Example #1
0
  /** Process the training and test files provided in the parameters file to the constructor. */
  public void process() {
    double[] outputs;
    double[] outputs2;
    Instance neighbor;
    double dist, mean;
    int actual;
    int[] N = new int[nneigh];
    double[] Ndist = new double[nneigh];
    boolean allNull;
    svm_problem SVMp = null;
    svm_parameter SVMparam = new svm_parameter();
    svm_model svr = null;
    svm_node SVMn[];
    double[] outputsCandidate = null;
    boolean same = true;
    Vector instancesSelected = new Vector();
    Vector instancesSelected2 = new Vector();

    // SVM PARAMETERS
    SVMparam.C = C;
    SVMparam.cache_size = 10; // 10MB of cache
    SVMparam.degree = degree;
    SVMparam.eps = eps;
    SVMparam.gamma = gamma;
    SVMparam.nr_weight = 0;
    SVMparam.nu = nu;
    SVMparam.p = p;
    SVMparam.shrinking = shrinking;
    SVMparam.probability = 0;
    if (kernelType.compareTo("LINEAR") == 0) {
      SVMparam.kernel_type = svm_parameter.LINEAR;
    } else if (kernelType.compareTo("POLY") == 0) {
      SVMparam.kernel_type = svm_parameter.POLY;
    } else if (kernelType.compareTo("RBF") == 0) {
      SVMparam.kernel_type = svm_parameter.RBF;
    } else if (kernelType.compareTo("SIGMOID") == 0) {
      SVMparam.kernel_type = svm_parameter.SIGMOID;
    }

    SVMparam.svm_type = svm_parameter.EPSILON_SVR;

    try {

      // Load in memory a dataset that contains a classification problem
      IS.readSet(input_train_name, true);
      int in = 0;
      int out = 0;

      ndatos = IS.getNumInstances();
      nvariables = Attributes.getNumAttributes();
      nentradas = Attributes.getInputNumAttributes();
      nsalidas = Attributes.getOutputNumAttributes();

      X = new String[ndatos][2]; // matrix with transformed data

      mostCommon = new String[nvariables];
      SVMp = new svm_problem();
      SVMp.l = ndatos;
      SVMp.y = new double[SVMp.l];
      SVMp.x = new svm_node[SVMp.l][nentradas + 1];
      for (int l = 0; l < SVMp.l; l++) {
        for (int n = 0; n < Attributes.getInputNumAttributes() + 1; n++) {
          SVMp.x[l][n] = new svm_node();
        }
      }

      for (int i = 0; i < ndatos; i++) {
        Instance inst = IS.getInstance(i);

        SVMp.y[i] = inst.getAllOutputValues()[0];
        for (int n = 0; n < Attributes.getInputNumAttributes(); n++) {
          SVMp.x[i][n].index = n;
          SVMp.x[i][n].value = inst.getAllInputValues()[n];
          SVMp.y[i] = inst.getAllOutputValues()[0];
        }
        // end of instance
        SVMp.x[i][nentradas].index = -1;
      }
      if (svm.svm_check_parameter(SVMp, SVMparam) != null) {
        System.out.println("SVM parameter error in training:");
        System.out.println(svm.svm_check_parameter(SVMp, SVMparam));
        System.exit(-1);
      }
      // train the SVM
      if (ndatos > 0) {
        svr = svm.svm_train(SVMp, SVMparam);
      }
      for (int i = 0; i < ndatos; i++) {
        Instance inst = IS.getInstance(i);
        X[i][0] = new String(String.valueOf(inst.getAllOutputValues()[0]));
        //			the values used for regression
        SVMn = new svm_node[Attributes.getInputNumAttributes() + 1];
        for (int n = 0; n < Attributes.getInputNumAttributes(); n++) {
          SVMn[n] = new svm_node();
          SVMn[n].index = n;
          SVMn[n].value = inst.getAllInputValues()[n];
        }
        SVMn[nentradas] = new svm_node();
        SVMn[nentradas].index = -1;
        // pedict the class
        X[i][1] = new String(String.valueOf((svm.svm_predict(svr, SVMn))));
      }
    } catch (Exception e) {
      System.out.println("Dataset exception = " + e);
      e.printStackTrace();
      System.exit(-1);
    }
    write_results(output_train_name);
    /** ************************************************************************************ */
    try {

      // Load in memory a dataset that contains a classification
      // problem
      IS.readSet(input_test_name, false);
      int in = 0;
      int out = 0;

      ndatos = IS.getNumInstances();
      nvariables = Attributes.getNumAttributes();
      nentradas = Attributes.getInputNumAttributes();
      nsalidas = Attributes.getOutputNumAttributes();

