Birch wx (#48)

* modify data sink part in StreamKM

* fix bug for birch, complete task #10, modify store functions

Former-commit-id: 511978b

benchmark/datasets/Mock.txt

@@ -0,0 +1,150 @@
+1 5.1 3.5 1.4 0.2 0
+2 4.9 3 1.4 0.2 0
+3 4.7 3.2 1.3 0.2 0
+4 4.6 3.1 1.5 0.2 0
+5 5 3.6 1.4 0.2 0
+6 5.4 3.9 1.7 0.4 0
+7 4.6 3.4 1.4 0.3 0
+8 5 3.4 1.5 0.2 0
+9 4.4 2.9 1.4 0.2 0
+10 4.9 3.1 1.5 0.1 0
+11 5.4 3.7 1.5 0.2 0
+12 4.8 3.4 1.6 0.2 0
+13 4.8 3 1.4 0.1 0
+14 4.3 3 1.1 0.1 0
+15 5.8 4 1.2 0.2 0
+16 5.7 4.4 1.5 0.4 0
+17 5.4 3.9 1.3 0.4 0
+18 5.1 3.5 1.4 0.3 0
+19 5.7 3.8 1.7 0.3 0
+20 5.1 3.8 1.5 0.3 0
+21 5.4 3.4 1.7 0.2 0
+22 5.1 3.7 1.5 0.4 0
+23 4.6 3.6 1 0.2 0
+24 5.1 3.3 1.7 0.5 0
+25 4.8 3.4 1.9 0.2 0
+26 5 3 1.6 0.2 0
+27 5 3.4 1.6 0.4 0
+28 5.2 3.5 1.5 0.2 0
+29 5.2 3.4 1.4 0.2 0
+30 4.7 3.2 1.6 0.2 0
+31 4.8 3.1 1.6 0.2 0
+32 5.4 3.4 1.5 0.4 0
+33 5.2 4.1 1.5 0.1 0
+34 5.5 4.2 1.4 0.2 0
+35 4.9 3.1 1.5 0.1 0
+36 5 3.2 1.2 0.2 0
+37 5.5 3.5 1.3 0.2 0
+38 4.9 3.1 1.5 0.1 0
+39 4.4 3 1.3 0.2 0
+40 5.1 3.4 1.5 0.2 0
+41 5 3.5 1.3 0.3 0
+42 4.5 2.3 1.3 0.3 0
+43 4.4 3.2 1.3 0.2 0
+44 5 3.5 1.6 0.6 0
+45 5.1 3.8 1.9 0.4 0
+46 4.8 3 1.4 0.3 0
+47 5.1 3.8 1.6 0.2 0
+48 4.6 3.2 1.4 0.2 0
+49 5.3 3.7 1.5 0.2 0
+50 5 3.3 1.4 0.2 0
+51 7 3.2 4.7 1.4 1
+52 6.4 3.2 4.5 1.5 1
+53 6.9 3.1 4.9 1.5 1
+54 5.5 2.3 4 1.3 1
+55 6.5 2.8 4.6 1.5 1
+56 5.7 2.8 4.5 1.3 1
+57 6.3 3.3 4.7 1.6 1
+58 4.9 2.4 3.3 1 1
+59 6.6 2.9 4.6 1.3 1
+60 5.2 2.7 3.9 1.4 1
+61 5 2 3.5 1 1
+62 5.9 3 4.2 1.5 1
+63 6 2.2 4 1 1
+64 6.1 2.9 4.7 1.4 1
+65 5.6 2.9 3.6 1.3 1
+66 6.7 3.1 4.4 1.4 1
+67 5.6 3 4.5 1.5 1
+68 5.8 2.7 4.1 1 1
+69 6.2 2.2 4.5 1.5 1
+70 5.6 2.5 3.9 1.1 1
+71 5.9 3.2 4.8 1.8 1
