Update data, and raw option, add docs + tests (#1)

devmotion · web-flow · commit 1fac8313ef0c · 2020-07-02T02:28:05.000+02:00
diff --git a/Project.toml b/Project.toml
@@ -1,7 +1,7 @@
 name = "PalmerPenguins"
 uuid = "8b842266-38fa-440a-9b57-31493939ab85"
 authors = ["David Widmann <dev+git@devmotion.de>"]
-version = "0.1.0"
+version = "0.1.1"
 
 [deps]
 CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
@@ -14,8 +14,9 @@ julia = "1"
 
 [extras]
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
+Dates = "ade2ca70-3891-5945-98fb-dc099432e06a"
 Tables = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 
 [targets]
-test = ["DataFrames", "Tables", "Test"]
+test = ["DataFrames", "Dates", "Tables", "Test"]
diff --git a/README.md b/README.md
@@ -33,28 +33,32 @@ More information about the dataset is available in
 
 ## Usage
 
-The dataset can be loaded by
-
+The simplified version of the raw data can be loaded by
 ```julia
 julia> using PalmerPenguins
 
 julia> table = PalmerPenguins.load()
 ```
-
-This will download the dataset once using [DataDeps.jl](https://github.com/oxinabox/DataDeps.jl),
+This will download the data (both the simplified and the raw version) 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
 julia> using DataFrames
 
