Created
May 3, 2015 16:58
-
-
Save dovahcrow/d414594810924fbb569e to your computer and use it in GitHub Desktop.
dbscan vs kmeans
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
using Distributions | |
using Gadfly | |
using RegERMs | |
using DataFrames | |
using Clustering | |
using Match | |
using Distances | |
using Iterators | |
gensin() = begin | |
gauss = Distributions.Gaussian(0, 1) | |
fuzz_sin(x) = sin(x) + rand(gauss) / 7 | |
fuzz_cos(x) = cos(x) + rand(gauss) / 7 | |
df = foldl(DataFrame([Float64, Float64, Symbol],[:x, :y, :tag], 0), [0:0.01:5.2]) do acc, idx | |
@match idx begin | |
less, if less <= 1.57 end => push!(acc, [idx, fuzz_sin(idx), :sin]) | |
middle, if 1.57 < middle < 3.2 end => begin | |
push!(acc, [idx, fuzz_sin(idx), :sin]) | |
push!(acc, [idx, fuzz_cos(idx), :cos]) | |
end | |
more, if 3.2 <= more end => push!(acc, [idx, fuzz_cos(idx), :cos]) | |
end | |
acc | |
end | |
df | |
end | |
genmdf(class... ;sample_per_class = 100) = begin | |
foldl((DataFrame([Float64, Float64, Symbol], [:x, :y, :tag], 0), 0), | |
chain(collect(map(class) do c | |
[rand(MvNormal([c[1], c[2]], c[3])) for i in 1:sample_per_class] | |
end)...)) do acc, b | |
df = acc[1] | |
count = acc[2] + 1 | |
tag = symbol("Class$(int(floor(acc[2] / sample_per_class)))") | |
push!(df, [b[1], b[2], tag]) | |
(df, count) | |
end[1] | |
end | |
gencir() = begin | |
foldl(DataFrame([Float64, Float64, Symbol],[:x, :y, :tag], 0), [-20:0.1:20]) do acc, idx | |
r1 = 3 | |
r2 = 7 | |
x12 = r1^2 - idx^2 + 5*rand(gauss) | |
x22 = r2^2 - idx^2 + 5*rand(gauss) | |
if x12 >= 0 | |
push!(acc, [idx, sqrt(x12), :Circle1]) | |
push!(acc, [idx, -sqrt(x12), :Circle1]) | |
end | |
if x22 >= 0 | |
push!(acc, [idx, sqrt(x22), :Circle2]) | |
push!(acc, [idx, -sqrt(x22), :Circle2]) | |
end | |
acc | |
end | |
end | |
km(df, ks = 2; title = "kmeans") = begin | |
clusterdf = copy(df) | |
kres = kmeans(array(clusterdf[[:x,:y]])', ks) | |
clusterdf[:cluster] = [symbol("Cluster$t") for t in kres.assignments] | |
plot(clusterdf, x=:x, y=:y, color=:cluster, Geom.point, Guide.title("KMeans-$title")) | |
end | |
dbs(df, eps = 0.1, minpts = 1; title = "dbscan") = begin | |
df = copy(df) | |
D = zeros(Float64, nrow(df), nrow(df)) | |
map(combinations(1:nrow(df), 2)) do cob | |
dis = euclidean(vec(array(df[cob[1],[:x,:y]])), vec(array(df[cob[2], [:x,:y]]))) | |
D[cob[1], cob[2]] = dis | |
D[cob[2], cob[1]] = dis | |
0 | |
end | |
dbres = dbscan(D, eps, minpts) | |
df[:cluster] = [symbol("Cluster$t") for t in dbres.assignments] | |
plot(df, x=:x, y=:y, color=:cluster, Geom.point, Guide.title("Dbscan-$title")) | |
end | |
# sin | |
############################################ | |
sdf = gensin() | |
plot(df, x=:x, y=:y, color=:tag, Geom.point) | |
km(df, 2) | |
dbs(df, 1.5, 1) | |
# circle | |
cdf = gencir() | |
plot(cdf, x=:x, y=:y,) | |
km(cdf, 4) | |
dbs(cdf, 1, 1) | |
# multi gaussian | |
################################ | |
mdf = genmdf((0., 0., 1), (6., 4., 2), (-1., 7., 1), (10., -3., 2)) | |
plot(mdf, x=:x, y=:y,) | |
km(mdf, 4) | |
dbs(mdf, 1, 1) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment