/// <summary>
/// Import the model from an xml file
/// </summary>
public void Import(string model_file_name)
{
try
{
XmlSerializer serializer = new XmlSerializer(typeof(svm_model));
FileStream fs = new FileStream(model_file_name, FileMode.Open);
this.model = (svm_model)serializer.Deserialize(fs);
fs.Close();
}
catch (Exception ex)
{
throw new Exception("An error occured when importing svm model: " + ex.Message);
}
}
/// <summary>
///
/// </summary>
/// <param name="text"></param>
/// <returns></returns>
public void klassifiziere(string text, Hashtable vektorraum, svm_model model)
{
FeatureVector fv = new FeatureVector(text);
fv.Vektorraum = vektorraum;
fv.ErzeugeVektor();
LibSVMWrapper lsvmwrap = new LibSVMWrapper();
lsvmwrap.SVMModel = model;
lsvmwrap.klazzifiziere(fv.Vektor);
label = lsvmwrap.Label;
labels = lsvmwrap.Labels;
probs = lsvmwrap.Wahrscheinlichkeiten;
}
public bool LoadFromFile(string fileName)
{
if (File.Exists(fileName))
{
FileStream fs = new FileStream(fileName, FileMode.Open);
using (BinaryReader r = new BinaryReader(fs))
{
this.model = new svm_model();
svm_parameter p = new svm_parameter();
p.C = r.ReadDouble();
p.cache_size = r.ReadDouble();
p.coef0 = r.ReadDouble();
p.degree = r.ReadDouble();
p.eps = r.ReadDouble();
p.gamma = r.ReadDouble();
p.kernel_type = r.ReadInt32();
p.nr_weight = r.ReadInt32();
p.nu = r.ReadDouble();
p.p = r.ReadDouble();
p.probability = r.ReadInt32();
p.shrinking = r.ReadInt32();
p.svm_type = r.ReadInt32();
p.weight = ReadDoubleArray(r);
p.weight_label = ReadIntArray(r);
this.model.param = p;
this.model.nr_class = r.ReadInt32();
this.model.l = r.ReadInt32();
this.model.SV = ReadSvmNodeArray(r);
this.model.sv_coef = ReadDouble2DArray(r);
this.model.rho = ReadDoubleArray(r);
this.model.probA = ReadDoubleArray(r);
this.model.probB = ReadDoubleArray(r);
this.model.label = ReadIntArray(r);
this.model.nSV = ReadIntArray(r);
return true;
}
}
this.model = null;
return false;
}
private void run(System.String[] argv)
{
parse_command_line(argv);
read_problem();
error_msg = svm.svm_check_parameter(prob, param);
if ((System.Object) error_msg != null)
{
System.Console.Error.Write("Error: " + error_msg + "\n");
System.Environment.Exit(1);
}
if (cross_validation != 0)
{
do_cross_validation();
}
else
{
model = svm.svm_train(prob, param);
svm.svm_save_model(model_file_name, model);
}
}
public static int svm_get_svm_type(svm_model model)
{
return model.param.svm_type;
}
public static int svm_get_nr_class(svm_model model)
{
return model.nr_class;
}
public static void svm_get_labels(svm_model model, int[] label)
{
if (model.label != null)
for (int i = 0; i < model.nr_class; i++)
label[i] = model.label[i];
}
//
// Interface functions
//
public static svm_model svm_train(svm_problem prob, svm_parameter param, TrainingProgressEvent progressEvent = null)
{
svm_model model = new svm_model();
model.param = param;
if (param.svm_type == svm_parameter.ONE_CLASS || param.svm_type == svm_parameter.EPSILON_SVR || param.svm_type == svm_parameter.NU_SVR)
{
// regression or one-class-svm
model.nr_class = 2;
model.label = null;
model.nSV = null;
model.probA = null; model.probB = null;
model.sv_coef = new double[1][];
if (param.probability == 1 && (param.svm_type == svm_parameter.EPSILON_SVR || param.svm_type == svm_parameter.NU_SVR))
{
model.probA = new double[1];
model.probA[0] = svm_svr_probability(prob, param);
}
decision_function f = svm_train_one(prob, param, 0, 0);
model.rho = new double[1];
model.rho[0] = f.rho;
int nSV = 0;
int i;
for (i = 0; i < prob.l; i++)
if (System.Math.Abs(f.alpha[i]) > 0)
++nSV;
model.l = nSV;
model.SV = new svm_node[nSV][];
model.sv_coef[0] = new double[nSV];
int j = 0;
for (i = 0; i < prob.l; i++)
if (System.Math.Abs(f.alpha[i]) > 0)
{
model.SV[j] = prob.x[i];
model.sv_coef[0][j] = f.alpha[i];
