Add _groupby

Author: giopaglia

src/SoleBase.jl

@@ -56,10 +56,14 @@ function slicedataset(
         return deepcopy(dataset)
     else
         dataset_slice = vec(collect(dataset_slice))
-        @assert eltype(dataset_slice) <: Integer
-        @assert (allow_no_instances ||
+        if !(eltype(dataset_slice) <: Integer)
+            error("Cannot slice dataset with slice of type $(eltype(dataset_slice))")
+        end
+        if !(allow_no_instances ||
             (!(dataset_slice isa Union{AbstractVector{<:Integer},Tuple{<:Integer}}) ||
-                length(dataset_slice) > 0)) "Cannot apply empty slice to dataset."
+                length(dataset_slice) > 0))
+            error("Cannot apply empty slice to dataset.")
+        end
         return instances(dataset, dataset_slice, Val(return_view); kwargs...)
     end
 end

src/utils.jl

@@ -14,11 +14,15 @@ Log detailed debug info
 """
 const LogDetail = LogLevel(-1500)
 
-
+"""
+Returns the human-readable size in Bytes/KBs/MBs/GBs/TBs of a Julia object.
+"""
 function humansize(X; digits = 2, minshowndigits = digits)
     s = Base.summarysize(X)
     d = repeat('0', digits-minshowndigits)
-    if !startswith(string(round(s/1024/1024/1024, digits=digits)), "0.$(d)")
+    if !startswith(string(round(s/1024/1024/1024/1024, digits=digits)), "0.$(d)")
+        "$(s/1024/1024/1024/1024 |> x->round(x, digits=digits)) TBs"
+    elseif !startswith(string(round(s/1024/1024/1024, digits=digits)), "0.$(d)")
         "$(s/1024/1024/1024 |> x->round(x, digits=digits)) GBs"
     elseif !startswith(string(round(s/1024/1024, digits=digits)), "0.$(d)")
         "$(s/1024/1024 |> x->round(x, digits=digits)) MBs"
@@ -68,6 +72,47 @@ function nat_sort(x, y)
     return length(xarr) < length(yarr)
 end
 
+# https://discourse.julialang.org/t/groupby-function/9896
+
+"""
+    group items of list l according to the corresponding values in list v
+
+    julia> _groupby([31,28,31,30,31,30,31,31,30,31,30,31],
+           [:Jan,:Feb,:Mar,:Apr,:May,:Jun,:Jul,:Aug,:Sep,:Oct,:Nov,:Dec])
+    Dict{Int64,Array{Symbol,1}} with 3 entries:
+        31 => Symbol[:Jan, :Mar, :May, :Jul, :Aug, :Oct, :Dec]
+        28 => Symbol[:Feb]
+        30 => Symbol[:Apr, :Jun, :Sep, :Nov]
+
+"""
+function _groupby(v::AbstractVector, l::AbstractVector)
+  @assert length(v) == length(l) "$(@show v, l)"
+  res = Dict{eltype(v),Vector{eltype(l)}}()
+  for (k, val) in zip(v, l)
+    push!(get!(res, k, similar(l, 0)), val)
+  end
+  res
+end
+
+"""
+    group items of list l according to the values taken by function f on them
+
+    julia> _groupby(iseven,1:10)
+    Dict{Bool,Array{Int64,1}} with 2 entries:
+        false => [1, 3, 5, 7, 9]
+        true  => [2, 4, 6, 8, 10]
+
+Note:in this version l is required to be non-empty since I do not know how to
+access the return type of a function
+"""
+function _groupby(f,l::AbstractVector)
+  res = Dict(f(l[1]) => [l[1]]) # l should be nonempty
+  for val in l[2:end]
+    push!(get!(res, f(val), similar(l, 0)), val)
+  end
+  res
+end
+
 ############################################################################################
 
 _typejoin(S::_S) where {_S} = S