Bump

Project.toml

@@ -1,7 +1,7 @@
 name = "SoleFeatures"
 uuid = "3ceb4e54-d968-4e97-8c18-2deeb0d429fb"
 authors = ["Patrik CAVINA", "Federico Manzella", "Giovanni Pagliarini"]
-version = "0.1.0"
+version = "0.2.0"
 
 [deps]
 Catch22 = "acdeb78f-3d39-4310-8fdf-6d75c17c6d5a"
@@ -10,6 +10,7 @@ HypothesisTests = "09f84164-cd44-5f33-b23f-e6b0d136a0d5"
 IterTools = "c8e1da08-722c-5040-9ed9-7db0dc04731e"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 MLBase = "f0e99cf1-93fa-52ec-9ecc-5026115318e0"
+MultiData = "8cc5100c-b3d1-4f82-90cb-0ea93d317aba"
 OrderedCollections = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
 PyCall = "438e738f-606a-5dbb-bf0a-cddfbfd45ab0"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
@@ -20,17 +21,18 @@ Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
 
 [compat]
-HypothesisTests = "0.10 - 0.11"
-SoleData = "0.12"
-StatsBase = "0.30 - 0.34"
-Random = "1"
 Catch22 = "0.4, 0.5"
 DataFrames = "1"
+HypothesisTests = "0.10 - 0.11"
 IterTools = "1"
 OrderedCollections = "1"
 PyCall = "1"
+Random = "1"
 Reexport = "1"
 Revise = "3"
+SoleData = "0.13"
+MultiData = "0"
+StatsBase = "0.30 - 0.34"
 julia = "1"
 
 [extras]

src/SoleFeatures.jl

@@ -1,6 +1,7 @@
 module SoleFeatures
 
 using StatsBase
+using MultiData
 using SoleData
 using Reexport
 using Random

src/core.jl

@@ -6,7 +6,7 @@ Removes from provided samples variables indicated by bitmask or selector
 
 # Arguments
 
-- `X::AbstractDataFrame|MultiModalDataset`: samples to evaluate
+- `X::AbstractDataFrame|MultiDataset`: samples to evaluate
 - `y::AbstractVector`: target vector
 - `bm::BitVector`: Vector of bit containing which variables are suitable(1) or not(0)
 - `selector::AbstractFeaturesSelector`: Selector
@@ -38,35 +38,35 @@ function transform!(
 end
 
 function transform!(
-    X::SoleData.AbstractMultiModalDataset,
+    X::MultiData.AbstractMultiDataset,
     bm::BitVector;
     i_modality::Union{Integer,Nothing} = nothing
 )
     if (isnothing(i_modality))
         nvariables(X) != length(bm) && throw(DimensionMismatch(""))
-        return SoleData.dropvariables!(X, findall(!, bm))
+        return MultiData.dropvariables!(X, findall(!, bm))
     else
         nvariables(X, i_modality) != length(bm) && throw(DimensionMismatch(""))
-        return SoleData.dropvariables!(X, i_modality, findall(!, bm))
+        return MultiData.dropvariables!(X, i_modality, findall(!, bm))
     end
 end
 
 function transform!(
-    X::SoleData.AbstractMultiModalDataset,
+    X::MultiData.AbstractMultiDataset,
     selector::AbstractFeaturesSelector;
     i_modality::Union{Integer,Nothing} = nothing
 )
     if (isnothing(i_modality))
-        return transform!(SoleData.data(X), selector)
+        return transform!(MultiData.data(X), selector)
     else
-        return transform!(SoleData.modality(X, i_modality), selector)
+        return transform!(MultiData.modality(X, i_modality), selector)
     end
 end
 
-# TODO: transform! for MultiModalDataset with supervised selector
+# TODO: transform! for MultiDataset with supervised selector
 
 transform(X::AbstractDataFrame, args...; kwargs...) = transform!(deepcopy(X), args...; kwargs...)
-transform(X::SoleData.AbstractMultiModalDataset, args...; kwargs...) = transform!(deepcopy(X), args...; kwargs...)
+transform(X::MultiData.AbstractMultiDataset, args...; kwargs...) = transform!(deepcopy(X), args...; kwargs...)
 # (s::AbstractFeaturesSelector)(X, args; kwargs...) = transform(X, args..., kwargs...) # TODO: correct this
 
 """
@@ -88,14 +88,14 @@ True values indicate selected variable index
 - `i_modality::Integer`: Modality index
 """
 function buildbitmask(
-    X::SoleData.MultiModalDataset,
+    X::MultiData.MultiDataset,
     selector::AbstractFeaturesSelector,
     i_modality::Integer
 )::Tuple{BitVector,BitVector}
-    return buildbitmask(SoleData.modality(X, i_modality), selector)
+    return buildbitmask(MultiData.modality(X, i_modality), selector)
 end
 
