Custom CSV fails with header

[muschellij2]

GGIR/R/g.report.part2.R

Line 137 in bb399f0

if (header != "no header") {

Describe the bug
CSV with time/x/y/z fails when specifying rmc arguments. Following https://cran.r-project.org/web/packages/GGIR/vignettes/readmyacccsv.html still returns an error due to header.

62161_sub.csv.zip

To Reproduce

library(curl)
#> Warning: package 'curl' was built under R version 4.4.1
#> Using libcurl 8.4.0 with LibreSSL/3.3.6
library(GGIR)
zipfile = tempfile(fileext = ".zip")
curl_download(url = "https://github.com/user-attachments/files/17941173/62161_sub.csv.zip", destfile = zipfile)
exdir = tempfile()
unzip(zipfile, exdir = exdir)

datadir = file.path(exdir, "62161_sub.csv")
cat(readLines(datadir, n = 5), sep = "\n")
#> time,x,y,z
#> 2000-01-08T12:30:00.000Z,0.534,0.106,-0.877
#> 2000-01-08T12:30:00.013Z,0.487,0.126,-0.874
#> 2000-01-08T12:30:00.024Z,0.519,0.085,-0.874
#> 2000-01-08T12:30:00.036Z,0.543,0.114,-0.871

I = g.inspectfile(
  datadir,
  desiredtz = "UTC",
  configtz = "UTC",
  params_rawdata = list(
    #=====================
    rmc.dec = ".",
    rmc.firstrow.acc = 2,
    rmc.firstrow.header = 1,
    rmc.header.length = NULL,
    rmc.col.acc = 2:4,
    rmc.col.temp = NULL,
    rmc.col.time = 1,
    rmc.unit.acc = "g",
    rmc.unit.temp = "C",
    rmc.unit.time = "character",
    rmc.format.time = "%Y-%m-%d %H:%M:%OS",
    rmc.bitrate = NULL,
    rmc.dynamic_range = 6,
    rmc.unsignedbit = TRUE,
    rmc.origin = "1970-01-01",
    rmc.sf = 80L,
    rmc.headername.sf = NULL,
    rmc.headername.sn = NULL,
    rmc.headername.recordingid = NULL,
    rmc.header.structure = NULL,
    rmc.check4timegaps = FALSE,
    rmc.noise = 13,
    rmc.col.wear = NULL,
    rmc.doresample = FALSE,
    rmc.scalefactor.acc = 1
  )
)
I
#> $header
#>               
#> time         x
#> sample_rate 80
#> 
#> $monc
#> [1] 0
#> 
#> $monn
#> [1] "unknown"
#> 
#> $dformc
#> [1] 5
#> 
#> $dformn
#> [1] "csv"
#> 
#> $sf
#> [1] 80
#> 
#> $decn
#> [1] "."
#> 
#> $filename
#> [1] "62161_sub.csv"

outputdir = tempfile()
dir.create(outputdir)
GGIR::GGIR(
  datadir = datadir,
  outputdir = outputdir,
  studyname = "pax_g",
  print.filename = TRUE,
  desiredtz = "UTC",
  configtz = "UTC",
  sensor.location = "wrist", 
  verbose = TRUE,
  minimumFileSizeMB = 0, # don't let small gz files be skipped
  do.parallel = FALSE,
  dynrange = 6L, # dynamic range of 6g (https://wwwn.cdc.gov/Nchs/Nhanes/2011-2012/PAX80_G.htm)
  idloc = 6, # filename gives the ID before the "."
  