-julia> df = DataFrame(table)
+julia> df = DataFrame(table; copycols = false) # or: df = DataFrame!(table)
+```
+
+The raw data can be loaded with
+```julia
+julia> tableraw = PalmerPenguins.load(; raw = true)
 ```
+If `raw = false` (the default), then the simplified version is returned.
 
 ## Bibliography
 
diff --git a/src/PalmerPenguins.jl b/src/PalmerPenguins.jl
@@ -4,8 +4,8 @@ import CSV
 import DataDeps
 
 const DEPNAME = "PalmerPenguins"
-const LINK = "https://cdn.jsdelivr.net/gh/allisonhorst/palmerpenguins@f13c212d42c1341167368dc225df191c5a6029b9/data-raw/"
-const DATA = "penguins.csv"
+const LINK = "https://cdn.jsdelivr.net/gh/allisonhorst/palmerpenguins@433439c8b013eff3d36c847bb7a27fa0d7e353d8/inst/extdata/"
+const DATA = ["penguins.csv", "penguins_raw.csv"]
 const INFO =
 """
 Dataset: The Palmer penguins dataset
@@ -14,7 +14,7 @@ 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.
 
@@ -36,17 +36,35 @@ Please include this citation if you plan to use this database:
     e90081. https://doi.org/10.1371/journal.pone.0090081
 """
 
-function load()
-    file = DataDeps.@datadep_str DEPNAME * "/" * DATA
-    return CSV.File(file; missingstring="NA")
+"""
+    load([; raw = false])
+
+Load the Palmer penguins dataset.
+
+If `raw` is `true`, then the raw data is returned. Otherwise the simplified version of
+the data is loaded.
+
+# References
+
+[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(; raw::Bool = false)
+    file = DataDeps.@datadep_str DEPNAME * "/" * DATA[1 + Int(raw)]
+    return CSV.File(
+        file;
+        missingstring="NA", truestrings=["Yes"], falsestrings=["No"], dateformat="y-m-d",
+    )
 end
 
 function __init__()
     DataDeps.register(DataDeps.DataDep(
         DEPNAME,
         INFO,
-        LINK * DATA,
-        "97d467baa3522040aa892fa7f2ff57b5195be5fef3cceca3f78a6b1a6e32d7a2",
+        LINK .* DATA,
+        "839b058be09b164f7dfa0d030a959cb3c5426dea281e8a34d34c557e398bd01f",
     ))
 end
 
diff --git a/test/runtests.jl b/test/runtests.jl
@@ -2,70 +2,181 @@ using PalmerPenguins
 using CSV
 using DataFrames
 using Tables
+
+using Dates
 using Test
 
 # Always accept download in CI tests
 ENV["DATADEPS_ALWAYS_ACCEPT"] = true
 
 @testset "PalmerPenguins.jl" begin
+    # column names
+    colnames_simplified = [
+        "species",
+        "island",
+        "bill_length_mm",
+        "bill_depth_mm",
+        "flipper_length_mm",
+        "body_mass_g",
+        "sex",
+    ]
+    coleltypes_simplified = [
+        String,
+        String,
+        Union{Missing,Float64},
+        Union{Missing,Float64},
+        Union{Missing,Int64},
+        Union{Missing,Int64},
+        Union{Missing,String},
+    ]
+    firstrow_simplified = [
+        "Adelie",
+        "Torgersen",
+        39.1,
+        18.7,
+        Int64(181),
+        Int64(3750),
+        "male"
+    ]
+
+    colnames_raw = [
+        "studyName",
+        "Sample Number",
+        "Species",
+        "Region",
+        "Island",
+        "Stage",
+        "Individual ID",
+        "Clutch Completion",
+        "Date Egg",
+        "Culmen Length (mm)",
+        "Culmen Depth (mm)",
+        "Flipper Length (mm)",
+        "Body Mass (g)",
+        "Sex",
+        "Delta 15 N (o/oo)",
+        "Delta 13 C (o/oo)",
+        "Comments",
+    ]
+    coleltypes_raw = [
+        String,
+        Int64,
+        String,
+        String,
+        String,
+        String,
+        Bool,
+        Date,
+        Union{Missing,Float64},
+        Union{Missing,Float64},
+        Union{Missing,Int64},
+        Union{Missing,Int64},
+        Union{Missing,String},
+        Float64,
+        Float64,
+        String,
+    ]
+    firstrow_raw = [
+        "PAL0708",
+        Int64(1),
+        "Adelie Penguin (Pygoscelis adeliae)",
+        "Anvers",
+        "Torgersen",
+        "Adult, 1 Egg Stage",
+        "N1A1",
+        true,
+        Date(2007, 11, 11),
+        39.1,
+        18.7,
+        Int64(181),
+        Int64(3750),
+        "MALE",
+        missing,
+        missing,
+        "Not enough blood for isotopes.",
+    ]
+
     @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"
+        @testset "simplified" begin
+            table = PalmerPenguins.load()
+            table2 = PalmerPenguins.load(; raw = false)
+            for i in 1:length(table)
+                @test all(table[i] .=== table2[i])
+            end
+
+            # Check some properties
+            @test table isa CSV.File
+            @test length(table) == 344
+            @test Tables.columnnames(Tables.columns(table)) == Symbol.(colnames_simplified)
+            for (name, T) in zip(colnames_simplified, coleltypes_simplified)
+                eltype(Tables.getcolumn(Tables.columns(table), Symbol(name))) === T
+            end
+
+            # Check first row
+            firstrow = first(table)
+            for i in 1:length(firstrow)
+                @test firstrow[i] === firstrow_simplified[i]
+            end
+        end
+
+        @testset "raw" begin
+            table = PalmerPenguins.load(; raw = true)
+
+            # Check some properties
+            @test table isa CSV.File
+            @test length(table) == 344
+            @test Tables.columnnames(Tables.columns(table)) == Symbol.(colnames_raw)
+            for (name, T) in zip(colnames_raw, coleltypes_raw)
+                eltype(Tables.getcolumn(Tables.columns(table), Symbol(name))) === T
+            end
+
+            # Check first row
+            firstrow = first(table)
+            for i in 1:length(firstrow)
+                @test firstrow[i] === firstrow_raw[i]
+            end
+        end
     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,Int64}
-        @test eltype(df[!, :body_mass_g]) === Union{Missing,Int64}
-        @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"
+        @testset "simplified" begin
+            df = DataFrame!(PalmerPenguins.load())
+            df2 = DataFrame!(PalmerPenguins.load(; raw = false))
+            for i in 1:size(df, 2)
+                @test all(df[!, i] .=== df2[!, i])
+            end
+
+            # Check some properties
+            @test df isa DataFrame
+            @test nrow(df) == 344
+            @test names(df) == colnames_simplified
+            for (name, T) in zip(colnames_simplified, coleltypes_simplified)
+                eltype(df[!, name]) === T
+            end
+
+            # Check first row
+            firstrow = df[1, :]
+            for i in 1:length(firstrow)
+                @test firstrow[i] === firstrow_simplified[i]
+            end
+        end
+
+        @testset "raw" begin
+            df = DataFrame!(PalmerPenguins.load(; raw = true))
+
+            # Check some properties
+            @test df isa DataFrame
+            @test nrow(df) == 344
+            @test names(df) == colnames_raw
+            for (name, T) in zip(colnames_raw, coleltypes_raw)
+                eltype(df[!, name]) === T
+            end
+
+            # Check first row
+            firstrow = df[1, :]
+            for i in 1:length(firstrow)
+                @test firstrow[i] === firstrow_raw[i]
+            end
+        end
     end
 end
