public static KMeansCluster Cluster(Vector2[] data, int k)
{
int n = data.Length;
Vector2[] centroids = initCentroid(data, k);
int[] clusters = new int[n];
double RSS = double.MaxValue;
int it = 0;
while (it < MaxIterate)
{
bool changed = false;
string cs = "";
foreach (var v in centroids)
{
cs += v + ", ";
}
//Console.WriteLine("质心：" + cs);
for (int i = 0; i < n; ++i)
{
// 对剩余的每个向量测量其到每个质心的距离
double[] distance = new double[k];
for (int j = 0; j < k; ++j)
{
distance[j] = Vector2.DistanceSqr(data[i], centroids[j]) + 0.0001;
}
double sumDis = 0;
for (int j = 0; j < k; ++j)
{
sumDis += distance[j];
}
for (int j = 0; j < k; ++j)
{
distance[j] = distance[j] / sumDis;
}
double[] disSum = new double[k];
disSum[0] = distance[0];
for (int j = 1; j < k; ++j)
{
disSum[j] = disSum[j - 1] + distance[j];
}
double r = rand.NextDouble();
int pos = 0;
while (pos < k)
{
if (r < disSum[pos])
{
break;
}
pos++;
}
clusters[i] = pos;
}
// if (!changed) break; // 未发现改变，跳出
// 重新计算每个类的质心
calcCentroids(data, centroids, clusters);
// 重新计算总方差
double newRSS = calcRSS(data, centroids, clusters);
double diff = Math.Abs(newRSS - RSS);
//Console.WriteLine("迭代次数{0}，方差：{1}/{2}/{3}。", it, RSS, newRSS, diff);
RSS = newRSS;
++it;
if (diff < Epsilon)
{
break; // RSS收敛，跳出
}
}
//List<Vector2>[] result = new List<Vector2>[k];
KMeansCluster result = new KMeansCluster(n, k);
Array.Copy(clusters, result.ClusterIndex, n); // 拷贝聚类索引
for (int i = 0; i < k; ++i)
{
result[i].Centroid = centroids[i]; // 拷贝每类的质心
}
for (int i = 0; i < n; ++i)
{
int c = clusters[i];
result[c].Add(data[i]);
}
return(result);
}
public KMeansCluster <T> Cluster()
{
initCenter(); // 随机初始化中心
double RSS = double.MaxValue;
int it = 0;
while (it < MaxIterate)
{
bool changed = false;
for (int i = 0; i < n; ++i)
{
// 对剩余的每个向量测量其到每个质心的距离
double[] distance = new double[k];
for (int j = 0; j < k; ++j)
{
distance[j] = distanceOf(data[i], centers[j]) + Epsilon;
}
int minCluster = 0;
for (int j = 1; j < k; ++j)
{
if (distance[j] < distance[minCluster])
{
minCluster = j;
}
}
clusters[i] = minCluster;
#region 随机化
//double sumDis = 0;
//for (int j = 0; j < k; ++j) {
// sumDis += distance[j];
//}
//for (int j = 0; j < k; ++j) {
// distance[j] = distance[j] / sumDis;
//}
//double[] disSum = new double[k];
//disSum[0] = distance[0];
//for (int j = 1; j < k; ++j) {
// disSum[j] = disSum[j - 1] + distance[j];
//}
//double r = rand.NextDouble();
//int pos = 0;
//while (pos < k) {
// if (r < disSum[pos]) {
// break;
// }
// pos++;
//}
//clusters[i] = pos;
#endregion
}
// if (!changed) break; // 未发现改变，跳出
// 重新计算每个类的质心
computeCenters();
// 重新计算总方差
double newRSS = computeRSS();
double diff = Math.Abs(newRSS - RSS);
//Console.WriteLine("迭代次数{0}，方差：{1}/{2}/{3}。", it, RSS, newRSS, diff);
RSS = newRSS;
Console.WriteLine("第{0}次迭代,方差{1:F4}.", it, RSS);
++it;
if (diff < Epsilon)
{
break; // RSS收敛，跳出
}
}
KMeansCluster <T> result = new KMeansCluster <T>(n, k);
Array.Copy(clusters, result.ClusterIndex, n); // 拷贝聚类索引
for (int i = 0; i < k; ++i)
{
result[i].Center = centers[i]; // 拷贝每类的中心
}
for (int i = 0; i < n; ++i)
{
int c = clusters[i];
result[c].Add(data[i]);
}
return(result);
}
/* 我自己的，先不写
* private static double createRandom(Vector2[] data, Vector2[] centroids, int[] clusters) {
* int n = data.Length, k = centroids.Length;
* Dictionary<int, bool> used = new Dictionary<int, bool>();
* while (used.Count < k) {
* int r = rand.Next(data.Length);
* if (!used.ContainsKey(r)) {
* centroids[used.Count] = data[r];