  #=====================
  # read.myacc.csv arguments for reading in CSVS
  #=====================
  #=====================
  rmc.dec = ".",
  rmc.firstrow.acc = 2,
  rmc.firstrow.header = 1,
  rmc.header.length = 1,
  rmc.col.acc = 2:4,
  rmc.col.temp = NULL,
  rmc.col.time = 1,
  rmc.unit.acc = "g",
  rmc.unit.temp = "C",
  rmc.unit.time = "character",
  rmc.format.time = "%Y-%m-%d %H:%M:%OS",
  rmc.bitrate = NULL,
  rmc.dynamic_range = 6,
  rmc.unsignedbit = TRUE,
  rmc.origin = "1970-01-01",
  rmc.sf = 80L,
  rmc.headername.sf = NULL,
  rmc.headername.sn = NULL,
  rmc.headername.recordingid = NULL,
  rmc.header.structure = NULL,
  rmc.check4timegaps = FALSE,
  rmc.noise = 13,
  rmc.col.wear = NULL,
  rmc.doresample = FALSE,
  rmc.scalefactor.acc = 1
)
#> 
#> Checking that user has write access permission for directory specified by argument outputdir: Yes
#> 
#>    GGIR version: 3.1.7
#> 
#>    Do not forget to cite GGIR in your publications via a version number and
#>    Migueles et al. 2019 JMPB. doi: 10.1123/jmpb.2018-0063. 
#>    See also: https://cran.r-project.org/package=GGIR/vignettes/GGIR.html#citing-ggir
#> 
#>    To make your research reproducible and interpretable always report:
#>      (1) Accelerometer brand and product name
#>      (2) How you configured the accelerometer
#>      (3) Study protocol and wear instructions given to the participants
#>      (4) GGIR version
#>      (5) How GGIR was used: Share the config.csv file or your R script.
#>      (6) How you post-processed / cleaned GGIR output
#>      (7) How reported outcomes relate to the specific variable names in GGIR
#> ________________________________________________________________________________
#>  Part 1 
#> 
#> Checking that user has read access permission for all files in data directory: Yes
#> 1 
#> File name: 62161_sub.csv
#> P1 file 1
#> 
#> Investigate calibration of the sensors with function g.calibrate:
#> 
#> Loading chunk: 1 2 3
#> Extract signal features (metrics) with the g.getmeta function:
#> 
#> Loading chunk: 1 2
#> Save .RData-file with: calibration report, file inspection report and all signal features...
#> 
#> ________________________________________________________________________________
#>  Part 2 
#> 1 
#> ________________________________________________________________________________
#>  Part 3 
#> 1
#> 
#> ________________________________________________________________________________
#>  Part 4 
#>  1
#> 
#> ________________________________________________________________________________
#>  Part 5 
#> 1 
#> ________________________________________________________________________________
#>  Report part 2 
#>  1
#> Error in if (header != "no header") {: argument is of length zero

^{Created on 2024-11-27 with reprex v2.1.1}

Session info

sessioninfo::session_info()
#> ─ Session info ───────────────────────────────────────────────────────────────
#>  setting  value
#>  version  R version 4.4.0 (2024-04-24)
#>  os       macOS Sonoma 14.4.1
#>  system   x86_64, darwin20
#>  ui       X11
#>  language (EN)
#>  collate  en_US.UTF-8
#>  ctype    en_US.UTF-8
#>  tz       America/New_York
#>  date     2024-11-27
#>  pandoc   3.2 @ /Applications/RStudio.app/Contents/Resources/app/quarto/bin/tools/x86_64/ (via rmarkdown)
#> 
#> ─ Packages ───────────────────────────────────────────────────────────────────
#>  package     * version date (UTC) lib source
#>  cli           3.6.3   2024-06-21 [1] CRAN (R 4.4.0)
#>  curl        * 5.2.3   2024-09-20 [1] CRAN (R 4.4.1)
#>  data.table    1.16.2  2024-10-10 [1] CRAN (R 4.4.1)
#>  digest        0.6.37  2024-08-19 [1] CRAN (R 4.4.1)
#>  evaluate      1.0.1   2024-10-10 [1] CRAN (R 4.4.1)
#>  fastmap       1.2.0   2024-05-15 [1] CRAN (R 4.4.0)
#>  fs            1.6.5   2024-10-30 [1] CRAN (R 4.4.1)
#>  GGIR        * 3.1-7   2024-11-28 [1] Github (wadpac/GGIR@bb399f0)
#>  glue          1.8.0   2024-09-30 [1] CRAN (R 4.4.1)
#>  htmltools     0.5.8.1 2024-04-04 [1] CRAN (R 4.4.0)
#>  knitr         1.49    2024-11-08 [1] CRAN (R 4.4.1)
#>  lattice       0.22-6  2024-03-20 [1] CRAN (R 4.4.0)
#>  lifecycle     1.0.4   2023-11-07 [1] CRAN (R 4.4.0)
#>  reprex        2.1.1   2024-07-06 [1] CRAN (R 4.4.0)
#>  rlang         1.1.4   2024-06-04 [1] CRAN (R 4.4.0)
#>  rmarkdown     2.29    2024-11-04 [1] CRAN (R 4.4.1)
#>  rstudioapi    0.17.1  2024-10-22 [1] CRAN (R 4.4.1)
#>  sessioninfo   1.2.2   2021-12-06 [1] CRAN (R 4.4.0)
#>  withr         3.0.2   2024-10-28 [1] CRAN (R 4.4.1)
#>  xfun          0.49    2024-10-31 [1] CRAN (R 4.4.1)
#>  yaml          2.3.10  2024-07-26 [1] CRAN (R 4.4.0)
#>  zoo           1.8-12  2023-04-13 [1] CRAN (R 4.4.0)
#> 
#>  [1] /Library/Frameworks/R.framework/Versions/4.4-x86_64/Resources/library
#> 
#> ──────────────────────────────────────────────────────────────────────────────

