From 97e01009d69b8fbebfebf68f51e3d126d0ed43fc Mon Sep 17 00:00:00 2001
From: Daniel Baumann <daniel.baumann@progress-linux.org>
Date: Wed, 30 Nov 2022 19:47:05 +0100
Subject: Merging upstream version 1.37.0.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
---
 ml/KMeans.cc | 43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)
 create mode 100644 ml/KMeans.cc

(limited to 'ml/KMeans.cc')

diff --git a/ml/KMeans.cc b/ml/KMeans.cc
new file mode 100644
index 000000000..edc2ef49e
--- /dev/null
+++ b/ml/KMeans.cc
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-3.0-or-later
+
+#include "KMeans.h"
+#include <dlib/clustering.h>
+
+void KMeans::train(const std::vector<DSample> &Samples, size_t MaxIterations) {
+    MinDist = std::numeric_limits<CalculatedNumber>::max();
+    MaxDist = std::numeric_limits<CalculatedNumber>::min();
+
+    ClusterCenters.clear();
+
+    dlib::pick_initial_centers(NumClusters, ClusterCenters, Samples);
+    dlib::find_clusters_using_kmeans(Samples, ClusterCenters, MaxIterations);
+
+    for (const auto &S : Samples) {
+        CalculatedNumber MeanDist = 0.0;
+
+        for (const auto &KMCenter : ClusterCenters)
+            MeanDist += dlib::length(KMCenter - S);
+
+        MeanDist /= NumClusters;
+
+        if (MeanDist < MinDist)
+            MinDist = MeanDist;
+
+        if (MeanDist > MaxDist)
+            MaxDist = MeanDist;
+    }
+}
+
+CalculatedNumber KMeans::anomalyScore(const DSample &Sample) const {
+    CalculatedNumber MeanDist = 0.0;
+    for (const auto &CC: ClusterCenters)
+        MeanDist += dlib::length(CC - Sample);
+
+    MeanDist /= NumClusters;
+
+    if (MaxDist == MinDist)
+        return 0.0;
+
+    CalculatedNumber AnomalyScore = 100.0 * std::abs((MeanDist - MinDist) / (MaxDist - MinDist));
+    return (AnomalyScore > 100.0) ? 100.0 : AnomalyScore;
+}
-- 
cgit v1.2.3