求助！关于基于Hadoop的mahout聚类计算问题

[hyous]

本人菜鸟一枚，尝试在虚拟机搭建的伪分布式环境下，跑mahout的kmeans算法。
数据文件保存在test.txt中，将数据转换为List<Vector>，然后通过writePointsToFile（）转换为sequenceFile
问题是这样似乎txt大小有一定限制，数据文件10M的时候可以跑，100M数据似乎就转换不过来了... ...

请问怎么改动能让它跑更大型的数据文件？？？
求解答，谢谢！！！

public class Kmeans {
	
	public static List<Vector> FileToVector(FileInputStream fs) throws IOException {
		BufferedReader br = new BufferedReader(new InputStreamReader(fs));
    	String readLine = null;
    	List<Vector> points = new ArrayList<Vector>();
    	 double []data=new double[20];
        while ((readLine = br.readLine()) != null) {
    		 String[] point=readLine.split(" ");
             for(int j=0;j<20;j++) 
            	 data[j] = Double.parseDouble(point[j]);
    		 
    		 //double[] fr = data;
    		 Vector vec = new RandomAccessSparseVector(data.length);
    		 vec.assign(data);
    		 points.add(vec);
    		 }
            br.close();
    		return points;	
    	}

public static void writePointsToFile(List<Vector> points,
										String fileName,
										FileSystem fs,
										Configuration conf) throws IOException {
		Path path = new Path(fileName);
		
		//SequenceFile.Writer（FileSystem, Configuration, Path, key.getClass(), value.getClass()）
		SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf,
		path, LongWritable.class, VectorWritable.class);
		long recNum = 0;
		VectorWritable vec = new VectorWritable();
		for (Vector point : points) {
			vec.set(point);
			writer.append(new LongWritable(recNum++), vec);
			
		}
		writer.close();
	}
public static void main(String args[]) throws Exception {
		
		FileInputStream fis = new FileInputStream("E:\\Users\\ZZS\\Desktop\\结果\\new-data\\test.txt");
System.setProperty("HADOOP_USER_NAME", "root");
		int k = 4;
		List<Vector> vectors =FileToVector(fis);
		//List<Vector> vectors = getPoints(points);
 
		File testData = new File("clustering/testdata");
		if (!testData.exists()) {
			testData.mkdir();
		}
		testData = new File("clustering/testdata/points");
		if (!testData.exists()) {
			testData.mkdir();
		}
 
		Configuration conf = new Configuration();
		FileSystem fs = FileSystem.get(conf);
		//使得file1中存放可以被mahout识别的向量文件
		writePointsToFile(vectors, "clustering/testdata/points/file1", fs, conf);
 
		Path path = new Path("clustering/testdata/clusters/part-00000");
		
		SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf, path, Text.class, Kluster.class);

for (int i = 0; i < k; i++) {
			//int n=(int) (Math.random() * points.length);  
			Vector vec = vectors.get(i);
			Kluster cluster = new Kluster(vec, i, new EuclideanDistanceMeasure());//采用欧几里得测距方式测量两点之间的距离
			writer.append(new Text(cluster.getIdentifier()), cluster);
		}
		writer.close();
		KMeansDriver.run(conf,
		new Path("clustering/testdata/points"),     //inputPath
		new Path("clustering/testdata/clusters"),   //ClusterPath
		new Path("clustering/output"),              //OutputPath
		0.001,                                      //convergenceDelta收敛系数 
		10,                                         //MaxIterations
		true,                                       //runCLustering
		0,                                          //clusterClassificationThreshold
		true);                                      //runSequential
		
		SequenceFile.Reader reader = new SequenceFile.Reader(fs,
		new Path("clustering/output/" + "clusteredPoints"+"/part-m-0"), conf);
		
		
		File f2 = new File("E:\\结果\\hadoop\\kmeans");
		PrintStream ps = new PrintStream(f2.getPath());
		//PrintStream Console = System.out;
		System.setOut(ps);
		
		
		IntWritable key = new IntWritable();
		
		WeightedPropertyVectorWritable value = new WeightedPropertyVectorWritable();
		//ClusterWritable value=new ClusterWritable();
		while (reader.next(key, value)) {
			System.out.println(value.toString() + " belongs to cluster " + key.toString());
		}
		ps.close();
		reader.close();
	}
 
}

	]

[hyous]

有人看一下吗？