-# TODO: buildbitmask for MultiModalDataset with supervised selector
+# TODO: buildbitmask for MultiDataset with supervised selector
 
 function buildbitmask(
     X::AbstractDataFrame,

src/utils/utils.jl

@@ -1,19 +1,19 @@
-# TODO: minmax_normalize in SoleData
+# TODO: minmax_normalize in MultiData
 """
 Normalize passed DataFrame using min-max normalization.
 Return a new normalized DataFrame
 """
 minmax_normalize(c, args...; kwars...) = minmax_normalize!(deepcopy(c), args...; kwars...)
 
 function minmax_normalize!(
-    md::SoleData.MultiModalDataset,
+    md::MultiData.MultiDataset,
     frame_index::Integer;
     min_quantile::Real = 0.0,
     max_quantile::Real = 1.0,
     col_quantile::Bool = true,
 )
     return minmax_normalize!(
-        SoleData.modality(md, frame_index);
+        MultiData.modality(md, frame_index);
         min_quantile = min_quantile,
         max_quantile = max_quantile,
         col_quantile = col_quantile
@@ -74,12 +74,12 @@ end
 """
     _mod_bm2mfd_bm(md, frame_index, frame_bm)
 
-Modality bitmask to MultiModalDataset bitmask.
+Modality bitmask to MultiDataset bitmask.
 
-return bitmask for entire MultiModalDataset from a modality of it
+return bitmask for entire MultiDataset from a modality of it
 """
 function _mod_bm2mfd_bm(
-    md::SoleData.MultiModalDataset,
+    md::MultiData.MultiDataset,
     i_mods::Union{Integer,AbstractVector{<:Integer}},
     framebms::Union{BitVector,AbstractVector{<:BitVector}}
 )::BitVector
@@ -92,7 +92,7 @@ function _mod_bm2mfd_bm(
     for i in 1:lastindex(i_mods)
         i_modality = i_mods[i]
         frbm = framebms[i]
-        framedescr = SoleData.grouped_variables(md)[i_modality] # modality indices in md
+        framedescr = MultiData.grouped_variables(md)[i_modality] # modality indices in md
         bm[framedescr] = frbm
     end
     return bm
@@ -103,12 +103,12 @@ end
 
 return tuple containing names of suitable variables and names of not suitable variables
 """
-function bm2var(md::SoleData.MultiModalDataset, bm::BitVector)
-    return bm2var(SoleData.data(md), bm)
+function bm2var(md::MultiData.MultiDataset, bm::BitVector)
+    return bm2var(MultiData.data(md), bm)
 end
 
-function bm2var(md::SoleData.MultiModalDataset, i_modality::Integer, bm::BitVector)
-    return bm2var(SoleData.modality(md, i_modality), bm)
+function bm2var(md::MultiData.MultiDataset, i_modality::Integer, bm::BitVector)
+    return bm2var(MultiData.modality(md, i_modality), bm)
 end
 
 function bm2var(df::AbstractDataFrame, bm::BitVector)

test/runtests.jl

@@ -2,7 +2,7 @@ using HypothesisTests
 using StatsBase
 using Test
 using Revise
-using SoleData
+using MultiData
 using SoleFeatures
 
 include("./test_function.jl")
@@ -11,27 +11,27 @@ include("./test_function.jl")
 
     @testset "transform" begin
 
-        @testset "transform!(md, bm; i_modality) using bitmask on a modality of MultiModalDataset" begin
+        @testset "transform!(md, bm; i_modality) using bitmask on a modality of MultiDataset" begin
             df = random_timeseries_df(; nvar=10)
-            md = SoleData.MultiModalDataset(df, [[3,7,8], [1,2,4], [5,6,9,10]])
+            md = MultiData.MultiDataset(df, [[3,7,8], [1,2,4], [5,6,9,10]])
             bm_mod = BitVector([0,1,0])
             idx_mod = 1
             # expected values
             emfd = deepcopy(md)
-            SoleData.dropvariables!(emfd, [3,8])
+            MultiData.dropvariables!(emfd, [3,8])
 
             SoleFeatures.transform!(md, bm_mod; i_modality=idx_mod)
 
             @test isequal(md, emfd)
         end
 
-        @testset "transform!(md, bm) using bitmask on whole MultiModalDataset" begin
+        @testset "transform!(md, bm) using bitmask on whole MultiDataset" begin
             df = random_timeseries_df(; nvar=5)
-            md = SoleData.MultiModalDataset(df, [[4,2,1], [5,3]])
+            md = MultiData.MultiDataset(df, [[4,2,1], [5,3]])
             bm_mod = BitVector([0,1,0,1,1])
             # expected values
             emfd = deepcopy(md)
-            SoleData.dropvariables!(emfd, [1,3])
+            MultiData.dropvariables!(emfd, [1,3])
 
             SoleFeatures.transform!(md, bm_mod)
 
@@ -50,27 +50,27 @@ include("./test_function.jl")
             @test isequal(df, edf)
         end
 
