Merge pull request #141 from Evovest/perf

Perf

Project.toml

@@ -1,7 +1,7 @@
 name = "EvoTrees"
 uuid = "f6006082-12f8-11e9-0c9c-0d5d367ab1e5"
 authors = ["jeremiedb <[email protected]>"]
-version = "0.9.5"
+version = "0.9.6"
 
 [deps]
 BSON = "fbb218c0-5317-5bc6-957e-2ee96dd4b1f0"

README.md

@@ -2,7 +2,8 @@
 
 [![Build Status](https://travis-ci.org/Evovest/EvoTrees.jl.svg?branch=master)](https://travis-ci.org/Evovest/EvoTrees.jl)
 [![Build status](https://github.com/Evovest/EvoTrees.jl/workflows/CI/badge.svg)](https://github.com/Evovest/EvoTrees.jl/actions)
-[![](https://img.shields.io/badge/docs-stable-blue.svg)](https://Evovest.github.io/EvoTrees.jl/dev)
+[![](https://img.shields.io/badge/docs-stable-blue.svg)](https://Evovest.github.io/EvoTrees.jl/stable)
+[![](https://img.shields.io/badge/docs-dev-blue.svg)](https://Evovest.github.io/EvoTrees.jl/dev)
 
 A Julia implementation of boosted trees with CPU and GPU support.
 Efficient histogram based algorithms with support for multiple loss functions (notably multi-target objectives such as max likelihood methods).

src/find_split.jl

@@ -1,12 +1,15 @@
 #############################################
 # Get the braking points
 #############################################
-function get_edges(X::AbstractMatrix{T}, nbins = 250) where {T}
+function get_edges(X::AbstractMatrix{T}, nbins) where {T}
+    Random.seed!(123)
+    nobs = min(size(X, 1), 1000 * nbins)
+    obs = rand(1:size(X, 1), nobs)
     edges = Vector{Vector{T}}(undef, size(X, 2))
     @threads for i = 1:size(X, 2)
-        edges[i] = quantile(view(X, :, i), (1:nbins) / nbins)
+        edges[i] = quantile(view(X, obs, i), (1:nbins) / nbins)
         if length(edges[i]) == 0
-            edges[i] = [minimum(view(X, :, i))]
+            edges[i] = [minimum(view(X, obs, i))]
         end
     end
     return edges
@@ -18,9 +21,9 @@ end
 function binarize(X, edges)
     X_bin = zeros(UInt8, size(X))
     @threads for i = 1:size(X, 2)
-        X_bin[:, i] = searchsortedlast.(Ref(edges[i][1:end-1]), view(X, :, i)) .+ 1
+        X_bin[:, i] .= searchsortedlast.(Ref(edges[i][1:end-1]), view(X, :, i)) .+ 1
     end
-    X_bin
+    return X_bin
 end
 
 """