Initial version

.github/workflows/ci.yml

@@ -1,7 +1,11 @@
 name: CI
+
 on:
-  - push
-  - pull_request
+  push:
+    branches:
+      - master
+  pull_request:
+
 jobs:
   test:
     name: Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }}
@@ -10,13 +14,12 @@ jobs:
       matrix:
         version:
           - '1.0'
-          - '1.4'
+          - '1'
           - 'nightly'
         os:
-          - ubuntu-latest
-          - macOS-latest
           - windows-latest
         arch:
+          - x86
           - x64
     steps:
       - uses: actions/checkout@v2
@@ -36,10 +39,3 @@ jobs:
             ${{ runner.os }}-
       - uses: julia-actions/julia-buildpkg@latest
       - uses: julia-actions/julia-runtest@latest
-      - uses: julia-actions/julia-processcoverage@v1
-      - uses: codecov/codecov-action@v1
-        with:
-          file: lcov.info
-      - uses: julia-actions/julia-uploadcoveralls@latest
-        env:
-          COVERALLS_TOKEN: ${{ secrets.COVERALLS_TOKEN }}

.travis.yml

@@ -1,34 +1,26 @@
 # Documentation: http://docs.travis-ci.com/user/languages/julia
 language: julia
-notifications:
-  email: false
-julia:
-  - 1.0
-  - 1.4
-  - nightly
+branches:
+  only:
+    - master
 os:
   - linux
   - osx
-  - windows
-arch:
-  - x64
+julia:
+  - 1.0
+  - 1
+  - nightly
 cache:
   directories:
     - ~/.julia/artifacts
-jobs:
-  fast_finish: true
+matrix:
   allow_failures:
     - julia: nightly
+  fast_finish: true
+notifications:
+  email: false
 after_success:
-  - |
-    julia -e '
-      using Pkg
-      Pkg.add("Coverage")
-      using Coverage
-      Codecov.submit(process_folder())'
-  - |
-    julia -e '
-      using Pkg
-      Pkg.add("Coverage")
-      using Coverage
-      Coveralls.submit(process_folder())'
+  - if [[ $TRAVIS_JULIA_VERSION = 1 ]] && [[ $TRAVIS_OS_NAME = linux ]]; then
+      julia -e 'using Pkg; Pkg.add("Coverage"); using Coverage; Codecov.submit(process_folder())';
+      julia -e 'using Pkg; Pkg.add("Coverage"); using Coverage; Coveralls.submit(process_folder())';
+    fi

CITATION.bib

@@ -1,8 +1,10 @@
-@misc{PalmerPenguins.jl,
-	author  = {David Widmann <dev+git@devmotion.de>},
-	title   = {PalmerPenguins.jl},
-	url     = {https://github.com/devmotion/PalmerPenguins.jl},
-	version = {v0.1.0},
-	year    = {2020},
-	month   = {6}
+@article{PalmerPenguins.jl-2014,
+    title = {Ecological Sexual Dimorphism and Environmental Variability within a Community of Antarctic Penguins (Genus Pygoscelis)},
+    author = {Gorman KB and Williams TD and Fraser WR},
+    journal = {PLoS ONE},
+    year = {2014},
+    volume = {9(3)},
+    number = {e90081},
+    pages = {-13},
+    url = {https://doi.org/10.1371/journal.pone.0090081},
 }

Project.toml

@@ -3,11 +3,19 @@ uuid = "8b842266-38fa-440a-9b57-31493939ab85"
 authors = ["David Widmann <[email protected]>"]
 version = "0.1.0"
 
+[deps]
+CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
+DataDeps = "124859b0-ceae-595e-8997-d05f6a7a8dfe"
+
 [compat]
+CSV = "0.7.1"
+DataDeps = "0.7.2"
 julia = "1"
 
 [extras]
+DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
+Tables = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 
 [targets]
-test = ["Test"]
+test = ["DataFrames", "Tables", "Test"]

README.md

@@ -1,6 +1,62 @@
-# PalmerPenguins
+# PalmerPenguins.jl <a href='https://allisonhorst.github.io/palmerpenguins'><img src='man/figures/logo.png' align="right" height="138.5" /></a>
 
