This script reads all CSV files exported from the GOM Inspect scripts, and imports them into one single CSV file and one single R file.
The script will:
dir_in <- "analysis/raw_data/EAP-flake"
dir_out <- "analysis/derived_data/"Raw data must be located in ~/analysis/raw_data/EAP-flake.
Formatted data will be saved in ~/analysis/derived_data/.
The knit directory for this script is the project directory.
pack_to_load <- c("openxlsx", "R.utils")
sapply(pack_to_load, library, character.only = TRUE, logical.return = TRUE)Warning: package 'openxlsx' was built under R version 4.1.3Warning: package 'R.utils' was built under R version 4.1.3openxlsx R.utils
TRUE TRUE Angles <- list.files(dir_in, pattern = "_w_.*\\.csv$", full.names = TRUE)
Angles.infos <- vector(mode = "list", length = length(Angles))
for (i in seq_along(Angles.infos)){
Angles.infos[[i]] <- file.info(Angles[i])
}
Angles.infos <- do.call(rbind, Angles.infos)
Angles.infos <- data.frame(file = basename(row.names(Angles.infos)), Angles.infos)Angles.data <- vector(mode = "list", length = length(Angles))
for (i in seq_along(Angles.data)){
Angles.data[[i]] <- read.csv(Angles[i])
Angles.data[[i]][["steps"]] <- Angles.data[[i]][2,3] - Angles.data[[i]][1,3]
}
Angles.data <- do.call(rbind, Angles.data)
names(Angles.data) <- c("section", "angle_number", "dist_intersection", "segment_length", "3points", "2lines", "best_fit", "steps")
Angles.data <- Angles.data[c(1:2, 8, 3:7)]
str(Angles.data)'data.frame': 1398 obs. of 8 variables:
$ section : chr "EAP-flake_1_E1_RE_SEC-01_local" "EAP-flake_1_E1_RE_SEC-01_local" "EAP-flake_1_E1_RE_SEC-01_local" "EAP-flake_1_E1_RE_SEC-01_local" ...
$ angle_number : int 1 2 3 4 5 6 7 8 9 10 ...
$ steps : num 0.2 0.2 0.2 0.2 0.2 0.2 0.2 0.2 0.2 0.2 ...
$ dist_intersection: num 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6 1.8 2 ...
$ segment_length : num 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 ...
$ 3points : num 116.6 106 105.4 93 84.6 ...
$ 2lines : num 111.3 95.6 80.1 53.4 52.3 ...
$ best_fit : num 107.4 98.9 79.6 55.9 50.8 ...The units are based on the first CSV-file. Units are incorporated to the data object Angles.data as comments.
headers <- unlist(strsplit(readLines(Angles[1], n = 1), ","))
units.var <- sub(pattern = ".*\\[(.+)\\]", "\\1", headers)[-(1:2)]
units.var <- c(rep(units.var[1],2), units.var[-1])
names(units.var) <- names(Angles.data)[-(1:2)]
comment(Angles.data) <- units.var
units.var.table <- data.frame(variable = names(units.var), unit = units.var)file_out <- "EAP-flake"The files will be saved as “~/EAP-flake.[ext]”.
write.xlsx(list(data = Angles.data, units = units.var.table, CSV_infos = Angles.infos),
file = paste0(dir_out, file_out, ".xlsx"))saveObject(Angles.data, file = paste0(dir_out, file_out, ".Rbin"))sessionInfo()R version 4.1.0 (2021-05-18)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 10 x64 (build 19043)
Matrix products: default
locale:
[1] LC_COLLATE=German_Germany.1252 LC_CTYPE=German_Germany.1252
[3] LC_MONETARY=German_Germany.1252 LC_NUMERIC=C
[5] LC_TIME=German_Germany.1252
attached base packages:
[1] stats graphics grDevices utils datasets methods base
other attached packages:
[1] R.utils_2.11.0 R.oo_1.24.0 R.methodsS3_1.8.1 openxlsx_4.2.5
loaded via a namespace (and not attached):
[1] Rcpp_1.0.8.3 digest_0.6.29 R6_2.5.1 jsonlite_1.8.0
[5] magrittr_2.0.3 evaluate_0.15 zip_2.2.0 stringi_1.7.6
[9] rlang_1.0.2 cli_3.3.0 rstudioapi_0.13 jquerylib_0.1.4
[13] bslib_0.3.1 rmarkdown_2.14 tools_4.1.0 stringr_1.4.0
[17] xfun_0.30 yaml_2.3.5 fastmap_1.1.0 compiler_4.1.0
[21] htmltools_0.5.2 knitr_1.39 sass_0.4.1 RStudio version 1.4.1717.
for (i in pack_to_load) print(citation(i), bibtex = FALSE)
To cite package 'openxlsx' in publications use:
Philipp Schauberger and Alexander Walker (2021). openxlsx: Read,
Write and Edit xlsx Files. R package version 4.2.5.
https://CRAN.R-project.org/package=openxlsx
To cite package 'R.utils' in publications use:
Henrik Bengtsson (2021). R.utils: Various Programming Utilities. R
package version 2.11.0. https://CRAN.R-project.org/package=R.utilsEND OF SCRIPT