From 217f1950471243401a50e24d0fc912638e7820f3 Mon Sep 17 00:00:00 2001
From: Ryan Boldi <ryan.boldi123@gmail.com>
Date: Tue, 29 Mar 2022 15:32:34 -0400
Subject: [PATCH] Implemented max-min, which takes the maximum minimum distance
 into account instead of average distances

---
 src/propeller/downsample.cljc          | 23 ++++++++++++++++++++++-
 src/propeller/gp.cljc                  | 10 +++-------
 src/propeller/tools/metrics.cljc       |  6 +++++-
 test/propeller/tools/metrics_test.cljc |  5 +++++
 4 files changed, 35 insertions(+), 9 deletions(-)

diff --git a/src/propeller/downsample.cljc b/src/propeller/downsample.cljc
index ed7be71..283761f 100644
--- a/src/propeller/downsample.cljc
+++ b/src/propeller/downsample.cljc
@@ -20,7 +20,7 @@
   [training-data {:keys [downsample-rate]}]
   (take (int (* downsample-rate (count training-data))) (shuffle training-data)))
 
-(defn select-downsample-tournament
+(defn select-downsample-avg
   "uses case-tournament selection to select a downsample that is biased to being spread out"
   [training-data {:keys [downsample-rate case-t-size]}]
   (let [shuffled-cases (shuffle training-data)
@@ -42,6 +42,27 @@
                  (shuffle (concat (utils/drop-nth selected-case-index tournament)
                                   rest-of-cases))))))))
 
+(defn select-downsample-maxmin
+  "uses tournament selection to select a downsample that has it's cases maximally far away"
+  [training-data {:keys [downsample-rate case-t-size]}]
+  (let [shuffled-cases (shuffle training-data)
+        goal-size (int (* downsample-rate (count training-data)))]
+    (loop [new-downsample (conj [] (first shuffled-cases))
+           cases-to-pick-from (rest shuffled-cases)]
+      (if (>= (count new-downsample) goal-size)
+        new-downsample
+        (let [tournament (take case-t-size cases-to-pick-from)
+              rest-of-cases (drop case-t-size cases-to-pick-from)
+              min-case-distances (metrics/min-of-colls
+                              (map (fn [distance-list]
+                                     (utils/filter-by-index distance-list (map #(:index %) tournament)))
+                                   (map #(:distances %) new-downsample)))
+              selected-case-index (metrics/argmax min-case-distances)]
+          (prn {:min-case-distances min-case-distances :selected-case-index selected-case-index})
+          (recur (conj new-downsample (nth tournament selected-case-index))
+                 (shuffle (concat (utils/drop-nth selected-case-index tournament)
+                                  rest-of-cases))))))))
+
 (defn select-downsample-metalex
   "uses meta-lexicase selection to select a downsample that is biased to being spread out"
   [training-data {:keys [downsample-rate]}])
diff --git a/src/propeller/gp.cljc b/src/propeller/gp.cljc
index d37a07f..f76c9d6 100644
--- a/src/propeller/gp.cljc
+++ b/src/propeller/gp.cljc
@@ -52,7 +52,8 @@
     (prn {:data (some #(when (zero? (:index %)) %) indexed-training-data)})
     (let [training-data (if (= (:parent-selection argmap) :ds-lexicase)
                             (case (:ds-function argmap)
-                               :case-tournament (downsample/select-downsample-tournament indexed-training-data argmap)
+                               :case-avg (downsample/select-downsample-avg indexed-training-data argmap)
+                               :case-maxmin (downsample/select-downsample-maxmin indexed-training-data argmap)
                                (downsample/select-downsample-random indexed-training-data argmap))
                           indexed-training-data) ;defaults to random
           full-evaluated-pop (sort-by :total-error
@@ -65,13 +66,8 @@
                                      population))
           best-individual (first ds-evaluated-pop)
           best-individual-passes-ds (and (= (:parent-selection argmap) :ds-lexicase) (<= (:total-error best-individual) solution-error-threshold))
-          tot-evaluated-pop (when best-individual-passes-ds ;evaluate the whole pop on all training data
-                              (sort-by :total-error
-                                       (mapper
-                                        (partial error-function argmap (:training-data argmap))
-                                        population)))
           ;;best individual on all training-cases
-          tot-best-individual (if best-individual-passes-ds (first tot-evaluated-pop) best-individual)]
+          tot-best-individual (if best-individual-passes-ds (first full-evaluated-pop) best-individual)]
       (prn (first training-data))
       (if (:custom-report argmap)
         ((:custom-report argmap) ds-evaluated-pop generation argmap)
diff --git a/src/propeller/tools/metrics.cljc b/src/propeller/tools/metrics.cljc
index 3019edd..d0039c3 100755
--- a/src/propeller/tools/metrics.cljc
+++ b/src/propeller/tools/metrics.cljc
@@ -18,9 +18,13 @@
 (defn mean-of-colls
   "returns the mean of multiple colls"
   [coll]
-  ;(prn {:func :mean-of-colls :coll coll})
   (map mean (math/transpose coll)))
 
+(defn min-of-colls
+  "returns the smallest value of multiple colls"
+  [coll]
+  (map #(apply min %) (math/transpose coll)))
+
 (defn median
   "Returns the median of a collection."
   [coll]
diff --git a/test/propeller/tools/metrics_test.cljc b/test/propeller/tools/metrics_test.cljc
index b35b7f1..3b0908d 100644
--- a/test/propeller/tools/metrics_test.cljc
+++ b/test/propeller/tools/metrics_test.cljc
@@ -14,6 +14,11 @@
   (t/is (= (m/mean-of-colls '((1 2 3) (4 3 2 1))) '(2.5 2.5 2.5)))
   (t/is (= (m/mean-of-colls '((1))) '(1.0))))
 
+(t/deftest min-of-colls-test
+  (t/is (= (m/min-of-colls '((1 2 3 4) (4 3 2 1))) '(1 2 2 1)))
+  (t/is (= (m/min-of-colls '((1 2 3) (4 3 2 1))) '(1 2 2)))
+  (t/is (= (m/min-of-colls '((1))) '(1))))
+
 (t/deftest mean-test
   (t/is (= (m/mean '(1 2 3 4)) 2.5))
   (t/is (= (m/mean '()) 0)))