/// <summary>
/// 获取聚类结果的评价指标
/// </summary>
/// <param name="data">聚类结果</param>
/// <param name="K">类的个数</param>
/// <returns>结果的purity和gini</returns>
public static ValidationPair GetValidation(Dataset data, int K)
{
dataset = data.Data.ToArray();
nClusters = K;
ValidationPair result = new ValidationPair();
result.gini = GetGini();
result.purity = GetPurity();
return result;
}
public static void OutputResult(Dataset dataset)
{
StreamWriter sw = new StreamWriter("output.txt");
sw.WriteLine("生成类,原始类");
foreach(var data in dataset.Data)
{
sw.WriteLine(data.label.ToString() + "," + data.label_grountTruth.ToString());
}
sw.Close();
}
static void Input()
{
Console.WriteLine("输入读入文件的文件名：");
fileName = Console.ReadLine();
dataset = new Dataset();
StreamReader sr = new StreamReader(fileName);
string line;
while ((line=sr.ReadLine())!=null)
{
var tmp = line.Split(',');
DataType newdata = new DataType(tmp.Length - 1);
newdata.features = tmp.Take(tmp.Length - 1).Select<string, double>(x => Convert.ToDouble(x)).ToArray();
newdata.cntFeatures = tmp.Length - 1;
newdata.label_grountTruth = Convert.ToInt32(tmp[tmp.Length - 1]);
dataset.AddData(newdata);
}
sr.Close();
}
/// <summary>
/// 构造函数
/// </summary>
/// <param name="data">数据集</param>
/// <param name="conv">kmeans时的收敛值</param>
/// <param name="addr">邻接表的地址</param>
public SpectralClusteringGenerator(Dataset data, double conv, PrintLogFunction PrintLog, string addr)
{
dataset = data;
arrData = data.Data.ToArray();
convergence = conv;
PrintLog("初始化MATLAB组件...");
matlab = new MLApp.MLAppClass();
matlab.Visible = 0;
PrintLog("初始化结束...");
if (addr == null /*|| File.Exists(addr)==false*/)
{
PrintLog("初始化Spectral邻居点图, 正在寻找每个点相邻最近的数个点...");
FindNeighbours(9, PrintLog);
PrintLog("初始化结束...");
}
else
{
addrNeighbours = addr;
}
}
private DataType[] presentative; //聚类的代表
#endregion Fields
#region Constructors
/// <summary>
/// 构造函数
/// </summary>
/// <param name="data">数据集</param>
/// <param name="conv">收敛条件</param>
public KmeansGenerator(Dataset data, double conv)
{
dataset = data;
dataset.NormalizeLabel();
convergence = conv;
}
/// <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);
}
