-
Notifications
You must be signed in to change notification settings - Fork 4
/
hierarchical.cljc
70 lines (62 loc) · 2.68 KB
/
hierarchical.cljc
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
;; The MIT License (MIT)
;;
;; Copyright (c) 2016 Richard Hull
;;
;; Permission is hereby granted, free of charge, to any person obtaining a copy
;; of this software and associated documentation files (the "Software"), to deal
;; in the Software without restriction, including without limitation the rights
;; to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
;; copies of the Software, and to permit persons to whom the Software is
;; furnished to do so, subject to the following conditions:
;;
;; The above copyright notice and this permission notice shall be included in all
;; copies or substantial portions of the Software.
;;
;; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
;; IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
;; FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
;; AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
;; LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
;; OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
;; SOFTWARE.
(ns clustering.core.hierarchical
(:require
[clojure.math.combinatorics :refer [combinations]]))
(defrecord BiCluster [branch? data left right distance])
(defn bi-cluster
([data] (BiCluster. false data nil nil 0))
([data [left right] distance] (BiCluster. true data left right distance)))
(defn find-closest
"Loop through every pair looking for the smallest distance"
[distance-fn points]
(reduce
(fn [state curr]
(let [dist (apply distance-fn curr)]
(if (< dist (or (first state) #?(:clj Integer/MAX_VALUE
:cljs (.-MAX_SAFE_INTEGER js/Number))))
[dist curr]
state)))
[]
(combinations points 2)))
(defn cluster [distance-fn average-fn dataset]
(let [distance-fn (memoize
(fn [clust1 clust2]
(distance-fn (:data clust1) (:data clust2))))]
(loop [clusters (set (map bi-cluster dataset))]
(if (<= (count clusters) 1)
(first clusters)
(let [[closest lowest-pair] (find-closest distance-fn clusters)
averaged-data (average-fn (map :data lowest-pair))
new-cluster (bi-cluster averaged-data lowest-pair closest)]
(recur
(->
(apply disj clusters lowest-pair)
(conj new-cluster))))))))
(defn prefix-walk
([visitor-fn clust]
(prefix-walk visitor-fn clust 0))
([visitor-fn clust level]
(when-not (empty? clust)
(visitor-fn clust level)
(prefix-walk visitor-fn (:left clust) (inc level))
(prefix-walk visitor-fn (:right clust) (inc level)))))