Updated benchmark plot

Author: PyDataBlog

docs/src/benchmark_image.png

@@ -198,7 +198,7 @@ ________________________________________________________________________________
 |19.955                 |2.758             |0.000166957      |0.000009206     |ParallelKMeans Lloyd    |Julia      |full scan |
 |11.234                 |1.654             |0.000109074      |0.000012819     |ParallelKMeans Hamerly  |Julia      |full scan |
 |19.394                 |1.436             |0.000109262      |0.000013726     |ParallelKMeans Elkan    |Julia      |full scan |
-|14.080                 |0.000972914       |0.000095325      |0.000009802     |ParallelKMeans YingYang |Julia      |stochastic|
+|14.080                 |0.000972914       |0.000095325      |0.000009802     |ParallelKMeans YingYang |Julia      |full scan |
 
 _________________________________________________________________________________________________________
 

docs/src/index.md

@@ -0,0 +1,64 @@
+using Plots
+using CSV
+using DataFrames
+using Chain
+
+
+data = CSV.read("extras/updated_benchmarks_may_1.csv", DataFrame)
+
+#data2 = stack(data, 1:4)
+#unstack(data2, :variable, :package, :value) |> CSV.write("extras/wide.csv")
+
+long_data = @chain data begin
+    rename(_, [replace(x, " " => "_") for x in names(_)])
+    rename(_, [replace(x, "_sample_(secs)" => "") for x in names(_)])
+    filter(:process => !=("stochastic"), _)
+    stack(_, 1:4)
+end
+
+color_map = Dict{String, Int}()
+
+for (idx, val) in enumerate(unique(long_data.package))
+    push!(color_map, val => idx)
+end
+
+assign_linestyle(x) = occursin("ParallelKMeans", x) ? :solid : :dashdot
+
+function assign_rank(x)
+    if x == "1_million"
+        return 4
+    elseif x == "100k"
+        return 3
+    elseif x == "10k"
+        return 2
+    elseif x == "1k"
+        return 1
+    end
+end
+
+long_data[:, "linestyle"] = assign_linestyle.(long_data.package);
+long_data[:, "rank"] = assign_rank.(long_data.variable);
+
+
+plt = plot(title = "Elbow Method Benchmark Results",
+           yaxis=:log,
+           palette=:seaborn_deep,
+           size=(1000, 700),
+           ylabel="Execution Time (in seconds - logged)",
+           yrotation=30,
+           xlabel="Sample Sizes",
+           legend=:topleft)
+
+for pkg in unique(long_data.package)
+    pkg_data = filter(:package => ==(pkg), long_data)
+    sort!(pkg_data, order(:rank, rev=false))
+    plot!(pkg_data.variable,
+         pkg_data.value,
+         lw=3,
+         linestyle=pkg_data.linestyle,
+         label=pkg,
+         color=color_map[pkg])
+    scatter!(pkg_data.variable, pkg_data.value, markersize=4, color=color_map[pkg], label="")
+end
+
+display(plt)

extras/benchmark_plot.jl

@@ -0,0 +1,10 @@
+1 million sample (secs),100k sample (secs),10k sample (secs),1k sample (secs),package,language,process
+282.7,15.27,0.7324,0.01682,Knor,R,full scan
+854,87,6.11,0.000719,Sklearn KMeans,Python,full scan
+11.2,1.41,0.000317,0.000141,Sklearn MiniBatch Kmeans,Python,stochastic
+254.481,18.517,0.000794956,0.000031211,Mlpack ,C++ Wrapper,full scan
+653.178,45.468,0.000824115,0.000017301,Clustering.jl,Julia,full scan
+19.955,2.758,0.000166957,0.000009206,ParallelKMeans Lloyd,Julia,full scan
+11.234,1.654,0.000109074,0.000012819,ParallelKMeans Hamerly,Julia,full scan
+19.394,1.436,0.000109262,0.000013726,ParallelKMeans Elkan,Julia,full scan
+14.08,0.000972914,0.000095325,0.000009802,ParallelKMeans YingYang,Julia,full scan