In rubenarslan/codebook: Automatic Codebooks from Metadata Encoded in Dataset Attributes

knitr::opts_chunk$set(
  warning = TRUE, # show warnings during codebook generation
  message = TRUE, # show messages during codebook generation
  error = TRUE, # do not interrupt codebook generation in case of errors,
                # usually better for debugging
  echo = TRUE  # show R code
)
ggplot2::theme_set(ggplot2::theme_bw())

library(codebook)
library(tidyverse)
library(labelled)

knit_by_pkgdown <- !is.null(knitr::opts_chunk$get("fig.retina"))

ggplot2::theme_set(ggplot2::theme_bw())
knitr::opts_chunk$set(warning = TRUE, message = TRUE, error = TRUE, echo = TRUE)

intergroup_dating <- rio::import("https://osf.io/btzku/download", "sav")

metadata(intergroup_dating)$name <- "An evolutionary perspective on intergroup dating bias"

metadata(intergroup_dating)$description <- paste0("


### Download link
[Open Science Framework](https://osf.io/btzku/download)

")


metadata(intergroup_dating)$identifier <- "https://osf.io/6bwmq/"
metadata(intergroup_dating)$datePublished <- "2018-01-24"
metadata(intergroup_dating)$contributors <- list(
      "Samantha Brindley "," Melissa Marie McDonald "," Lisa Welling "," Virgil Zeigler-Hill ")
metadata(intergroup_dating)$citation <- " Samantha Brindley, Melissa M. McDonald, Lisa L. M. Welling & Virgil Zeigler-Hill (2018) An evolutionary perspective on intergroup dating bias, Comprehensive Results in Social Psychology, 3:1, 28-55, DOI: 10.1080/23743603.2018.1436939 "
metadata(intergroup_dating)$url <- "https://osf.io/btzku/"
metadata(intergroup_dating)$temporalCoverage <- "2018" 

metadata(intergroup_dating)$distribution = list(
  list("@type" = "DataDownload",
       "requiresSubscription" = "http://schema.org/True",
       "encodingFormat" = "https://www.loc.gov/preservation/digital/formats/fdd/fdd000469.shtml",
       contentUrl = "https://osf.io/btzku/download")
)

codebook_data <- intergroup_dating

val_labels(codebook_data$citizen) <- c("Yes" = 1, "No" = 2)
val_labels(codebook_data$education) <- c("1" = 1,
   "2" = 2, "3" = 3,  "4" = 4,  "5" = 5, "6" = 6, "7" = 7)
val_labels(codebook_data$MC1nationalitycorrect) <- c("wrong" = 0, "right" = 1)
val_labels(codebook_data$MC2incomecorrect) <- c("wrong" = 0, "right" = 1)
val_labels(codebook_data$MC3hobbiescorrect) <- c("wrong" = 0, "right" = 1)


codebook_data$risk_and_fear <- codebook_data %>% select(BehVig1:BehVig7, BehVig8r, BehVig9:BehVig25, BehVig26r:BehVig30r) %>% aggregate_and_document_scale()

codebook_data$mate_value <- codebook_data %>% select(matevalue1:matevalue5) %>% aggregate_and_document_scale()

dict <- rio::import("https://osf.io/uq98j/download", "xlsx")
# 
# var_label(codebook_data) <- dict %>% select(Variable, Label) %>% dict_to_list()

# omit the following lines, if your missing values are already properly labelled
codebook_data <- detect_missing(codebook_data,
    only_labelled = TRUE, # only labelled values are autodetected as
                                   # missing
    negative_values_are_missing = FALSE, # negative values are missing values
    ninety_nine_problems = TRUE,   # 99/999 are missing values, if they
                                   # are more than 5 MAD from the median
    )

# If you are not using formr, the codebook package needs to guess which items
# form a scale. The following line finds item aggregates with names like this:
# scale = scale_1 + scale_2R + scale_3R
# identifying these aggregates allows the codebook function to
# automatically compute reliabilities.
# However, it will not reverse items automatically.
codebook_data <- detect_scales(codebook_data)

codebook(codebook_data)

rubenarslan/codebook documentation built on Nov. 13, 2022, 12:40 p.m.