Fix tests and add Tables.jl interface

Author: darsnack

src/containers/tabledataset.jl

@@ -56,3 +56,10 @@ Base.length(dataset::TableDataset{<:DataFrame}) = nrow(dataset.table)
 # fast access for CSV.File
 Base.getindex(dataset::TableDataset{<:CSV.File}, i) = dataset.table[i]
 Base.length(dataset::TableDataset{<:CSV.File}) = length(dataset.table)
+
+## Tables.jl interface
+
+Tables.istable(::TableDataset) = true
+for fn in (:rowaccess, :rows, :columnaccess, :columns, :schema, :materializer)
+    @eval Tables.$fn(dataset::TableDataset) = Tables.$fn(dataset.table)
+end

test/containers/cacheddataset.jl

@@ -1,7 +1,7 @@
 @testset "CachedDataset" begin
     @testset "CachedDataset(::FileDataset)" begin
         files = setup_filedataset_test()
-        fdataset = FileDataset("root", "*.csv")
+        fdataset = FileDataset(f -> CSV.read(f, DataFrame), "root", "*.csv")
         cdataset = CachedDataset(fdataset)
 
         @test numobs(cdataset) == numobs(fdataset)

test/containers/filedataset.jl

@@ -27,10 +27,10 @@ cleanup_filedataset_test() = rm("root"; recursive = true)
 
 @testset "FileDataset" begin
     files = setup_filedataset_test()
-    dataset = FileDataset("root", "*.csv")
+    dataset = FileDataset(f -> CSV.read(f, DataFrame), "root", "*.csv")
     @test numobs(dataset) == length(files)
     for (i, file) in enumerate(files)
-        true_obs = MLDatasets.loadfile(file)
+        true_obs = CSV.read(file, DataFrame)
         @test getobs(dataset, i) == true_obs
     end
     cleanup_filedataset_test()

test/containers/tabledataset.jl

@@ -50,4 +50,22 @@
         @test numobs(td) == 1
         rm("test.csv")
     end
+
+    @testset "TableDataset is a table" begin
+        testtable = DataFrame(
+            col1 = [1, 2, 3, 4, 5],
+            col2 = ["a", "b", "c", "d", "e"],
+            col3 = [10, 20, 30, 40, 50],
+            col4 = ["A", "B", "C", "D", "E"],
+            col5 = [100.0, 200.0, 300.0, 400.0, 500.0],
+            split = ["train", "train", "train", "valid", "valid"],
+        )
+        td = TableDataset(testtable)
+        @testset for fn in (Tables.istable,
+                            Tables.rowaccess, Tables.rows,
+                            Tables.columnaccess, Tables.columns,
+                            Tables.schema, Tables.materializer)
+            @test fn(td) == fn(testtable)
+        end
+    end
 end

test/runtests.jl

@@ -1,5 +1,6 @@
 using Test
 using MLDatasets
+using FileIO
 using ImageCore
 using DataDeps
 using DataFrames, CSV, Tables