library(scienceverse)
#>
#> ************
#> Welcome to scienceverse For support and examples visit:
#> http://scienceverse.github.io/
#> - Get and set global package options with: scienceverse_options()
#> ************Codebooks in scienceverse follow the Psych-DS 0.1.0 format by default
as set up in the function faux::codebook(), although you
can manually add your own codebook to the JSON file.
When you add simulated data to a study object, the codebook is generated by default.
study <- study("Demo") %>%
add_sim_data("pets",
between = list(pet = c(cat = "Cat Owners",
dog = "Dog Owners")),
n = c(4, 6),
dv = list(happy = "Happiness Score"),
id = list(id = "Subject ID"),
mu = c(10, 12),
sd = 4)
#> id set to dataType string
#> pet set to dataType string
#> happy set to dataType floatYou can retrieve the codebook with the function
get_codebook(). If you don’t specify the data_id, it
defaults to the first data set in the study.
cb <- get_codebook(study, data_id = "pets")If you just type the codebook object into the console, you’ll see the info formatted like this.
cb
#> Codebook for pets (Psych-DS 0.1.0)
#>
#> Dataset Parameters
#>
#> * name: pets
#> * schemaVersion: Psych-DS 0.1.0
#>
#> Column Parameters
#>
#> * id (string): Subject ID
#> * pet (string)
#> * Levels
#> * cat: Cat Owners
#> * dog: Dog Owners
#> * Ordered: FALSE
#> * happy (float): Happiness ScoreBut the codebook is actually a nested list formatted like this:
str(cb)
#> List of 5
#> $ @context : chr "https://schema.org/"
#> $ @type : chr "Dataset"
#> $ name : chr "pets"
#> $ schemaVersion : chr "Psych-DS 0.1.0"
#> $ variableMeasured:List of 3
#> ..$ :List of 4
#> .. ..$ @type : chr "PropertyValue"
#> .. ..$ name : chr "id"
#> .. ..$ description: chr "Subject ID"
#> .. ..$ dataType : chr "string"
#> ..$ :List of 6
#> .. ..$ @type : chr "PropertyValue"
#> .. ..$ name : chr "pet"
#> .. ..$ description : chr "pet"
#> .. ..$ levels :List of 2
#> .. .. ..$ cat: chr "Cat Owners"
#> .. .. ..$ dog: chr "Dog Owners"
#> .. ..$ dataType : chr "string"
#> .. ..$ levelsOrdered: logi FALSE
#> ..$ :List of 4
#> .. ..$ @type : chr "PropertyValue"
#> .. ..$ name : chr "happy"
#> .. ..$ description: chr "Happiness Score"
#> .. ..$ dataType : chr "float"
#> - attr(*, "class")= chr [1:2] "psychds_codebook" "list"You can also view it in JSON format.
get_codebook(study, data_id = "pets", as_json = TRUE)
#> {
#> "@context": "https://schema.org/",
#> "@type": "Dataset",
#> "name": "pets",
#> "schemaVersion": "Psych-DS 0.1.0",
#> "variableMeasured": [
#> {
#> "@type": "PropertyValue",
#> "name": "id",
#> "description": "Subject ID",
#> "dataType": "string"
#> },
#> {
#> "@type": "PropertyValue",
#> "name": "pet",
#> "description": "pet",
#> "levels": {
#> "cat": "Cat Owners",
#> "dog": "Dog Owners"
#> },
#> "dataType": "string",
#> "levelsOrdered": false
#> },
#> {
#> "@type": "PropertyValue",
#> "name": "happy",
#> "description": "Happiness Score",
#> "dataType": "float"
#> }
#> ]
#> }
#> You can run the codebook function on existing data, but will need to manually input some things. For now, the supported properties are: “description”, “privacy”, “dataType”, “propertyID”, “minValue”, “maxValue”, “levels”, “levelsOrdered”, “na”, “naValue”, “alternateName”, “unitCode” and “unitText”. You can set unsupported properties, but this will produce a warning.
vardesc <- list(
description = list(
mpg = "Miles/(US) gallon",
cyl = "Number of cylinders",
disp = "Displacement (cu.in.)",
hp = "Gross horsepower",
drat = "Rear axle ratio",
wt = "Weight (1000 lbs)",
qsec = "1/4 mile time",
vs = "Engine (0 = V-shaped, 1 = straight)",
am = "Transmission (0 = automatic, 1 = manual)",
gear = "Number of forward gears",
carb = "Number of carburetors"
),
# min and max values can be set manually or from data
# min and max are often outside the observed range
minValue = list(mpg = 0, cyl = min(mtcars$cyl)),
maxValue = list(cyl = max(mtcars$cyl)),
levels = list(
vs = c("0" = "V-shaped", "1" = "straight"),
am = c("0" = "automatic", "1" = "manual")
),
dataType = list(
cyl = "integer",
hp = "integer",
vs = "factor",
am = "factor",
gear = "integer",
carb = "integer"
)
)
codebook(mtcars, "Motor Trend Car Road Tests", vardesc)
#> mpg set to dataType float
#> disp set to dataType float
#> drat set to dataType float
#> wt set to dataType float
#> qsec set to dataType float
#> {
#> "@context": "https://schema.org/",
#> "@type": "Dataset",
#> "name": "Motor Trend Car Road Tests",
#> "schemaVersion": "Psych-DS 0.1.0",
#> "variableMeasured": [
#> {
#> "@type": "PropertyValue",
#> "name": "mpg",
#> "description": "Miles/(US) gallon",
#> "minValue": 0,
#> "dataType": "float"
#> },
#> {
#> "@type": "PropertyValue",
#> "name": "cyl",
#> "description": "Number of cylinders",
#> "minValue": 4,
#> "maxValue": 8,
#> "dataType": "int"
#> },
#> {
#> "@type": "PropertyValue",
#> "name": "disp",
#> "description": "Displacement (cu.in.)",
#> "dataType": "float"
#> },
#> {
#> "@type": "PropertyValue",
#> "name": "hp",
#> "description": "Gross horsepower",
#> "dataType": "int"
#> },
#> {
#> "@type": "PropertyValue",
#> "name": "drat",
#> "description": "Rear axle ratio",
#> "dataType": "float"
#> },
#> {
#> "@type": "PropertyValue",
#> "name": "wt",
#> "description": "Weight (1000 lbs)",
#> "dataType": "float"
#> },
#> {
#> "@type": "PropertyValue",
#> "name": "qsec",
#> "description": "1/4 mile time",
#> "dataType": "float"
#> },
#> {
#> "@type": "PropertyValue",
#> "name": "vs",
#> "description": "Engine (0 = V-shaped, 1 = straight)",
#> "levels": {
#> "0": "V-shaped",
#> "1": "straight"
#> },
#> "dataType": "string",
#> "levelsOrdered": false
#> },
#> {
#> "@type": "PropertyValue",
#> "name": "am",
#> "description": "Transmission (0 = automatic, 1 = manual)",
#> "levels": {
#> "0": "automatic",
#> "1": "manual"
#> },
#> "dataType": "string",
#> "levelsOrdered": false
#> },
#> {
#> "@type": "PropertyValue",
#> "name": "gear",
#> "description": "Number of forward gears",
#> "dataType": "int"
#> },
#> {
#> "@type": "PropertyValue",
#> "name": "carb",
#> "description": "Number of carburetors",
#> "dataType": "int"
#> }
#> ]
#> }
#>