-        @testset "transform(md, bm; i_modality) using bitmask on a modality of MultiModalDataset" begin
+        @testset "transform(md, bm; i_modality) using bitmask on a modality of MultiDataset" begin
             df = random_timeseries_df(; nvar=10)
-            md = SoleData.MultiModalDataset(df, [[3,7,8], [1,2,4], [5,6,9,10]])
+            md = MultiData.MultiDataset(df, [[3,7,8], [1,2,4], [5,6,9,10]])
             bm_mod = BitVector([0,1,0])
             idx_mod = 1
             # expected values
             emfd = deepcopy(md)
-            SoleData.dropvariables!(emfd, [3,8])
+            MultiData.dropvariables!(emfd, [3,8])
 
             md = SoleFeatures.transform(md, bm_mod; i_modality=idx_mod)
 
             @test isequal(md, emfd)
         end
 
-        @testset "transform(md, bm) using bitmask on whole MultiModalDataset" begin
+        @testset "transform(md, bm) using bitmask on whole MultiDataset" begin
             df = random_timeseries_df(; nvar=5)
-            md = SoleData.MultiModalDataset(df, [[4,2,1], [5,3]])
+            md = MultiData.MultiDataset(df, [[4,2,1], [5,3]])
             bm_mod = BitVector([0,1,0,1,1])
             # expected values
             emfd = deepcopy(md)
-            SoleData.dropvariables!(emfd, [1,3])
+            MultiData.dropvariables!(emfd, [1,3])
 
             md = SoleFeatures.transform(md, bm_mod)
 
@@ -95,7 +95,7 @@ include("./test_function.jl")
 
         @testset "_mod_bm2mfd_bm using array of frames and array of bitmasks" begin
             df = random_timeseries_df(; nvar=10)
-            md = SoleData.MultiModalDataset(df, [[3,7,8], [1,2,4], [5,6,9,10]])
+            md = MultiData.MultiDataset(df, [[3,7,8], [1,2,4], [5,6,9,10]])
             frms = [1,2,3]
             bms = Vector{BitVector}([ [0,1,0],[0,0,1],[0,1,1,0] ])
             # expected values
@@ -108,7 +108,7 @@ include("./test_function.jl")
 
         @testset "_mod_bm2mfd_bm using modality and bitmask" begin
             df = random_timeseries_df(; nvar=10)
-            md = SoleData.MultiModalDataset(df, [[3,7,8], [1,2,4], [5,6,9,10]])
+            md = MultiData.MultiDataset(df, [[3,7,8], [1,2,4], [5,6,9,10]])
             frm = 2
             bm = BitVector([0,0,1])
             # expected values
@@ -186,12 +186,12 @@ include("./test_function.jl")
                 @test (SoleFeatures.transform!(df, cf) isa DataFrame)
             end
 
-            @testset "VarianceRanking on MultiModalDataset" begin
+            @testset "VarianceRanking on MultiDataset" begin
                 df = random_df();
                 df = SoleFeatures.minmax_normalize(df; min_quantile=0.0, max_quantile=1.0)
-                md = SoleData.MultiModalDataset(df, [ [1,2,3,4], [5] ])
+                md = MultiData.MultiDataset(df, [ [1,2,3,4], [5] ])
                 vr = VarianceRanking(3)
-                @test_broken (SoleFeatures.transform!(md, vr; i_modality=1) isa MultiModalDataset)
+                @test_broken (SoleFeatures.transform!(md, vr; i_modality=1) isa MultiDataset)
             end
 
         end

test/test_function.jl

@@ -118,7 +118,7 @@ end
 function random_timeseries_mfd(;ninstances=100, nvar=5, ts_len=5)
     df = random_timeseries_df(;ninstances=ninstances, nvar=nvar, ts_len=ts_len)
     fd = [ collect(1:nvar) ]
-    return MultiModalDataset(df, fd)
+    return MultiDataset(df, fd)
 end
 
 function random_timeseries_df(;ninstances=100, nvar=5, ts_len=5)
@@ -140,5 +140,5 @@ end
 function random_mfd(;ninstances=100, nvar=5)
     df = random_df(;ninstances = ninstances, nvar = nvar)
     fd = [ collect(1:nvar) ]
-    return MultiModalDataset(df, fd)
+    return MultiDataset(df, fd)
 end

test/voiceexperiment.jl

@@ -15,7 +15,7 @@ isdefined(Main, :Catch22) && (Base.nameof(f::SuperFeature) = getname(f)) # wrap
 
 # 28 variables 2 classes
 # X, y = arff_2_mfd_multivariate("/home/patrik/develop/aclai/features_selection/results-sole/datasets/FingerMovements_TRAIN.arff")
-# X = SoleData.modality(X, 1)
+# X = MultiData.modality(X, 1)
 
 # ================== PREPARE VARIABLES, WINDOWS, MEASURES ==================
 @info "PREPARE VARIABLES, WINDOWS, MEASURES"