public static void main(String[] args) {
int i, j;
int n, k, dim;
kMeans cluster;
Scanner sc = new Scanner(System.in);
k = sc.nextInt();
n = sc.nextInt();
dim = sc.nextInt();
Point[] tmpPoints = new Point[n];
for (i = 0; i < n; i++) {
double[] num = new double[dim];
for (j = 0; j < dim; j++) num[j] = sc.nextDouble();
tmpPoints[i] = new Point(dim, num);
}
cluster = new kMeans(k, tmpPoints);
cluster.getCluster();
// calculate the sse value after clustering
cluster.sseValue = 0.0;
for (i = 0; i < n; i++) {
cluster.sseValue +=
cluster.points[i].distEuclid(cluster.centroids[cluster.points[i].clusterIndex]);
}
System.out.println("The SSE of after clustering is: " + cluster.sseValue);
/*
int[] clusterCount = new int[k];
for(i = 0; i < k; i++){
clusterCount[i] = 0;
}
for(i = 0; i < cluster.points.length; i++){
clusterCount[cluster.points[i].clusterIndex]++;
//System.out.print(cluster.points[i].clusterIndex);
//System.out.print(" ");
}
System.out.println(" ");
for(i = 0; i < k; i++){
System.out.println(clusterCount[i]);
}
*/
}
/**
* Main method -- to test the kMeans class
*
* @param args command line arguments
*/
public static void main(String[] args) {
// //对用户矩阵，从3到100个聚类数目，分别计算这个数目下的聚类结果，写入文件
// for(int z = 3; z <=100; z++){
//
// //计算z个聚类的聚类结果
// kMeans km = new kMeans(z, "D:/pca/pcauserM0.85.txt");
//
// try {
// km.readData();
// } catch (Exception e) {
// System.err.println(e);
// System.exit(-1);
// }
//
// km.runKMeans();
// System.out.println(km.getDataPoints().size());
// System.out.println(km.getDataPoints().get(0));
// System.out.println(km.getDataPoints().get(km.getDataPoints().size()-1));
//
// //把结果写入文件
//// Iterator i = this.kMeansPoints.iterator();
//// while (i.hasNext()){
//// //设置一个String用来写入到文件
//// String strWr = new String();
//// strWr = "\n" + (kMeansPoint)(i.next());
//// }
//
// //把结果写入文件
// for(int i = 0; i < km.getDataPoints().size(); i++){
// //设置一个String用来写入到文件
// String strWr = new String();
// kMeansPoint kmp = (kMeansPoint) km.getDataPoints().get(i);
// strWr = i+":"+ kmp.getClusterNumber();
//
// //设置一个路径用来保存文件
// String pathZ = "D:/pca/difClusters/kM_" + z + "kind_0.85_0.3user.txt";
// write(pathZ, strWr);
// }
// }
// //给电影矩阵聚类，从3到100个聚类数目，分别计算这个数目下的聚类结果，写入文件
// for(int z = 3; z <=100; z++){
// //计算z个聚类的聚类结果
// kMeans km = new kMeans(z, "D:/pca/pcauserMovieM0.85.txt");
//
// try {
// km.readData();
// } catch (Exception e) {
// System.err.println(e);
// System.exit(-1);
// }
//
// km.runKMeans();
// System.out.println(km.getDataPoints().size());
// System.out.println(km.getDataPoints().get(0));
// System.out.println(km.getDataPoints().get(km.getDataPoints().size()-1));
//
// //把结果写入文件
//// Iterator i = this.kMeansPoints.iterator();
//// while (i.hasNext()){
//// //设置一个String用来写入到文件
//// String strWr = new String();
//// strWr = "\n" + (kMeansPoint)(i.next());
//// }
//
// //把结果写入文件
// for(int i = 0; i < km.getDataPoints().size(); i++){
// //设置一个String用来写入到文件
// String strWr = new String();
// kMeansPoint kmp = (kMeansPoint) km.getDataPoints().get(i);
// strWr = i+":"+ kmp.getClusterNumber();
//
// //设置一个路径用来保存文件
// String pathZ = "D:/pca/difMovieClusters/kM_" + z + "kind_0.85_0.3movie.txt";
// write(pathZ, strWr);
// }
// }
// 给用户-电影类别矩阵聚类，从3到100个聚类数目，分别计算这个数目下的聚类结果，写入文件
for (int z = 238; z <= 300; z++) {
// 计算z个聚类的聚类结果
kMeans km = new kMeans(z, "D:/pca/recommendWork/pcamovieByAdd1Matrix0.85.txt");
try {
km.readData();
} catch (Exception e) {
System.err.println(e);
System.exit(-1);
}
km.runKMeans();
System.out.println(km.getDataPoints().size());
System.out.println(km.getDataPoints().get(0));
System.out.println(km.getDataPoints().get(km.getDataPoints().size() - 1));
// 把结果写入文件
// Iterator i = this.kMeansPoints.iterator();
// while (i.hasNext()){
// //设置一个String用来写入到文件
// String strWr = new String();
// strWr = "\n" + (kMeansPoint)(i.next());
// }s
// 把结果写入文件
for (int i = 0; i < km.getDataPoints().size(); i++) {
// 设置一个String用来写入到文件
String strWr = new String();
kMeansPoint kmp = (kMeansPoint) km.getDataPoints().get(i);
strWr = i + ":" + kmp.getClusterNumber();
// 设置一个路径用来保存文件
String pathZ = "D:/pca/recommendWork/difMovClusters/kM_" + z + "kind_0.85_clu_movie.txt";
write(pathZ, strWr);
}
}
} // end of main()