+72 6.1 2.8 4 1.3 1
+73 6.3 2.5 4.9 1.5 1
+74 6.1 2.8 4.7 1.2 1
+75 6.4 2.9 4.3 1.3 1
+76 6.6 3 4.4 1.4 1
+77 6.8 2.8 4.8 1.4 1
+78 6.7 3 5 1.7 1
+79 6 2.9 4.5 1.5 1
+80 5.7 2.6 3.5 1 1
+81 5.5 2.4 3.8 1.1 1
+82 5.5 2.4 3.7 1 1
+83 5.8 2.7 3.9 1.2 1
+84 6 2.7 5.1 1.6 1
+85 5.4 3 4.5 1.5 1
+86 6 3.4 4.5 1.6 1
+87 6.7 3.1 4.7 1.5 1
+88 6.3 2.3 4.4 1.3 1
+89 5.6 3 4.1 1.3 1
+90 5.5 2.5 4 1.3 1
+91 5.5 2.6 4.4 1.2 1
+92 6.1 3 4.6 1.4 1
+93 5.8 2.6 4 1.2 1
+94 5 2.3 3.3 1 1
+95 5.6 2.7 4.2 1.3 1
+96 5.7 3 4.2 1.2 1
+97 5.7 2.9 4.2 1.3 1
+98 6.2 2.9 4.3 1.3 1
+99 5.1 2.5 3 1.1 1
+100 5.7 2.8 4.1 1.3 1
+101 6.3 3.3 6 2.5 2
+102 5.8 2.7 5.1 1.9 2
+103 7.1 3 5.9 2.1 2
+104 6.3 2.9 5.6 1.8 2
+105 6.5 3 5.8 2.2 2
+106 7.6 3 6.6 2.1 2
+107 4.9 2.5 4.5 1.7 2
+108 7.3 2.9 6.3 1.8 2
+109 6.7 2.5 5.8 1.8 2
+110 7.2 3.6 6.1 2.5 2
+111 6.5 3.2 5.1 2 2
+112 6.4 2.7 5.3 1.9 2
+113 6.8 3 5.5 2.1 2
+114 5.7 2.5 5 2 2
+115 5.8 2.8 5.1 2.4 2
+116 6.4 3.2 5.3 2.3 2
+117 6.5 3 5.5 1.8 2
+118 7.7 3.8 6.7 2.2 2
+119 7.7 2.6 6.9 2.3 2
+120 6 2.2 5 1.5 2
+121 6.9 3.2 5.7 2.3 2
+122 5.6 2.8 4.9 2 2
+123 7.7 2.8 6.7 2 2
+124 6.3 2.7 4.9 1.8 2
+125 6.7 3.3 5.7 2.1 2
+126 7.2 3.2 6 1.8 2
+127 6.2 2.8 4.8 1.8 2
+128 6.1 3 4.9 1.8 2
+129 6.4 2.8 5.6 2.1 2
+130 7.2 3 5.8 1.6 2
+131 7.4 2.8 6.1 1.9 2
+132 7.9 3.8 6.4 2 2
+133 6.4 2.8 5.6 2.2 2
+134 6.3 2.8 5.1 1.5 2
+135 6.1 2.6 5.6 1.4 2
+136 7.7 3 6.1 2.3 2
+137 6.3 3.4 5.6 2.4 2
+138 6.4 3.1 5.5 1.8 2
+139 6 3 4.8 1.8 2
+140 6.9 3.1 5.4 2.1 2
+141 6.7 3.1 5.6 2.4 2
+142 6.9 3.1 5.1 2.3 2
+143 5.8 2.7 5.1 1.9 2
+144 6.8 3.2 5.9 2.3 2
+145 6.7 3.3 5.7 2.5 2
+146 6.7 3 5.2 2.3 2
+147 6.3 2.5 5 1.9 2
+148 6.5 3 5.2 2 2
+149 6.2 3.4 5.4 2.3 2
+150 5.9 3 5.1 1.8 2

