benchmark suite about dataframes.jl HOT 4 CLOSED

N = 10000000
v= randn(N)
datavec = DataVec(v)
idx = randi(N, 10000)
vna = copy(v)
vna[idx] = NA
datavecna = copy(datavec)
datavecna[idx] = NA

# Results without NA's in the data:

julia> @time sum(v)
elapsed time: 0.06444692611694336 seconds
-3206.747631560774

julia> @time sum(datavec)
elapsed time: 2.0190951824188232 seconds
-3206.7476315604167

julia> @time sum(nafilter(v))
elapsed time: 0.265045166015625 seconds
-3206.747631560774

julia> @time sum(nafilter(datavec))
elapsed time: 0.19718289375305176 seconds
-3206.747631560774

julia> @time sum(naFilter(v))
elapsed time: 0.046386003494262695 seconds
-3206.7476315604167

julia> @time sum(naFilter(datavec))
elapsed time: 4.131659030914307 seconds
-3206.7476315604167


# Results with NA's in the data:

julia> @time sum(vna)
elapsed time: 0.05554509162902832 seconds
NaN

julia> @time sum(datavecna)
no method +(Float64,NAtype)
 in method_missing at base.jl:60
 in sum at reduce.jl:63

julia> @time sum(nafilter(vna))
elapsed time: 0.23963308334350586 seconds
-3061.658194729886

julia> @time sum(nafilter(datavecna))
elapsed time: 0.18987488746643066 seconds
-3061.658194729886

julia> @time sum(naFilter(vna))
elapsed time: 0.04549598693847656 seconds
-3061.658194729652

julia> @time sum(naFilter(datavecna))
elapsed time: 4.118844985961914 seconds
-3061.658194729652