From e5791bc5f6e8130e4d41287c7856c3e7f4da4d34 Mon Sep 17 00:00:00 2001
From: Mike J Innes <mike.j.innes@gmail.com>
Date: Sat, 17 Feb 2018 11:19:14 +0000
Subject: [PATCH] frequencies utility

---
 src/utils.jl | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/src/utils.jl b/src/utils.jl
index 464d9295..facba05a 100644
--- a/src/utils.jl
+++ b/src/utils.jl
@@ -26,6 +26,26 @@ chunk(xs, n) = collect(Iterators.partition(xs, ceil(Int, length(xs)/n)))
 
 batchindex(xs, i) = (reverse(Base.tail(reverse(indices(xs))))..., i)
 
+"""
+    frequencies(xs)
+
+Count the number of times that each element of `xs` appears.
+
+```julia
+julia> frequencies(['a','b','b'])
+Dict{Char,Int64} with 2 entries:
+  'b' => 2
+  'a' => 1
+```
+"""
+function frequencies(xs)
+  fs = Dict{eltype(xs),Int}()
+  for x in xs
+    fs[x] = get(fs, x, 0) + 1
+  end
+  return fs
+end
+
 """
   batch(xs)