static void TestKmeans(int cnt, double conv)
{
StreamWriter sw = new StreamWriter(@".\"+fileName+@"\result_kmeans.txt");
ValidationPair result;
PrintLog("开始执行kmeans...");
KmeansGenerator kmeans = new KmeansGenerator(dataset, conv);
result = kmeans.Generate(cnt, 10, PrintLog);
sw.WriteLine("purity=" + result.purity.ToString());
sw.WriteLine("gini=" + result.gini.ToString());
PrintLog("kmeans结束...");
sw.Close();
}
/// <summary>
/// 执行谱聚类算法，生成K个类，每个点选最近的neighbourCnt个邻居
/// </summary>
/// <param name="K">类个数</param>
/// <param name="neighbourCnt">邻居个数</param>
/// <returns>聚类结果的purity和gini指标</returns>
public ValidationPair Generate(int K, int neighbourCnt,PrintLogFunction PrintLog)
{
GetNeighbours(neighbourCnt);
int n = arrData.Count();
matlab.Execute("n = " + n.ToString() + ";");
Array W = new double[n, n];
//计算W矩阵
for (int i=0;i< n;i++)
{
for(int j=0;j<neighbourCnt;j++)
{
int a = i;
int b = nearestNeighbours[i][j];
W.SetValue(1, a, b);
W.SetValue(1, b, a);
}
}
Array piW = new double[n, n];
matlab.PutFullMatrix("W", "base", W, piW);
//计算D矩阵
matlab.Execute("s = sum(W);");//对W的每一行求和
matlab.Execute("D = full(sparse(1:n, 1:n, s));");//将s赋值给D的对角线
//计算E矩阵,E的K个最大特征值等于归一化L后L的K个最小特征值
matlab.Execute("L = D - W;");
matlab.Execute("E = D^(-1/2)*W*D^(-1/2);");
matlab.Execute("k=" + K.ToString() + ";");
PrintLog("正在计算特征值特征向量...");
matlab.Execute("[Q, V] = eigs(E, k);");
PrintLog("特征值特征向量计算完毕");
//将特征向量填充给新的数据集
Array pr = new double[n, K];
Array pi = new double[n, K];
matlab.GetFullMatrix("Q", "base", ref pr, ref pi);
Dataset newData = new Dataset();
for (int i = 0; i < n; i++)
{
DataType d = new DataType(K);
for (int j = 0; j < K; j++) d.features[j] = (double)pr.GetValue(i, j);
d.label_grountTruth = arrData[i].label_grountTruth;
newData.AddData(d);
}
//对新的数据进行kmeans聚类
KmeansGenerator kmeans = new KmeansGenerator(newData, convergence);
return kmeans.Generate(K, 10, PrintLog);
}
