ImageShow and docs

Author: CarloLucibello

Project.toml

@@ -1,10 +1,9 @@
 name = "MLDatasets"
 uuid = "eb30cadb-4394-5ae3-aed4-317e484a6458"
-version = "0.6.0"
+version = "0.7.0"
 
 [deps]
 CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
-ColorTypes = "3da002f7-5984-5a60-b8a6-cbb66c0b333f"
 DataDeps = "124859b0-ceae-595e-8997-d05f6a7a8dfe"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 DelimitedFiles = "8bb1440f-4735-579b-a4ab-409b98df4dab"
@@ -13,7 +12,7 @@ FixedPointNumbers = "53c48c17-4a7d-5ca2-90c5-79b7896eea93"
 GZip = "92fee26a-97fe-5a0c-ad85-20a5f3185b63"
 Glob = "c27321d9-0574-5035-807b-f59d2c89b15c"
 HDF5 = "f67ccb44-e63f-5c2f-98bd-6dc0ccc4ba2f"
-ImageCore = "a09fc81d-aa75-5fe9-8630-4744c3626534"
+ImageShow = "4e3cecfd-b093-5904-9786-8bbb286a6a31"
 JLD2 = "033835bb-8acc-5ee8-8aae-3f567f8a3819"
 JSON3 = "0f8b85d8-7281-11e9-16c2-39a750bddbf1"
 LazyModules = "8cdb02fc-e678-4876-92c5-9defec4f444e"
@@ -27,15 +26,14 @@ Tables = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
 
 [compat]
 CSV = "0.10.2"
-ColorTypes = "0.11"
 DataDeps = "0.7"
 DataFrames = "1.3"
 FileIO = "1.14"
 FixedPointNumbers = "0.8"
 GZip = "0.5"
 Glob = "1.3"
 HDF5 = "0.16.2"
-ImageCore = "0.9"
+ImageShow = "0.3"
 JLD2 = "0.4.21"
 JSON3 = "1"
 LazyModules = "0.3"
@@ -48,7 +46,8 @@ Tables = "1.6"
 julia = "1.6"
 
 [extras]
+ColorTypes = "3da002f7-5984-5a60-b8a6-cbb66c0b333f"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 
 [targets]
-test = ["Test"]
+test = ["Test", "ColorTypes"]

