA, NA,
> NA), da20_xfers_per_sec_write = c(0, 0, NA, NA, NA, NA, 0, 0,
> NA, NA, NA, NA, 0, 0, NA, NA, NA, NA), da2_busy_pct = c(84.5,
> 81.8, 29.5, 26.7, 55.5, 50.9, 80.6, 79.7, 29.2, 27.3, 58.8, 50.2,
> 74.6, 79.3, 29.4, 26.6, 55.4, 50.1), da2_dev_type = structure(c(2L,
> 2L, 3L, 3L, 3L, 3L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 3L, 3L, 3L,
> 3L), .Label = c("", "hdd", "ssd"), class = "factor"), da2_kb_per_xfer_read = c(690.67,
> 686.63, 613.78, 587, 571.64, 553.27, 692.26, 660.05, 612.01,
> 594.28, 560.16, 566.41, 672.68, 670.25, 604.64, 592.16, 565.02,
> 564.43), da2_kb_per_xfer_write = c(0, 0, 0, 0, 0, 0, 0, 0, 0,
> 0, 0, 0, 0, 0, 0, 0, 0, 0), da2_mb_per_sec_read = c(44.52, 41.57,
> 134.26, 120.38, 252.88, 229.09, 41.24, 39.96, 132.68, 123.61,
> 268.04, 227.34, 37.44, 39.93, 133.45, 120.28, 251.06, 225.99),
>     da2_mb_per_sec_write = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
>     0, 0, 0, 0, 0, 0, 0), da2_ms_per_xactn_read = c(49.1, 47.8,
>     2, 1.8, 2.6, 2.4, 40.3, 43.9, 2, 1.8, 2.8, 2.4, 37.1, 40.9,
>     1.9, 1.8, 2.6, 2.4), da2_ms_per_xactn_write = c(0, 0, 0,
>     0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), da2_Q_length = c(0,
>     2, 0, 1, 3, 0, 3, 0, 0, 0, 0, 0, 2, 2, 0, 0, 0, 3), da2_xfers_per_sec_other = c(0,
>     0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), da2_xfers_per_sec_read = c(66,
>     62, 224, 210, 453, 424, 61, 62, 222, 213, 490, 411, 57, 61,
>     226, 208, 455, 410), da2_xfers_per_sec_write = c(0, 0, 0,
>     0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)), .Names = c("timestamp",
> "hostname", "health", "hw", "fw", "role", "type", "da20_busy_pct",
> "da20_dev_type", "da20_kb_per_xfer_read", "da20_kb_per_xfer_write",
> "da20_mb_per_sec_read", "da20_mb_per_sec_write", "da20_ms_per_xactn_read",
> "da20_ms_per_xactn_write", "da20_Q_length", "da20_xfers_per_sec_other",
> "da20_xfers_per_sec_read", "da20_xfers_per_sec_write", "da2_busy_pct",
> "da2_dev_type", "da2_kb_per_xfer_read", "da2_kb_per_xfer_write",
> "da2_mb_per_sec_read", "da2_mb_per_sec_write", "da2_ms_per_xactn_read",
> "da2_ms_per_xactn_write", "da2_Q_length", "da2_xfers_per_sec_other",
> "da2_xfers_per_sec_read", "da2_xfers_per_sec_write"), class = "data.frame", row.names = c(1L,
> 2L, 7L, 8L, 13L, 16L, 19L, 20L, 25L, 26L, 31L, 34L, 37L, 38L,
> 43L, 44L, 49L, 52L))
>> dim(bw)
> [1] 18 31
>
> (In the current case, there are a few more columns per device, as
> well as about 40 more devices -- and thousands of rows -- represented
> in the data.)
>
> For reference (as well):
>> version
>                _
> platform       i386-portbld-freebsd10.1
> arch           i386
> os             freebsd10.1
> system         i386, freebsd10.1
> status         Patched
> major          3
> minor          0.2
> year           2013
> month          11
> day            12
> svn rev        64207
> language       R
> version.string R version 3.0.2 Patched (2013-11-12 r64207)
> nickname       Frisbee Sailing
>>
>
> [BTW: the first link cited (above) is now a redirect to
> <http://adv-r.had.co.nz/Reproducibility.html>.]
>
> Peace,
> david
> --
> David H. Wolfskill                              r at catwhisker.org
> Those who murder in the name of God or prophet are blasphemous cowards.
>
> See http://www.catwhisker.org/~david/publickey.gpg for my public key.
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

More information about the R-help mailing list