|
| 1 | +\name{penguins} |
| 2 | +\encoding{UTF-8} |
| 3 | +\docType{data} |
| 4 | +\title{Measurements of Penguins near Palmer Station, Antarctica} |
| 5 | +\alias{penguins} |
| 6 | +\alias{penguins_raw} |
| 7 | +\description{ |
| 8 | + Data on adult penguins covering three species found on three islands in the |
| 9 | + Palmer Archipelago, Antarctica, including their size |
| 10 | + (flipper length, body mass, bill dimensions), and sex. |
| 11 | + |
| 12 | + The columns of \code{penguins} are a subset of the more extensive |
| 13 | + \code{penguins_raw} data frame, which includes nesting observations |
| 14 | + and blood isotope data. There are differences in the column names |
| 15 | + and data types. See the \sQuote{Format} section for details. |
| 16 | +} |
| 17 | +\usage{ |
| 18 | +penguins |
| 19 | +penguins_raw |
| 20 | +} |
| 21 | +\format{ |
| 22 | + \code{penguins} is a data frame with 344 rows and 8 variables: |
| 23 | + \describe{ |
| 24 | + \item{\code{species}}{\code{\link{factor}}, with levels |
| 25 | + \code{Adelie}, \code{Chinstrap}, and \code{Gentoo}} |
| 26 | + \item{\code{island}}{\code{factor}, |
| 27 | + with levels \code{Biscoe}, \code{Dream}, and \code{Torgersen})} |
| 28 | + \item{\code{bill_len}}{\code{\link{numeric}}, bill length (millimeters)} |
| 29 | + \item{\code{bill_dep}}{\code{numeric}, bill depth (millimeters)} |
| 30 | + \item{\code{flipper_len}}{\code{\link{integer}}, flipper length (millimeters)} |
| 31 | + \item{\code{body_mass}}{\code{integer}, body mass (grams)} |
| 32 | + \item{\code{sex}}{\code{factor}, with levels \code{female} and \code{male}} |
| 33 | + \item{\code{year}}{\code{integer}, study year: 2007, 2008, or 2009} |
| 34 | + } |
| 35 | + |
| 36 | + \code{penguins_raw} is a data frame with 344 rows and 17 variables. |
| 37 | + 8 columns correspond to columns in \code{penguins}, |
| 38 | + though with different variable names and/or classes: |
| 39 | + \describe{ |
| 40 | + \item{\code{Species}}{\code{character}} |
| 41 | + \item{\code{Island}}{\code{character}} |
| 42 | + \item{\code{Culmen Length (mm)}}{\code{numeric}, bill length} |
| 43 | + \item{\code{Culmen Depth (mm)}}{\code{numeric}, bill depth} |
| 44 | + \item{\code{Flipper Length (mm)}}{\code{numeric}, flipper length} |
| 45 | + \item{\code{Body Mass (g)}}{\code{numeric}, body mass} |
| 46 | + \item{\code{Sex}}{\code{character}} |
| 47 | + \item{\code{Date Egg}}{\code{\link{Date}}, when study nest observed with 1 egg. |
| 48 | + The year component is the \code{year} column in \code{penguins}} |
| 49 | + } |
| 50 | + |
| 51 | + There are 9 further columns in \code{penguins_raw}: |
| 52 | + \describe{ |
| 53 | + \item{\code{studyName}}{\code{character}, expedition during which the data was collected} |
| 54 | + \item{\code{Sample Number}}{\code{numeric}, continuous numbering sequence for each sample} |
| 55 | + \item{\code{Region}}{\code{character}, the region of Palmer LTER sampling grid} |
| 56 | + \item{\code{Stage}}{\code{character}, denoting reproductive stage at sampling} |
| 57 | + \item{\code{Individual ID}}{\code{character}, unique ID for each individual in dataset} |
| 58 | + \item{\code{Clutch Completion}}{\code{character}, |
| 59 | + if the study nest was observed with a full clutch, i.e., 2 eggs} |
| 60 | + \item{\code{Delta 15 N (o/oo)}}{\code{numeric}, the ratio of stable isotopes 15N:14N} |
| 61 | + \item{\code{Delta 13 C (o/oo)}}{\code{numeric}, the ratio of stable isotopes 13C:12C} |
| 62 | + \item{\code{Comments}}{\code{character}, additional relevant information} |
| 63 | + } |
| 64 | +} |
| 65 | +\source{ |
| 66 | + \describe{ |
| 67 | + \item{\enc{Adélie}{Adelie} penguins:}{Palmer Station Antarctica LTER and K. Gorman (2020). |
| 68 | + Structural size measurements and isotopic signatures of foraging |
| 69 | + among adult male and female \enc{Adélie}{Adelie} penguins (Pygoscelis adeliae) |
| 70 | + nesting along the Palmer Archipelago near Palmer Station, 2007-2009 |
| 71 | + ver 5. Environmental Data Initiative, \doi{10.6073/pasta/98b16d7d563f265cb52372c8ca99e60f}.} |
| 72 | + |
| 73 | + \item{Gentoo penguins:}{Palmer Station Antarctica LTER and K. Gorman (2020). |