 [![Build Status](https://github.com/devmotion/PalmerPenguins.jl/workflows/CI/badge.svg)](https://github.com/devmotion/PalmerPenguins.jl/actions)
 [![Build Status](https://travis-ci.com/devmotion/PalmerPenguins.jl.svg?branch=master)](https://travis-ci.com/devmotion/PalmerPenguins.jl)
 [![Coverage](https://codecov.io/gh/devmotion/PalmerPenguins.jl/branch/master/graph/badge.svg)](https://codecov.io/gh/devmotion/PalmerPenguins.jl)
 [![Coverage](https://coveralls.io/repos/github/devmotion/PalmerPenguins.jl/badge.svg?branch=master)](https://coveralls.io/github/devmotion/PalmerPenguins.jl?branch=master)
+
+Load the [Palmer penguins dataset](https://allisonhorst.github.io/palmerpenguins/) in Julia.
+
+## Overview
+
+The [Palmer penguins dataset](https://allisonhorst.github.io/palmerpenguins/) by Allison
+Horst, Alison Hill, and Kristen Gorman is a dataset for data exploration & visualization,
+as an alternative to the Iris dataset.
+
+The dataset contains data for 344 penguins. There are 3 different species of penguins in
+this dataset, collected from 3 islands in the Palmer Archipelago, Antarctica.
+
+Data were collected and made available by
+[Dr. Kristen Gorman](https://www.uaf.edu/cfos/people/faculty/detail/kristen-gorman.php)
+and the [Palmer Station, Antarctica LTER](https://pal.lternet.edu/), a member of the
+[Long Term Ecological Research Network](https://lternet.edu/).
+
+Data are available by
+[CC-0](https://creativecommons.org/share-your-work/public-domain/cc0/) license in
+accordance with the [Palmer Station LTER Data Policy](http://pal.lternet.edu/data/policies)
+and the
+[LTER Data Access Policy for Type I data](https://lternet.edu/data-access-policy/).
+
+More information about the dataset is available in
+[its official documentation](https://allisonhorst.github.io/palmerpenguins/).
+
+## Usage
+
+The dataset can be loaded by
+
+```julia-repl
+julia> using PalmerPenguins
+
+julia> table = PalmerPenguins.load()
+```
+
+This will download the dataset once using [DataDeps.jl](https://github.com/oxinabox/DataDeps.jl),
+displaying the information above and making it available for future use. The function
+`PalmerPenguins.load()` returns a
+[`CSV.File`](https://juliadata.github.io/CSV.jl/stable/#CSV.File) object that supports the
+[Tables.jl](https://github.com/JuliaData/Tables.jl) interface. For instance, it can be
+converted to a
+[`DataFrame`](https://juliadata.github.io/DataFrames.jl/stable/man/getting_started/#The-DataFrame-Type-1)
+by executing
+
+```julia-repl
+julia> using DataFrames
+
+julia> df = DataFrame(table)
+```
+
+## Bibliography
+
+Gorman KB, Williams TD, Fraser WR (2014) Ecological Sexual Dimorphism and Environmental
+Variability within a Community of Antarctic Penguins (Genus Pygoscelis). PLoS ONE 9(3):
+e90081. https://doi.org/10.1371/journal.pone.0090081