Info

1. Sensor brand: ActiGraph
2. Data format: 'CSV from NHANES
3. Approximate recording duration: 17 hours
4. Are you using a sleep diary to guide the sleep detection: NO

Desktop (please complete the following information):

• OS: Mac OSX
• GGIR Version: 3.1.7

Additional context
Add any other context about the problem here.

Before submitting

• Have you tried the steps to reproduce? Do they include all relevant data and configuration? Does the issue you report still appear there?
• Have you tried this on the latest master branch from GitHub?

[vincentvanhees]

I think this is a misunderstanding. By 'header' we mean file header, not column headers. With the following parameter set I am able to process your file:

# Test with read.myacc.csv on its own to first check that parameters are correct:
D = read.myacc.csv(rmc.file = "path/to/filefolder/file.csv",
                   rmc.nrow = 100, # only read start of file for this test
                   rmc.dec = ".",
                   rmc.firstrow.acc = 2,
                   rmc.firstrow.header = NULL, # <= changed!
                   rmc.header.length = NULL,
                   rmc.col.acc = 2:4,
                   rmc.col.temp = NULL,
                   rmc.col.time = 1,
                   rmc.unit.acc = "g",
                   rmc.unit.temp = "C",
                   rmc.unit.time = "character",
                   rmc.format.time = "%Y-%m-%dT%H:%M:%OS", # <= changed!
                   desiredtz = "", # <= needed when using this function on its own, in GGIR() calls this happens automatically
                   rmc.bitrate = NULL,
                   rmc.dynamic_range = 6,
                   rmc.unsignedbit = TRUE,
                   rmc.origin = "1970-01-01",
                   rmc.sf = 80L,
                   rmc.headername.sf = NULL,
                   rmc.headername.sn = NULL,
                   rmc.headername.recordingid = NULL,
                   rmc.header.structure = NULL,
                   rmc.check4timegaps = FALSE,
                   rmc.col.wear = NULL,
                   rmc.doresample = FALSE,
                   rmc.scalefactor.acc = 1)

> print(head(D$data))
       time     x     y      z
1 947334600 0.534 0.106 -0.877
2 947334600 0.487 0.126 -0.874
3 947334600 0.519 0.085 -0.874
4 947334600 0.543 0.114 -0.871
5 947334600 0.507 0.114 -0.868
6 947334600 0.481 0.120 -0.862

# Test with GGIR as a whole:
GGIR(datadir = "/path/to/filefolder",
     outputdir = "/some/other/path",
     rmc.dec = ".",
     rmc.firstrow.acc = 2,
     rmc.firstrow.header = NULL,
     rmc.header.length = NULL,
     rmc.col.acc = 2:4,
     rmc.col.temp = NULL,
     rmc.col.time = 1,
     rmc.unit.acc = "g",
     rmc.unit.temp = "C",
     rmc.unit.time = "character",
     rmc.format.time = "%Y-%m-%dT%H:%M:%OS",
     rmc.bitrate = NULL,
     rmc.dynamic_range = 6,
     rmc.unsignedbit = TRUE,
     rmc.origin = "1970-01-01",
     rmc.sf = 80L,
     rmc.headername.sf = NULL,
     rmc.headername.sn = NULL,
     rmc.headername.recordingid = NULL,
     rmc.header.structure = NULL,
     rmc.check4timegaps = FALSE,
     rmc.col.wear = NULL,
     rmc.doresample = FALSE,
     rmc.scalefactor.acc = 1)

The documentation mentions 'file header' a couple of time, but I understand that this should be emphasized more systematically across the whole page. So, action points from this is to update the vignette accordingly.