update to DataFrames 0.8+

* drop Julia 0.4 support (since DataFrames require Julia 0.5)
* convert from using DataArrays to NullableArrays

Author: alyst

.travis.yml

@@ -3,7 +3,6 @@ os:
   - linux
   - osx
 julia:
-  - 0.4
   - 0.5
   - nightly
 notifications:

NEWS.md

@@ -1,3 +1,12 @@
+## RData v0.1.0 Release Notes
+
+Updated to DataFrames 0.9, dropped Julia v0.4
+
+##### Changes
+* using NullableArrays.jl and CategoricalArrays.jl
+instead of DataArrays.jl ([#19], see [JuliaStats/DataFrames.jl#1008])
+* Julia v0.4 not supported (DataFrames.jl v0.9 requirements)
+
 ## RData v0.0.4 Release Notes
 
 Now the recommended way to load `.RData`/`.rda` files is by `FileIO.load()`.
@@ -15,5 +24,7 @@ Initial release based on `DataFrames.read_rda()` ([JuliaStats/DataFrames.jl#1031
 [#9]: https://github.com/JuliaStats/RData.jl/issues/9
 [#10]: https://github.com/JuliaStats/RData.jl/issues/10
 [#15]: https://github.com/JuliaStats/RData.jl/issues/15
+[#19]: https://github.com/JuliaStats/RData.jl/issues/19
 
+[JuliaStats/DataFrames.jl#1008]: https://github.com/JuliaStats/DataFrames.jl/pull/1008
 [JuliaStats/DataFrames.jl#1031]: https://github.com/JuliaStats/DataFrames.jl/pull/1031

REQUIRE

@@ -1,6 +1,5 @@
-julia 0.4
-DataFrames 0.7
-DataArrays 0.3
+julia 0.5
+DataFrames 0.8+
 FileIO 0.1.2
 GZip 0.2
 Compat 0.8

appveyor.yml

@@ -1,7 +1,5 @@
 environment:
   matrix:
-  - JULIAVERSION: "julialang/bin/winnt/x86/0.4/julia-0.4-latest-win32.exe"
-  - JULIAVERSION: "julialang/bin/winnt/x64/0.4/julia-0.4-latest-win64.exe"
   - JULIAVERSION: "julialang/bin/winnt/x86/0.5/julia-0.5-latest-win32.exe"
   - JULIAVERSION: "julialang/bin/winnt/x64/0.5/julia-0.5-latest-win64.exe"
   - JULIAVERSION: "julianightlies/bin/winnt/x86/julia-latest-win32.exe"

src/RData.jl

@@ -3,7 +3,6 @@ __precompile__()
 module RData
 
 using Compat, DataFrames, GZip, FileIO
-import DataArrays: data
 import DataFrames: identifier
 import Compat: UTF8String, unsafe_string
 import FileIO: load

src/convert.jl

@@ -11,33 +11,48 @@ end
 
 ##############################################################################
 ##
-## Conversion of intermediate R objects into DataArray and DataFrame objects
+## Conversion of intermediate R objects into NullableArray and DataFrame objects
 ##
 ##############################################################################
 
-namask(rl::RLogicalVector) = BitArray(rl.data .== R_NA_INT32)
-namask(ri::RIntegerVector) = BitArray(ri.data .== R_NA_INT32)
-namask(rn::RNumericVector) = BitArray(map(isna_float64, reinterpret(UInt64, rn.data)))
+namask(rl::RLogicalVector) = [flag == R_NA_INT32 for flag in rl.data]
+namask(ri::RIntegerVector) = [flag == R_NA_INT32 for flag in ri.data]
+namask(rn::RNumericVector) = map(isna_float64, reinterpret(UInt64, rn.data))
 # if re or im is NA, the whole complex number is NA
 # FIXME avoid temporary Vector{Bool}
-namask(rc::RComplexVector) = BitArray([isna_float64(v.re) || isna_float64(v.im) for v in reinterpret(Complex{UInt64}, rc.data)])
+namask(rc::RComplexVector) = [isna_float64(v.re) || isna_float64(v.im) for v in reinterpret(Complex{UInt64}, rc.data)]
 namask(rv::RNullableVector) = rv.na
 
-DataArrays.data(rv::RVEC) = DataArray(rv.data, namask(rv))
+function _julia_vector(rv::RVEC, force_nullable::Bool)
+    na_mask = namask(rv)
+    (force_nullable || any(na_mask)) ? NullableArray(rv.data, na_mask) : rv.data
+end
+
+# convert R vector into either NullableArray
+# or Array if force_nullable=false and there are no NAs
+julia_vector(rv::RVEC, force_nullable::Bool) = _julia_vector(rv, force_nullable)
+
+# converts Vector{Int32} into Vector{R} replacing R_NA_INT32 with 0
+na2zero{R}(::Type{R}, v::Vector{Int32}) = [x != R_NA_INT32 ? R(x) : zero(R) for x in v]
+
+# convert to [Nullable]CategoricalArray{String} if `ri`is a factor,
+# or to [Nullable]Array{Int32} otherwise
+function julia_vector(ri::RIntegerVector, force_nullable::Bool)
+    !isfactor(ri) && return _julia_vector(ri, force_nullable) # not a factor
 
