From 03bf87dcb06f7021bfb2df2fa8691593c6148aff Mon Sep 17 00:00:00 2001
From: Daniel Baumann <daniel.baumann@progress-linux.org>
Date: Wed, 30 Nov 2022 19:47:00 +0100
Subject: Adding upstream version 1.37.0.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
---
 ml/Dimension.cc | 76 ++++++++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 57 insertions(+), 19 deletions(-)

(limited to 'ml/Dimension.cc')

diff --git a/ml/Dimension.cc b/ml/Dimension.cc
index 0fe07530c..bf34abb72 100644
--- a/ml/Dimension.cc
+++ b/ml/Dimension.cc
@@ -6,8 +6,13 @@
 
 using namespace ml;
 
-std::pair<CalculatedNumber *, size_t>
-TrainableDimension::getCalculatedNumbers() {
+bool Dimension::isActive() const {
+    bool SetObsolete = rrdset_flag_check(RD->rrdset, RRDSET_FLAG_OBSOLETE);
+    bool DimObsolete = rrddim_flag_check(RD, RRDDIM_FLAG_OBSOLETE);
+    return !SetObsolete && !DimObsolete;
+}
+
+std::pair<CalculatedNumber *, size_t> Dimension::getCalculatedNumbers() {
     size_t MinN = Cfg.MinTrainSamples;
     size_t MaxN = Cfg.MaxTrainSamples;
 
@@ -68,7 +73,7 @@ TrainableDimension::getCalculatedNumbers() {
     return { CNs, TotalValues };
 }
 
-MLResult TrainableDimension::trainModel() {
+MLResult Dimension::trainModel() {
     auto P = getCalculatedNumbers();
     CalculatedNumber *CNs = P.first;
     unsigned N = P.second;
@@ -81,7 +86,15 @@ MLResult TrainableDimension::trainModel() {
 
     SamplesBuffer SB = SamplesBuffer(CNs, N, 1, Cfg.DiffN, Cfg.SmoothN, Cfg.LagN,
                                      SamplingRatio, Cfg.RandomNums);
-    KM.train(SB, Cfg.MaxKMeansIters);
+    std::vector<DSample> Samples = SB.preprocess();
+
+    KMeans KM;
+    KM.train(Samples, Cfg.MaxKMeansIters);
+
+    {
+        std::lock_guard<std::mutex> Lock(Mutex);
+        Models[0] = KM;
+    }
 
     Trained = true;
     ConstantModel = true;
@@ -90,16 +103,25 @@ MLResult TrainableDimension::trainModel() {
     return MLResult::Success;
 }
 
-void PredictableDimension::addValue(CalculatedNumber Value, bool Exists) {
+bool Dimension::shouldTrain(const TimePoint &TP) const {
+    if (ConstantModel)
+        return false;
+
+    return (LastTrainedAt + Seconds(Cfg.TrainEvery * updateEvery())) < TP;
+}
+
+bool Dimension::predict(CalculatedNumber Value, bool Exists) {
     if (!Exists) {
         CNs.clear();
-        return;
+        AnomalyBit = false;
+        return false;
     }
 
     unsigned N = Cfg.DiffN + Cfg.SmoothN + Cfg.LagN;
     if (CNs.size() < N) {
         CNs.push_back(Value);
-        return;
+        AnomalyBit = false;
+        return false;
     }
 
     std::rotate(std::begin(CNs), std::begin(CNs) + 1, std::end(CNs));
@@ -108,28 +130,44 @@ void PredictableDimension::addValue(CalculatedNumber Value, bool Exists) {
         ConstantModel = false;
 
     CNs[N - 1] = Value;
-}
 
-std::pair<MLResult, bool> PredictableDimension::predict() {
-    unsigned N = Cfg.DiffN + Cfg.SmoothN + Cfg.LagN;
-    if (CNs.size() != N) {
+    if (!isTrained() || ConstantModel) {
         AnomalyBit = false;
-        return { MLResult::MissingData, AnomalyBit };
+        return false;
     }
 
     CalculatedNumber *TmpCNs = new CalculatedNumber[N * (Cfg.LagN + 1)]();
     std::memcpy(TmpCNs, CNs.data(), N * sizeof(CalculatedNumber));
-
-    SamplesBuffer SB = SamplesBuffer(TmpCNs, N, 1, Cfg.DiffN, Cfg.SmoothN, Cfg.LagN,
+    SamplesBuffer SB = SamplesBuffer(TmpCNs, N, 1,
+                                     Cfg.DiffN, Cfg.SmoothN, Cfg.LagN,
                                      1.0, Cfg.RandomNums);
-    AnomalyScore = computeAnomalyScore(SB);
+    const DSample Sample = SB.preprocess().back();
     delete[] TmpCNs;
 
-    if (AnomalyScore == std::numeric_limits<CalculatedNumber>::quiet_NaN()) {
+    std::unique_lock<std::mutex> Lock(Mutex, std::defer_lock);
+    if (!Lock.try_lock()) {
         AnomalyBit = false;
-        return { MLResult::NaN, AnomalyBit };
+        return false;
     }
 
-    AnomalyBit = AnomalyScore >= (100 * Cfg.DimensionAnomalyScoreThreshold);
-    return { MLResult::Success, AnomalyBit };
+    for (const auto &KM : Models) {
+        double AnomalyScore = KM.anomalyScore(Sample);
+        if (AnomalyScore == std::numeric_limits<CalculatedNumber>::quiet_NaN()) {
+            AnomalyBit = false;
+            continue;
+        }
+
+        if (AnomalyScore < (100 * Cfg.DimensionAnomalyScoreThreshold)) {
+            AnomalyBit = false;
+            return false;
+        }
+    }
+
+    AnomalyBit = true;
+    return true;
+}
+
+std::array<KMeans, 1> Dimension::getModels() {
+    std::unique_lock<std::mutex> Lock(Mutex);
+    return Models;
 }
-- 
cgit v1.2.3