| 74 | + \doi{10.6073/pasta/7fca67fb28d56ee2ffa3d9370ebda689}.} |
| 75 | + |
| 76 | + \item{Chinstrap penguins:}{Palmer Station Antarctica LTER and K. Gorman (2020). |
| 77 | + \doi{10.6073/pasta/c14dfcfada8ea13a17536e73eb6fbe9e}.} |
| 78 | + } |
| 79 | + |
| 80 | + The title naming convention for the source for the Gentoo and Chinstrap |
| 81 | + data is that same as for \enc{Adélie}{Adelie} penguins. |
| 82 | +} |
| 83 | +\references{ |
| 84 | + Gorman, K. B., Williams, T. D. and Fraser, W. R. (2014) |
| 85 | + Ecological Sexual Dimorphism and Environmental Variability within a |
| 86 | + Community of Antarctic Penguins (Genus Pygoscelis). |
| 87 | + \emph{PLoS ONE} \bold{9}, 3, e90081; \doi{10.1371/journal.pone.0090081}. |
| 88 | + |
| 89 | + Horst, A. M., Hill, A. P. and Gorman, K. B. (2022) |
| 90 | + Palmer Archipelago Penguins Data in the palmerpenguins R Package |
| 91 | + - An Alternative to Anderson's Irises. |
| 92 | + \emph{R Journal} \bold{14}, 1; \doi{10.32614/RJ-2022-020}. |
| 93 | +
|
| 94 | + Kaye, E., Turner, H., Gorman, K. B., Horst, A. M. and Hill, A. P. (2025) |
| 95 | + Preparing the Palmer Penguins Data for the \pkg{datasets} Package in R. |
| 96 | + \doi{10.5281/zenodo.14902740}. |
| 97 | +} |
| 98 | +\details{ |
| 99 | + \bibcite{Gorman \abbr{et al.}\sspace(2014)} |
| 100 | + used the data to study sex dimorphism separately for the three species. |
| 101 | +
|
| 102 | + \bibcite{Horst \abbr{et al.}\sspace(2022)} popularized the data as an illustration |
| 103 | + for different statistical methods, as an alternative to the \code{\link{iris}} data. |
| 104 | +
|
| 105 | + \bibcite{Kaye \abbr{et al.}\sspace(2025)} provide the scripts used to create |
| 106 | + these data sets from the original source data, |
| 107 | + and a notebook reproducing results from \bibcite{Gorman \abbr{et al.}\sspace(2014)}. |
| 108 | +} |
| 109 | +\note{ |
| 110 | + These data sets are also available in the \CRANpkg{palmerpenguins} package. |
| 111 | + See the \href{https://allisonhorst.github.io/palmerpenguins/}{package website} |
| 112 | + for further details and resources. |
| 113 | +
|
| 114 | + The \code{penguins} data has some shorter variable names than the \bold{palmerpenguins} version, |
| 115 | + for compact code and data display. |
| 116 | +} |
| 117 | +\examples{ |
| 118 | +## view summaries |
| 119 | +summary(penguins) |
| 120 | +summary(penguins_raw) # not useful for character vectors |
| 121 | +## convert character vectors to factors first |
| 122 | +dFactor <- function(dat) { |
| 123 | + dat[] <- lapply(dat, \(.) if (is.character(.)) as.factor(.) else .) |
| 124 | + dat |
| 125 | +} |
| 126 | +summary(dFactor(penguins_raw)) |
| 127 | +
|
| 128 | +## visualise distribution across factors |
| 129 | +plot(island ~ species, data = penguins) |
| 130 | +plot(sex ~ interaction(island, species, sep = "\n"), data = penguins) |
| 131 | +
|
| 132 | +## bill depth vs. length by species (color) and sex (symbol): |
| 133 | +## positive correlations for all species, males tend to have bigger bills |
| 134 | +sym <- c(1, 16) |
| 135 | +pal <- c("darkorange","purple","cyan4") |
| 136 | +plot(bill_dep ~ bill_len, data = penguins, pch = sym[sex], col = pal[species]) |
| 137 | +
|
| 138 | +## simplified sex dimorphism analysis for Adelie species: |
| 139 | +## proportion of males increases with several size measurements |
| 140 | +adelie <- subset(penguins, species == "Adelie") |
| 141 | +plot(sex ~ bill_len, data = adelie) |
| 142 | +plot(sex ~ bill_dep, data = adelie) |
| 143 | +plot(sex ~ body_mass, data = adelie) |
| 144 | +m <- glm(sex ~ bill_len + bill_dep + body_mass, data = adelie, family = binomial) |
| 145 | +summary(m) |
| 146 | +
|
| 147 | +## Produce the long variable names as from {palmerpenguins} pkg: |
| 148 | +long_nms <- sub("len", "length_mm", |
| 149 | + sub("dep","depth_mm", |
| 150 | + sub("mass", "mass_g", colnames(penguins)))) |
| 151 | +## compare long and short names: |
| 152 | +noquote(rbind(long_nms, nms = colnames(penguins))) |
| 153 | +
|
| 154 | +\dontrun{ # << keeping shorter 'penguins' names in this example: |
| 155 | + colnames(penguins) <- long_nms |
| 156 | +} |
| 157 | +} |
| 158 | +\keyword{datasets} |
0 commit comments