docs/src/index.md

@@ -71,6 +71,8 @@ julia> summary(X_train)
 Input features are commonly denoted by `features`, while classification labels and regression targets are denoted by `targets`.
 
 ```julia-repl
+julia> using MLDatasets, DataFrames
+
 julia> iris = Iris()
 dataset Iris:
   metadata    =>    Dict{String, Any} with 4 entries
@@ -136,6 +138,38 @@ julia> iris.targets
 MLDatasets.jl garuantees compatibility with the [getobs](https://juliaml.github.io/MLUtils.jl/dev/api/#MLUtils.getobs) and [numobs](https://juliaml.github.io/MLUtils.jl/dev/api/#MLUtils.numobs) interface defined in [MLUtils.jl](https://github.com/JuliaML/MLUtils.jl).
 In practice, applying `getobs` and `numobs` on datasets is equivalent to applying indexing and `length`.
 
+## Conditional module loading
+
+MLDatasets.jl relies on many different packages in order to load and process the diverse type of
+datasets it supports. Most likely, any single user of the library will use a limited subset 
+of these functionalities. In order to reduce the time taken by `using MLDatasets` in users' code,
+we use a [lazy import system](https://github.com/johnnychen94/LazyModules.jl) that defers the import of packages inside MLDatasets.jl as much as possible.  
+For some of the packages like (e.g. `DataFrames.jl`) some manual intervention is needed from the user. 
+As an example, the following code will produce an error:
+```julia-repl
+julia> using MLDataset
+
+julia> MNIST(); # fine, MNIST doesn't requ
+```
+```julia-repl
+julia> using MLDataset
+
+julia> MNIST(); # fine, MNIST doesn't require DataFrames
+
+julia> Iris() # ERROR: Add `import DataFrames` or `using DataFrames` to your code to unlock this functionality.
+```
+As recommended by the error message we can easily fix the error with an additional import:
+```
+julia> using MLDataset, DataFrames
+
+julia> Iris()
+dataset Iris:
+  metadata    =>    Dict{String, Any} with 4 entries
+  features    =>    150×4 DataFrame
+  targets     =>    150×1 DataFrame
+  dataframe   =>    150×5 DataFrame
+```
+
 ## Download location
 
 MLDatasets.jl is build on top of the package

src/MLDatasets.jl

@@ -6,7 +6,6 @@ using Tables
 using DataDeps
 import MLUtils
 using MLUtils: getobs, numobs, AbstractDataContainer
-using ColorTypes
 using Glob
 using DelimitedFiles: readdlm
 using FileIO
@@ -22,7 +21,7 @@ include("require.jl") # export @require
 
 @require import JSON3="0f8b85d8-7281-11e9-16c2-39a750bddbf1"
 @require import DataFrames="a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
-@lazy import ImageCore="a09fc81d-aa75-5fe9-8630-4744c3626534"
+@require import ImageShow="4e3cecfd-b093-5904-9786-8bbb286a6a31"
 # @lazy import NPZ # lazy imported by FileIO
 @lazy import Pickle="fbb45041-c46e-462f-888f-7c521cafbc2c"
 @lazy import MAT="23992714-dd62-5051-b70f-ba57cb901cac"

src/containers/tabledataset.jl

@@ -21,35 +21,41 @@ end
 TableDataset(table::T) where {T} = TableDataset{T}(table)
 TableDataset(path::AbstractString) = TableDataset(read_csv(path))
 
-# slow accesses based on Tables.jl
-_getobs_row(x, i) = first(Iterators.peel(Iterators.drop(x, i - 1)))
-function _getobs_column(x, i)
-    colnames = Tuple(Tables.columnnames(x))
-    rowvals = ntuple(j -> Tables.getcolumn(x, j)[i], length(colnames))
+# see https://github.com/JuliaML/MLUtils.jl/issues/67
+# Assume the table provides a size and indexing interface (DataFrame does)
+# otherwise have to resort to very slow fallbacks
+numobs_table(x) = size(x, 1)
+getobs_table(x, i) = x[i, :]
 
-    return NamedTuple{colnames}(rowvals)
-end
+# # slow accesses based on Tables.jl
+# _getobs_row(x, i) = first(Iterators.peel(Iterators.drop(x, i - 1)))
+# function _getobs_column(x, i)
+#     colnames = Tuple(Tables.columnnames(x))
+#     rowvals = ntuple(j -> Tables.getcolumn(x, j)[i], length(colnames))
 
-function getobs_table(table, i)
-    if Tables.rowaccess(table)
-        return _getobs_row(Tables.rows(table), i)
-    elseif Tables.columnaccess(table)
-        return _getobs_column(table, i)
-    else
-        error("The Tables.jl implementation used should have either rowaccess or columnaccess.")
-    end
-end
+#     return NamedTuple{colnames}(rowvals)
+# end
 
-function numobs_table(table)
-    if Tables.columnaccess(table)
-        return length(Tables.getcolumn(table, 1))
-    elseif Tables.rowaccess(table)
-        # length might not be defined, but has to be for this to work.
-        return length(Tables.rows(table))
-    else
-        error("The Tables.jl implementation used should have either rowaccess or columnaccess.")
-    end
-end
+# function getobs_table(table, i)
+#     if Tables.rowaccess(table)
+#         return _getobs_row(Tables.rows(table), i)
+#     elseif Tables.columnaccess(table)
+#         return _getobs_column(table, i)
+#     else
+#         error("The Tables.jl implementation used should have either rowaccess or columnaccess.")
+#     end
+# end
+
+# function numobs_table(table)
+#     if Tables.columnaccess(table)
+#         return length(Tables.getcolumn(table, 1))
+#     elseif Tables.rowaccess(table)
+#         # length might not be defined, but has to be for this to work.
+#         return length(Tables.rows(table))
+#     else
+#         error("The Tables.jl implementation used should have either rowaccess or columnaccess.")
+#     end
+# end
 
 Base.getindex(dataset::TableDataset, i) = getobs_table(dataset.table, i)
 Base.length(dataset::TableDataset) = numobs_table(dataset.table)

src/datasets/text/udenglish.jl

@@ -22,7 +22,6 @@ function __init__udenglish()
         detail on the Website.
         """,
         "https://raw.githubusercontent.com/UniversalDependencies/UD_English-EWT/master/" .* [TRAINFILE, DEVFILE, TESTFILE],
-        "6df6ee25ab3cd1cde3a09ab075dcc6b8c90d18648eef0809f400be4ad8bc81e2"
     ))
 end
 

src/datasets/vision/cifar10.jl

@@ -165,7 +165,8 @@ convert2image(::Type{<:CIFAR10}, x::AbstractArray{<:Integer}) =
 function convert2image(::Type{<:CIFAR10}, x::AbstractArray{T,N}) where {T,N}
     @assert N == 3 || N == 4
     x = permutedims(x, (3, 2, 1, 4:N...))
-    return ImageCore.colorview(RGB, x)
+    ImageCore = ImageShow.ImageCore
+    return ImageCore.colorview(ImageCore.RGB, x)
 end
 
 

src/datasets/vision/mnist.jl

@@ -141,7 +141,8 @@ convert2image(::Type{<:MNIST}, x::AbstractArray{<:Integer}) =
 function convert2image(::Type{<:MNIST}, x::AbstractArray{T,N}) where {T,N}
     @assert N == 2 || N == 3
     x = permutedims(x, (2, 1, 3:N...))
-    return ImageCore.colorview(Gray, x)
+    ImageCore = ImageShow.ImageCore
+    return ImageCore.colorview(ImageCore.Gray, x)
 end
 
 # DEPRECATED INTERFACE, REMOVE IN v0.7 (or 0.6.x)

src/utils.jl

@@ -36,9 +36,6 @@ bytes_to_type(::Type{T}, A::Array{UInt8}) where T<:Integer = convert(Array{T}, A
 bytes_to_type(::Type{T}, A::Array{UInt8}) where T<:AbstractFloat = A ./ T(255)
 bytes_to_type(::Type{T}, A::Array{UInt8}) where T<:Number  = convert(Array{T}, reinterpret(N0f8, A))
 
-# see https://github.com/JuliaML/MLUtils.jl/issues/67
-numobs_table(x) = size(x, 1)
-getobs_table(x, i) = x[i, :]
 
 function clean_nt(nt::NamedTuple)
     res = (; (p for p in  pairs(nt) if p[2] !== nothing)...)

test.jl

@@ -0,0 +1,4 @@
+using TestImages
+x = testimage("cameraman")
+using ImageShow
+x