benchmark/src/Benchmark.cpp

@@ -35,19 +35,7 @@ int main(int argc, char **argv) {
   SESAME::DataSinkPtr sinkPtr = SESAME::DataSinkFactory::create();
 
   //Create Algorithm.
-  SESAME::AlgorithmPtr algoPtr = SESAME::AlgorithmFactory::create(cmd_params.algoName,
-                                                                  cmd_params.pointNumber,
-                                                                  cmd_params.clusterNumber,
-                                                                  cmd_params.dimension,
-                                                                  cmd_params.coresetSize,
-                                                                  cmd_params.seed,
-                                                                  cmd_params.lastArrivingNum,
-                                                                  cmd_params.timeWindow,
-                                                                  cmd_params.timeInterval,
-                                                                  cmd_params.onlineClusterNumber,
-                                                                  cmd_params.radiusFactor,
-                                                                  cmd_params.initBuffer,
-                                                                  cmd_params.offlineTimeWindow);
+  SESAME::AlgorithmPtr algoPtr = SESAME::AlgorithmFactory::create(cmd_params);
 
   //Run algorithm producing results.
   BenchmarkUtils::runBenchmark(cmd_params, sourcePtr, sinkPtr, algoPtr);

include/Algorithm/Algorithm.hpp

@@ -30,7 +30,7 @@ class Algorithm {
   virtual void Initilize() = 0;
   virtual void runOnlineClustering(SESAME::PointPtr input) = 0;
   virtual void runOfflineClustering(SESAME::DataSinkPtr ptr) = 0;
-  void store(std::string outputPath, int numberOfCenters, int dimension, std::vector<PointPtr> results);
+  void store(std::string outputPath, int dimension, std::vector<PointPtr> results);
 };
 }
 

include/Algorithm/AlgorithmFactory.hpp

@@ -8,23 +8,13 @@
 #define SESAME_SRC_ALGORITHM_ALGORITHMFACTORY_HPP_
 
 #include <Algorithm/Algorithm.hpp>
+#include <Utils/BenchmarkUtils.hpp>
+
 namespace SESAME {
 class AlgorithmFactory {
 
  public:
-  static SESAME::AlgorithmPtr create(std::string algoName,
-                                     int pointNumber,
-                                     int clusterNumber,
-                                     int dimension,
-                                     int coresetSize,
-                                     int seed,
-                                     int lastArrivingNum,
-                                     int timeWindow,
-                                     unsigned int timeInterval,
-                                     int onlineClusterNumber,
-                                     double radiusFactor,
-                                     int initBuffer,
-                                     int offlineTimeWindow);
+  static SESAME::AlgorithmPtr create(param_t &cmd_params);
 };
 }
 #endif //SESAME_SRC_ALGORITHM_ALGORITHMFACTORY_HPP_

include/Algorithm/Birch.hpp

@@ -0,0 +1,56 @@
+//
+// Created by tuidan on 2021/8/24.
+//
+
+#ifndef SESAME_INCLUDE_ALGORITHM_BIRCH_HPP_
+#define SESAME_INCLUDE_ALGORITHM_BIRCH_HPP_
+#include <Algorithm/Algorithm.hpp>
+#include <Algorithm/WindowModel/LandmarkWindow.hpp>
+#include <Algorithm/OfflineClustering/KMeans.hpp>
+#include <Sinks/DataSink.hpp>
+#include <Algorithm/DataStructure/CFTree.hpp>
+namespace SESAME {
+
+class BirchParameter : public AlgorithmParameters {
+ public:
+  int maxInternalNodes; // B
+  int maxLeafNodes; // L
+  double thresholdDistance; // T
+};
+
+class Birch : public Algorithm {
+
+ public:
+  BirchParameter BirchParam;
+  std::shared_ptr<KMeans> kmeans; //used for offline initialization
+  int leafMask = 0;
+  NodePtr root;
+  vector<NodePtr> leafNodes;
+  CFTreePtr cfTree;
+  Birch();
+
+  ~Birch();
+
+  void Initilize() override;
+
+  void runOnlineClustering(PointPtr input) override;
+
+  void runOfflineClustering(DataSinkPtr sinkPtr) override;
+ private:
+
+  void forwardInsert(PointPtr point);
+  void backwardEvolution(NodePtr &curNode, PointPtr &point);
+  void calculateCorDistance(vector<vector<double>> &distance, vector<NodePtr> &nodes);
+  double calculateRadius(PointPtr &point, PointPtr &centroid);
+  void selectChild(vector<NodePtr> &children, PointPtr &insertPoint, NodePtr &node);
+  double clusterToClusterDist(NodePtr &nodeA, NodePtr &nodeB);
+  void pointToClusterDist(PointPtr &insertPoint, NodePtr &node, double &dist);
+  void calculateCentroid(CFPtr &cf, PointPtr &centroid);
+  void updateNLS(NodePtr &node, PointPtr &point, bool updateAll);
+  void initializeCF(CFPtr &cf, int dimension);
+  void setCFToBlankNode(SESAME::NodePtr &curNode, SESAME::PointPtr &point);
+  void addNodeNLSToNode(SESAME::NodePtr &child, SESAME::NodePtr &parent);
+  void clearChildParents(vector<SESAME::NodePtr> &children);
+};
+}
+#endif //SESAME_INCLUDE_ALGORITHM_BIRCH_HPP_

