mirrors
/
StringDistances.jl
mirror of https://github.com/matthieugomez/StringDistances.jl.git
1
0
Fork 0
Code Issues Releases Wiki Activity

Delete benchmark.jl

pull/22/head
matthieugomez 2019-12-12 17:01:40 -05:00
parent 164448f5d7
commit 0c1443310c
1 changed files with 0 additions and 81 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

81
benchmark/benchmark.jl
View File

@ -1,81 +0,0 @@
using StringDistances, Random
Random.seed!(2)
x = map(Random.randstring, rand(5:25,500_000))
y = map(Random.randstring, rand(5:25,500_000))
function f(t, x, y; min_score = 0.0)
[compare(x[i], y[i], t; min_score = min_score) for i in 1:length(x)]
end
@time f(Jaro(), x, y)
#0.3s
@time f(Levenshtein(), x, y)
# 0.35s. A bit faster than StringDist
@time f(Levenshtein(), x, y, min_score = 0.8)
# 0.11
@time f(DamerauLevenshtein(), x, y)
# 0.45s. Much faster than StringDist
@time f(DamerauLevenshtein(), x, y, min_score = 0.8)
# 0.08
@time findmax(x[1], y, Levenshtein())
# 0.14
@time findmax(x[1], y, DamerauLevenshtein())
# 0.15
@time findall(x[1], y, Levenshtein())
# 0.06
@time findall(x[1], y, DamerauLevenshtein())
# 0.05
@time findall(x[1], y, Partial(DamerauLevenshtein()))
# 0.9
@time findall(x[1], y, TokenSort(DamerauLevenshtein()))
# 0.27
@time findall(x[1], y, TokenSet(DamerauLevenshtein()))
# 0.74
@time findall(x[1], y, TokenMax(DamerauLevenshtein()))
# 2.25
# check
function h(t, x, y; min_score = 1/3)
out = fill(false, length(x))
for i in eachindex(x)
if compare(x[i], y[i], t) < min_score
out[i] = compare(x[i], y[i], t ; min_score = min_score) ≈ 0.0
else
out[i] = compare(x[i], y[i], t ; min_score = min_score) ≈ compare(x[i], y[i], t)
end
end
all(out)
end
h(Levenshtein(), x, y)
h(DamerauLevenshtein(), x, y)
#= Rcode
library(stringdist)
x <- sapply(sample(5:25,5 * 1e5,replace=TRUE), function(n) paste(sample(letters,n,replace=TRUE),collapse=""))
y <- sapply(sample(5:25,5 * 1e5,replace=TRUE), function(n) paste(sample(letters,n,replace=TRUE),collapse=""))
system.time(stringdist(x,y,method='lv', nthread = 1))
system.time(stringdist(x,y,method='dl', nthread = 1))
# 0.472
system.time(stringdist(x,y,method='jaccard', nthread = 1))
# 0.739
system.time(stringdist(x,y,method='cosine', nthread = 1))
system.time(stringdist(x,y,method='qgram', nthread = 1))
=#