-function DataArrays.data(ri::RIntegerVector)
-    if !isfactor(ri) return DataArray(ri.data, namask(ri)) end
-    # convert factor into PooledDataArray
-    pool = getattr(ri, "levels", emptystrvec)
-    sz = length(pool)
+    # convert factor into [Nullable]CategoricalArray
+    rlevels = getattr(ri, "levels", emptystrvec)
+    sz = length(rlevels)
     REFTYPE = sz <= typemax(UInt8)  ? UInt8 :
               sz <= typemax(UInt16) ? UInt16 :
               sz <= typemax(UInt32) ? UInt32 :
                                       UInt64
-    dd = ri.data
-    dd[namask(ri)] = 0
-    refs = convert(Vector{REFTYPE}, dd)
-    return PooledDataArray(DataArrays.RefArray(refs), pool)
+    # FIXME set ordered flag
+    refs = na2zero(REFTYPE, ri.data)
+    pool = CategoricalPool{String, REFTYPE}(rlevels)
+    (force_nullable || (findfirst(refs, zero(REFTYPE)) > 0)) ?
+        NullableCategoricalArray{String, 1, REFTYPE}(refs, pool) :
+        CategoricalArray{String, 1, REFTYPE}(refs, pool)
 end
 
 function sexp2julia(rex::RSEXPREC)
@@ -46,36 +61,32 @@ function sexp2julia(rex::RSEXPREC)
 end
 
 function sexp2julia(rv::RVEC)
-    # FIXME dimnames
-    # FIXME forceDataArrays option to always convert to DataArray
-    nas = namask(rv)
-    hasna = any(nas)
+    # TODO dimnames?
+    # FIXME forceNullable option to always convert to NullableArray
+    jv = julia_vector(rv, false)
     if hasnames(rv)
         # if data has no NA, convert to simple Vector
-        return DictoVec(hasna ? DataArray(rv.data, nas) : rv.data, names(rv))
+        return DictoVec(jv, names(rv))
     else
         hasdims = hasdim(rv)
         if !hasdims && length(rv.data)==1
             # scalar
-            # FIXME handle NAs
-            # if hasna
-            return rv.data[1]
+            return jv[1]
         elseif !hasdims
             # vectors
-            return hasna ? DataArray(rv.data, nas) : rv.data
+            return jv
         else
             # matrices and so on
-            dims = tuple(convert(Vector{Int64}, getattr(rv, "dim"))...)
-            return hasna ? DataArray(reshape(rv.data, dims), reshape(nas, dims)) :
-                         reshape(rv.data, dims)
+            dims = tuple(convert(Vector{Int}, getattr(rv, "dim"))...)
+            return reshape(jv, dims)
         end
     end
 end
 
 function sexp2julia(rl::RList)
     if isdataframe(rl)
-        # FIXME remove Any type assertion workaround
-        DataFrame(Any[data(col) for col in rl.data], map(identifier, names(rl)))
+        # FIXME forceNullable option to always convert to NullableArray
+        DataFrame(Any[julia_vector(col, true) for col in rl.data], map(identifier, names(rl)))
     elseif hasnames(rl)
         DictoVec(Any[sexp2julia(item) for item in rl.data], names(rl))
     else

src/sxtypes.jl

@@ -125,7 +125,7 @@ typealias RComplexVector RVector{Complex128, CPLXSXP}
 """
 immutable RNullableVector{T, S} <: RVEC{T, S}
     data::Vector{T}
-    na::BitVector                # mask of NA elements
+    na::Vector{Bool}             # mask of NA elements
     attr::Hash                   # collection of R object attributes
 end
 

test/RDA.jl

@@ -23,19 +23,19 @@ module TestRDA
     df[:int] = Int32[1, 2]
     df[:logi] = [true, false]
     df[:chr] = ["ab", "c"]
-    df[:factor] = pool(df[:chr])
+    df[:factor] = categorical(df[:chr])
     df[:cplx] = Complex128[1.1+0.5im, 1.0im]
     @test isequal(sexp2julia(load("$testdir/data/types.rda",convert=false)["df"]), df)
     @test isequal(sexp2julia(load("$testdir/data/types_ascii.rda",convert=false)["df"]), df)
 
-    df[2, :] = NA
+    df[2, :] = Nullable()
     append!(df, df[2, :])
     df[3, :num] = NaN
-    df[:, :cplx] = @data [NA, @compat(Complex128(1,NaN)), NaN]
+    df[:, :cplx] = NullableArray([Nullable(), Complex128(1,NaN), NaN])
     @test isequal(sexp2julia(load("$testdir/data/NAs.rda",convert=false)["df"]), df)
     # ASCII format saves NaN as NA
-    df[3, :num] = NA
-    df[:, :cplx] = @data [NA, NA, NA]
+    df[3, :num] = Nullable()
+    df[:, :cplx] = NullableArray{Complex128}(3)
     @test isequal(sexp2julia(load("$testdir/data/NAs_ascii.rda",convert=false)["df"]), df)
 
     rda_names = names(sexp2julia(load("$testdir/data/names.rda",convert=false)["df"]))