      X = new String[ndatos][2]; // matrix with transformed data
      // data

      mostCommon = new String[nvariables];

      for (int i = 0; i < ndatos; i++) {
        Instance inst = IS.getInstance(i);
        X[i][0] = new String(String.valueOf(inst.getAllOutputValues()[0]));

        SVMn = new svm_node[Attributes.getInputNumAttributes() + 1];
        for (int n = 0; n < Attributes.getInputNumAttributes(); n++) {
          SVMn[n] = new svm_node();
          SVMn[n].index = n;
          SVMn[n].value = inst.getAllInputValues()[n];
        }
        SVMn[nentradas] = new svm_node();
        SVMn[nentradas].index = -1;
        // pedict the class
        X[i][1] = new String(String.valueOf(svm.svm_predict(svr, SVMn)));
      }
    } catch (Exception e) {
      System.out.println("Dataset exception = " + e);
      e.printStackTrace();
      System.exit(-1);
    }
    System.out.println("escribiendo test");
    write_results(output_test_name);
  }
Example #2
0
	public static svm_model svm_load_model(String model_file_name) throws IOException
	{
		BufferedReader fp = new BufferedReader(new FileReader(model_file_name));

		// read parameters

		svm_model model = new svm_model();
		svm_parameter param = new svm_parameter();
		model.param = param;
		model.label = null;
		model.nSV = null;

		while(true)
		{
			String cmd = fp.readLine();
			String arg = cmd.substring(cmd.indexOf(' ')+1);

			if(cmd.startsWith("svm_type"))
			{
				int i;
				for(i=0;i<svm_type_table.length;i++)
				{
					if(arg.indexOf(svm_type_table[i])!=-1)
					{
						param.svm_type=i;
						break;
					}
				}
				if(i == svm_type_table.length)
				{
					System.err.print("unknown svm type.\n");
					System.exit(1);
				}
			}
			else if(cmd.startsWith("kernel_type"))
			{
				int i;
				for(i=0;i<kernel_type_table.length;i++)
				{
					if(arg.indexOf(kernel_type_table[i])!=-1)
					{
						param.kernel_type=i;
						break;
					}
				}
				if(i == kernel_type_table.length)
				{
					System.err.print("unknown kernel function.\n");
					System.exit(1);
				}
			}
			else if(cmd.startsWith("degree"))
				param.degree = atof(arg);
			else if(cmd.startsWith("gamma"))
				param.gamma = atof(arg);
			else if(cmd.startsWith("coef0"))
				param.coef0 = atof(arg);
			else if(cmd.startsWith("nr_class"))
				model.nr_class = atoi(arg);
			else if(cmd.startsWith("total_sv"))
				model.l = atoi(arg);
			else if(cmd.startsWith("rho"))
			{
				int n = model.nr_class * (model.nr_class-1)/2;
				model.rho = new double[n];
				StringTokenizer st = new StringTokenizer(arg);
				for(int i=0;i<n;i++)
					model.rho[i] = atof(st.nextToken());
			}
			else if(cmd.startsWith("label"))
			{
				int n = model.nr_class;
				model.label = new int[n];
				StringTokenizer st = new StringTokenizer(arg);
				for(int i=0;i<n;i++)
					model.label[i] = atoi(st.nextToken());					
			}
			else if(cmd.startsWith("nr_sv"))
			{
				int n = model.nr_class;
				model.nSV = new int[n];
				StringTokenizer st = new StringTokenizer(arg);
				for(int i=0;i<n;i++)
					model.nSV[i] = atoi(st.nextToken());
			}
			else if(cmd.startsWith("SV"))
			{
				break;
			}
			else
			{
				System.err.print("unknown text in model file\n");
				System.exit(1);
			}
		}

		// read sv_coef and SV

		int m = model.nr_class - 1;
		int l = model.l;
		model.sv_coef = new double[m][l];
		model.SV = new svm_node[l][];

		for(int i=0;i<l;i++)
		{
			String line = fp.readLine();
			StringTokenizer st = new StringTokenizer(line," \t\n\r\f:");

			for(int k=0;k<m;k++)
				model.sv_coef[k][i] = atof(st.nextToken());
			int n = st.countTokens()/2;
			model.SV[i] = new svm_node[n];
			for(int j=0;j<n;j++)
			{
				model.SV[i][j] = new svm_node();
				model.SV[i][j].index = atoi(st.nextToken());
				model.SV[i][j].value = atof(st.nextToken());
			}
		}

		fp.close();
		return model;
	}