* used[r] = true;
* }
* }
*
* for (int i = 0; i < n; ++i) {
* // 对每个向量测量其到每个质心的距离
* double minDis = double.MaxValue;
* for (int j = 0; j < k; ++j) {
* double dis = Vector2.DistanceSqr(data[i], centroids[j]);
* if (dis < minDis) {
* minDis = dis;
* clusters[i] = j;
* }
* }
* }
*
* // 计算每个类的质心
* calcCentroids(data, centroids, clusters);
*
* // 计算总方差
* double RSS = calcRSS(data, centroids, clusters);
* return RSS;
* }
*
* public static KMeansCluster AnnealCluster(Vector2[] data, int k) {
* throw new Exception();
* }
*
* */
/// <summary>
/// 基于模拟退火的动态聚类算法，杨忠明，黄道，王行愚。
/// </summary>
public static KMeansCluster AnnealCluster(Vector2[] data, int c, out int it)
{
it = 0;
int m = data.Length;
double dmax = double.MinValue, dmin = double.MaxValue;
for (int i = 0; i < m; ++i)
{
for (int j = 0; j < m; ++j)
{
if (i == j)
{
continue;
}
double dis = (data[i] - data[j]).Mod();
if (dis > dmax)
{
dmax = dis;
}
if (dis < dmin)
{
dmin = dis;
}
}
} // 确定最大最小距离（最小不是通常都是0吗……）
double t = 10 * dmax, tmin = 1e-1 * dmin + 1e-6;
Vector2[] center = new Vector2[c];
int[] cls = new int[m];
for (int i = 0; i < c; ++i)
{
center[i] = data[i];
cls[i] = i;
} // 以前c个样本作为初始聚类中心
for (int i = c; i < m; ++i)
{
double[] ds = new double[c];
for (int j = 0; j < c; ++j)
{
ds[j] = (data[i] - center[j]).Mod();
}
int pos = getPos(ds, data[i], center, t);
cls[i] = pos;
} // 对其他m-c个样本计算类别
Vector2[] cSum = new Vector2[c];
int[] cCounts = new int[c];
for (int i = 0; i < m; ++i)
{
int cs = cls[i];
cSum[cs] += data[i];
++cCounts[cs];
}
for (int i = 0; i < c; ++i)
{
center[i] = cSum[i] / cCounts[i];
}
double RSS = 0;
for (int i = 0; i < m; ++i)
{
int cs = cls[i];
RSS += Vector2.DistanceSqr(data[i], center[cs]);
} // 计算新的聚类中心和累计类内距离平方和
while (t > tmin && it < MaxIterate)
{
it++;
double nr = adjust(data, center, cls, cCounts, t, RSS);
double diff = Math.Abs(nr - RSS);
RSS = nr;
if (diff < Epsilon)
{
break;
}
t *= alpha; // 降温
}
KMeansCluster result = new KMeansCluster(m, c);
Array.Copy(cls, result.ClusterIndex, m); // 拷贝聚类索引
for (int i = 0; i < c; ++i)
{
result[i].Centroid = center[i]; // 拷贝每类的质心
}
for (int i = 0; i < m; ++i)
{
int cc = cls[i];
result[cc].Add(data[i]);
}
return(result);
}
public KMeansCluster <T> AnnealCluster(Func <T, T, T> add, Func <T, T, T> sub, Func <T, double, T> div, out int it)
{
this.add = add;
this.sub = sub;
this.div = div;
it = 0;
double dmax = double.MinValue, dmin = double.MaxValue;
for (int i = 0; i < n; ++i)
{
for (int j = 0; j < n; ++j)
{
if (i == j)
{
continue;
}
double dis = distanceOf(data[i], data[j]);
if (dis > dmax)
{
dmax = dis;
}
if (dis < dmin)
{
dmin = dis;
}
}
} // 确定最大最小距离（最小不是通常都是0吗……）
double t = 10 * dmax, tmin = 1e-1 * dmin + Epsilon;
for (int i = 0; i < k; ++i)
{
centers[i] = data[i];
clusters[i] = i;
} // 以前c个样本作为初始聚类中心
for (int i = k; i < n; ++i)
{
double[] ds = new double[k];
for (int j = 0; j < k; ++j)
{
ds[j] = distanceOf(data[i], centers[j]);
}
int pos = getPos(ds, t);
clusters[i] = pos;
} // 对其他m-c个样本计算类别
computeCenters(); // 重新计算中心
double RSS = computeRSS(); // 计算方差
while (t > tmin && it < MaxIterate)
{
it++;
double nr = adjust(t, RSS);
double diff = Math.Abs(nr - RSS);
RSS = nr;
if (diff < Epsilon)
{
break;
}
t *= alpha; // 降温
}
KMeansCluster <T> result = new KMeansCluster <T>(n, k);
Array.Copy(clusters, result.ClusterIndex, n); // 拷贝聚类索引
for (int i = 0; i < k; ++i)
{
result[i].Center = centers[i]; // 拷贝每类的中心
}
for (int i = 0; i < n; ++i)
{
int c = clusters[i];
result[c].Add(data[i]);
}
return(result);
}
