remove tabledataset

Author: CarloLucibello

docs/src/containers/overview.md

@@ -4,7 +4,6 @@ MLDatasets.jl contains several reusable data containers for accessing datasets i
 
 ```@docs
 FileDataset
-TableDataset
 CachedDataset
 MLDatasets.make_cache
 ```
@@ -13,6 +12,7 @@ MLDatasets.make_cache
 # TODO add back to docs when included again in the pkg
 HDF5Dataset
 Base.close(::HDF5Dataset)
+TableDataset
 JLD2Dataset
 Base.close(::JLD2Dataset) 
 -->

src/MLDatasets.jl

@@ -45,10 +45,10 @@ include("download.jl")
 
 include("containers/filedataset.jl")
 export FileDataset
-include("containers/tabledataset.jl")
-export TableDataset
 include("containers/cacheddataset.jl")
 export CachedDataset
+# include("containers/tabledataset.jl")
+# export TableDataset
 
 ## TODO add back when compatible with `@lazy` or `@require`
 ## which means that they cannot dispatch on types from JLD2 and HDF5

src/containers/tabledataset.jl

@@ -21,41 +21,36 @@ end
 TableDataset(table::T) where {T} = TableDataset{T}(table)
 TableDataset(path::AbstractString) = TableDataset(read_csv(path))
 
-# 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, :]
-
-# # 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))
-
-#     return NamedTuple{colnames}(rowvals)
-# 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
+
+# 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))
+
+    return NamedTuple{colnames}(rowvals)
+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)

test/runtests.jl

@@ -32,7 +32,7 @@ no_ci_dataset_tests = [
 
 container_tests = [
     "containers/filedataset.jl",
-    "containers/tabledataset.jl",
+    # "containers/tabledataset.jl",
     # "containers/hdf5dataset.jl",
     # "containers/jld2dataset.jl",
     "containers/cacheddataset.jl",