include/Algorithm/DataStructure/CFTree.hpp

@@ -0,0 +1,67 @@
+//
+// Created by tuidan on 2021/8/24.
+//
+
+#ifndef SESAME_INCLUDE_ALGORITHM_DATASTRUCTURE_CFTREE_HPP_
+#define SESAME_INCLUDE_ALGORITHM_DATASTRUCTURE_CFTREE_HPP_
+#include <iostream>
+#include <memory>
+#include <vector>
+#include <Algorithm/DataStructure/FeatureVector.hpp>
+#include <Algorithm/DataStructure/Point.hpp>
+namespace SESAME {
+
+// define the share point of the class object
+class CFNode;
+class CFTree;
+typedef std::shared_ptr<CFNode> NodePtr;
+typedef std::shared_ptr<CFTree> CFTreePtr;
+
+class CFTree {
+ private:
+  int maxInternalNodes; // max CF number of each internal node
+  int maxLeafNodes; // max CF number of each leaf node
+  double thresholdDistance; // threshold radius of each sub cluster in leaf nodes
+ public:
+  CFTree(int b, int l, double t);
+  void initialTree(int b, int l, double t);
+  ~CFTree();
+  int getB() const;
+  int getL() const;
+  double getT() const;
+  void setB(int b);
+  void setL(int l);
+  void setT(double t);
+};
+
+
+class CFNode {
+ private:
+  CFPtr curCF;
+  bool isLeaf;
+  std::vector<NodePtr> children;
+  std::vector<NodePtr> parent;
+  std:: vector<SESAME::PointPtr> clusterPoints;
+  int index;
+ public:
+  CFNode();
+  ~CFNode();
+  SESAME::CFPtr getCF();
+  void setCF(SESAME::CFPtr &cf);
+  void insertPoint(PointPtr &p);
+  std::vector<SESAME::PointPtr> getPoints();
+  std::vector<SESAME::NodePtr> getParents();
+  int getIndex() const;
+  std::vector<SESAME::NodePtr> getChildren();
+  void removeChild(SESAME::NodePtr &child);
+  SESAME::NodePtr copy();
+  bool getIsLeaf();
+  void setIsLeaf(bool leaf);
+  void setNode(SESAME::CFPtr &Node);
+  void setIndex(int Index);
+  void setParent(SESAME::NodePtr &Parent);
+  void setChild(SESAME::NodePtr &child);
+  void clearParents();
+};
+}
+#endif //SESAME_INCLUDE_ALGORITHM_DATASTRUCTURE_CFTREE_HPP_

include/Algorithm/DataStructure/DataStructureFactory.hpp

@@ -11,6 +11,9 @@
 #include <Algorithm/DataStructure/CoresetTree.hpp>
 #include <Algorithm/DataStructure/MicroCluster.hpp>
 #include <Algorithm/DataStructure/Snapshot.hpp>
+#include <Algorithm/DataStructure/CFTree.hpp>
+#include <Algorithm/DataStructure/FeatureVector.hpp>
+
 namespace SESAME {
 class DataStructureFactory {
 
@@ -28,6 +31,8 @@ class DataStructureFactory {
   static void clearMicroCluster(MicroClusterPtr microCluster);
   static SnapshotPtr createSnapshot(MicroClusters & otherMicroClusters,int elapsedTime);
   static void clearSnapshot(SnapshotPtr snapshot);
+  static CFTreePtr createCFTree();
+  static NodePtr createNode();
 
 };
 }

include/Algorithm/DataStructure/FeatureVector.hpp

@@ -0,0 +1,34 @@
+//
+// Created by tuidan on 2021/8/24.
+//
+
+#ifndef SESAME_INCLUDE_ALGORITHM_DATASTRUCTURE_FEATUREVECTOR_H_
+#define SESAME_INCLUDE_ALGORITHM_DATASTRUCTURE_FEATUREVECTOR_H_
+#include <memory>
+#include <vector>
+#include <iostream>
+
+namespace SESAME {
+class CF;
+typedef std::shared_ptr<CF> CFPtr;
+class CF {
+ private:
+  // N是子类中节点的数目，LS是N个节点的线性和，SS是N个节点的平方和
+  int NumberOfNodes;
+  std::vector<double> LS;
+  std::vector<double> SS;
+ public:
+  CF();
+  ~CF();
+  int getN() const;
+  void setN(int n);
+  std::vector<double> getLS() const;
+  std::vector<double> getSS() const;
+  double getLSItem(int index) const;
+  double getSSItem(int index) const;
+  void setLS(std::vector<double> &newLs);
+  void setSS(std::vector<double> &newSs);
+  SESAME::CFPtr copy();
+};
+}
+#endif //SESAME_INCLUDE_ALGORITHM_DATASTRUCTURE_FEATUREVECTOR_H_

include/Algorithm/DataStructure/Point.hpp

@@ -36,6 +36,7 @@ class Point {
   void setClusteringCenter(int index);
   int getDimension() const;
   void setDimension(int d);
+  int getFeatureLength();
   SESAME::PointPtr copy();
 };
 }