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>
/// 执行kmeans聚类方法，生成K个类，重复执行repeat次选结果最好的
/// </summary>
/// <param name="K">聚类个数</param>
/// <param name="repeat">重复次数</param>
/// <returns>聚类结果的purity和gini指标</returns>
public ValidationPair Generate(int K, int repeat, PrintLogFunction PrintLog)
{
ValidationPair result = new ValidationPair();
for (int r = 0; r < repeat; r++)
{
PrintLog("正在执行第" + r.ToString() + "次kmeans聚类...");
#region 执行一次聚类
presentative = new DataType[K];
InitializePresentative(K);
double sumDist = 100;
bool isOver = false;
while (sumDist > convergence)
{
//对当前的代表进行聚类
isOver = true;
foreach (var data in dataset.Data)
{
double minDist = double.MaxValue;
int lableNow = 0;
for (int i = 0; i < K; i++)
{
double d = Matrix.Dist(data.features, presentative[i].features);
if (d < minDist)
{
minDist = d;
lableNow = i;
}
}
if (lableNow != data.label) isOver = false;
data.label = lableNow;
}
if (isOver == true) break;//若当前迭代未改变类，则结束
//生成新的代表
DataType[] newPresentative = new DataType[K];
for (int i = 0; i < K; i++)
{
int clusterCount = 0;
newPresentative[i] = new DataType(presentative[0].cntFeatures);
//新的代表取聚类中所有向量的平均值
foreach (var data in dataset.Data)
{
if (data.label != i) continue;
clusterCount++;
newPresentative[i].Add(data);
}
for (int j = 0; j < newPresentative[i].cntFeatures; j++) newPresentative[i].features[j] /= clusterCount;
}
//计算两次代表之间的平均距离
sumDist = 0;
for (int i = 0; i < K; i++)
{
sumDist += Matrix.Dist(presentative[i].features, newPresentative[i].features);
}
presentative = newPresentative;
sumDist /= K;
}
#endregion
#region 生成评价指标
ValidationPair v = ClusterValidater.GetValidation(dataset, K);
if (v.purity>=result.purity)
{
if (v.purity > result.purity) result = v;
else if (v.gini < result.gini) result = v;
}
#endregion
}
return result;
}
/// <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);
}
/// <summary>
/// 添加一组数据
/// </summary>
/// <param name="newData"></param>
public void AddData(DataType newData)
{
data.AddLast(newData);
CntFeatures = newData.cntFeatures;
}