src/PalmerPenguins.jl

@@ -1,5 +1,53 @@
 module PalmerPenguins
 
-# Write your package code here.
+import CSV
+import DataDeps
+
+const DEPNAME = "PalmerPenguins"
+const LINK = "https://cdn.jsdelivr.net/gh/allisonhorst/palmerpenguins@f13c212d42c1341167368dc225df191c5a6029b9/data-raw/"
+const DATA = "penguins.csv"
+const INFO =
+"""
+Dataset: The Palmer penguins dataset
+Authors: Allison Horst, Alison Hill, Kristen Gorman
+Website: https://allisonhorst.github.io/palmerpenguins/index.html
+
+The Palmer penguins dataset is a dataset for data exploration & visualization, as an
+alternative to the Iris dataset.
+        
+The dataset contains data for 344 penguins. There are 3 different species of penguins in
+this dataset, collected from 3 islands in the Palmer Archipelago, Antarctica.
+
+Data were collected and made available by
+[Dr. Kristen Gorman](https://www.uaf.edu/cfos/people/faculty/detail/kristen-gorman.php)
+and the [Palmer Station, Antarctica LTER](https://pal.lternet.edu/), a member of the
+[Long Term Ecological Research Network](https://lternet.edu/).
+
+Data are available by
+[CC-0](https://creativecommons.org/share-your-work/public-domain/cc0/) license in
+accordance with the [Palmer Station LTER Data Policy](http://pal.lternet.edu/data/policies)
+and the
+[LTER Data Access Policy for Type I data](https://lternet.edu/data-access-policy/).
+
+Please include this citation if you plan to use this database:
+[Gorman et al., 2014]
+    Gorman KB, Williams TD, Fraser WR (2014) Ecological Sexual Dimorphism and Environmental
+    Variability within a Community of Antarctic Penguins (Genus Pygoscelis). PLoS ONE 9(3):
+    e90081. https://doi.org/10.1371/journal.pone.0090081
+"""
+
+function load()
+    file = DataDeps.@datadep_str DEPNAME * "/" * DATA
+    return CSV.File(file; missingstring="NA")
+end
+
+function __init__()
+    DataDeps.register(DataDeps.DataDep(
+        DEPNAME,
+        INFO,
+        LINK * DATA,
+        "97d467baa3522040aa892fa7f2ff57b5195be5fef3cceca3f78a6b1a6e32d7a2",
+    ))
+end
 
 end

test/runtests.jl

@@ -1,6 +1,71 @@
 using PalmerPenguins
+using CSV
+using DataFrames
+using Tables
 using Test
 
+# Always accept download in CI tests
+ENV["DATADEPS_ALWAYS_ACCEPT"] = true
+
 @testset "PalmerPenguins.jl" begin
-    # Write your tests here.
+    @testset "load" begin
+        table = PalmerPenguins.load()
+
+        # Check some properties
+        @test table isa CSV.File
+        @test length(table) == 344
+        @test Tables.columnnames(Tables.columns(table)) == [
+            :species,
+            :island,
+            :bill_length_mm,
+            :bill_depth_mm,
+            :flipper_length_mm,
+            :body_mass_g,
+            :sex,
+        ]
+
+        # Check first row
+        firstrow = first(table)
+        @test firstrow.species == "Adelie"
+        @test firstrow.island == "Torgersen"
+        @test firstrow.bill_length_mm == 39.1
+        @test firstrow.bill_depth_mm == 18.7
+        @test firstrow.flipper_length_mm == 181
+        @test firstrow.body_mass_g == 3750
+        @test firstrow.sex == "male"
+    end
+
+    @testset "DataFrames" begin
+        df = DataFrame(PalmerPenguins.load())
+
+        # Check some properties
+        @test df isa DataFrame
+        @test nrow(df) == 344
+        @test names(df) == [
+            "species",
+            "island",
+            "bill_length_mm",
+            "bill_depth_mm",
+            "flipper_length_mm",
+            "body_mass_g",
+            "sex",
+        ]
+        @test eltype(df[!, :species]) === String
+        @test eltype(df[!, :island]) === String
+        @test eltype(df[!, :bill_length_mm]) === Union{Missing,Float64}
+        @test eltype(df[!, :bill_depth_mm]) === Union{Missing,Float64}
+        @test eltype(df[!, :flipper_length_mm]) === Union{Missing,Int}
+        @test eltype(df[!, :body_mass_g]) === Union{Missing,Int}
+        @test eltype(df[!, :sex]) === Union{Missing,String}
+
+        # Check first row
+        firstrow = df[1, :]
+        @test firstrow.species == "Adelie"
+        @test firstrow.island == "Torgersen"
+        @test firstrow.bill_length_mm == 39.1
+        @test firstrow.bill_depth_mm == 18.7
+        @test firstrow.flipper_length_mm == 181
+        @test firstrow.body_mass_g == 3750
+        @test firstrow.sex == "male"
+    end
 end