++j;
}
}
else
{
// classification
// find out the number of classes
int l = prob.l;
int max_nr_class = 16;
int nr_class = 0;
int[] label = new int[max_nr_class];
int[] count = new int[max_nr_class];
int[] index = new int[l];
int i;
for (i = 0; i < l; i++)
{
//UPGRADE_WARNING: Data types in Visual C# might be different. Verify the accuracy of narrowing conversions. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1042_3"'
int this_label = (int)prob.y[i];
int j;
for (j = 0; j < nr_class; j++)
if (this_label == label[j])
{
++count[j];
break;
}
index[i] = j;
if (j == nr_class)
{
if (nr_class == max_nr_class)
{
max_nr_class *= 2;
int[] new_data = new int[max_nr_class];
Array.Copy(label, 0, new_data, 0, label.Length);
label = new_data;
new_data = new int[max_nr_class];
Array.Copy(count, 0, new_data, 0, count.Length);
count = new_data;
}
label[nr_class] = this_label;
count[nr_class] = 1;
++nr_class;
}
}
// group training data of the same class
int[] start = new int[nr_class];
start[0] = 0;
for (i = 1; i < nr_class; i++)
start[i] = start[i - 1] + count[i - 1];
svm_node[][] x = new svm_node[l][];
for (i = 0; i < l; i++)
{
x[start[index[i]]] = prob.x[i];
++start[index[i]];
}
start[0] = 0;
for (i = 1; i < nr_class; i++)
start[i] = start[i - 1] + count[i - 1];
// calculate weighted C
double[] weighted_C = new double[nr_class];
for (i = 0; i < nr_class; i++)
weighted_C[i] = param.C;
for (i = 0; i < param.nr_weight; i++)
{
int j;
for (j = 0; j < nr_class; j++)
if (param.weight_label[i] == label[j])
break;
if (j == nr_class)
System.Console.Error.Write("warning: class label " + param.weight_label[i] + " specified in weight is not found\n");
else
weighted_C[j] *= param.weight[i];
}
// train k*(k-1)/2 models
bool[] nonzero = new bool[l];
for (i = 0; i < l; i++)
nonzero[i] = false;
decision_function[] f = new decision_function[nr_class * (nr_class - 1) / 2];
double[] probA = null, probB = null;
if (param.probability == 1)
{
probA = new double[nr_class * (nr_class - 1) / 2];
probB = new double[nr_class * (nr_class - 1) / 2];
}
int p = 0;
for (i = 0; i < nr_class; i++)
for (int j = i + 1; j < nr_class; j++)
{
svm_problem sub_prob = new svm_problem();
int si = start[i], sj = start[j];
int ci = count[i], cj = count[j];
sub_prob.l = ci + cj;
sub_prob.x = new svm_node[sub_prob.l][];
sub_prob.y = new double[sub_prob.l];
int k;
for (k = 0; k < ci; k++)
{
sub_prob.x[k] = x[si + k];
sub_prob.y[k] = +1;
}
for (k = 0; k < cj; k++)
{
sub_prob.x[ci + k] = x[sj + k];
sub_prob.y[ci + k] = -1;
}
if (param.probability == 1)
{
double[] probAB = new double[2];
svm_binary_svc_probability(sub_prob, param, weighted_C[i], weighted_C[j], probAB);
probA[p] = probAB[0];
probB[p] = probAB[1];
}
f[p] = svm_train_one(sub_prob, param, weighted_C[i], weighted_C[j]);
for (k = 0; k < ci; k++)
if (!nonzero[si + k] && System.Math.Abs(f[p].alpha[k]) > 0)
nonzero[si + k] = true;
for (k = 0; k < cj; k++)
if (!nonzero[sj + k] && System.Math.Abs(f[p].alpha[ci + k]) > 0)
nonzero[sj + k] = true;
++p;
}
// build output
model.nr_class = nr_class;
model.label = new int[nr_class];
for (i = 0; i < nr_class; i++)
model.label[i] = label[i];
model.rho = new double[nr_class * (nr_class - 1) / 2];
for (i = 0; i < nr_class * (nr_class - 1) / 2; i++)
model.rho[i] = f[i].rho;
if (param.probability == 1)
{
model.probA = new double[nr_class * (nr_class - 1) / 2];
model.probB = new double[nr_class * (nr_class - 1) / 2];
for (i = 0; i < nr_class * (nr_class - 1) / 2; i++)
{
model.probA[i] = probA[i];
model.probB[i] = probB[i];
}
}
else
{
model.probA = null;
model.probB = null;
}
int nnz = 0;
int[] nz_count = new int[nr_class];
model.nSV = new int[nr_class];
for (i = 0; i < nr_class; i++)
{
int nSV = 0;
for (int j = 0; j < count[i]; j++)
if (nonzero[start[i] + j])
{
++nSV;
++nnz;
}
model.nSV[i] = nSV;
nz_count[i] = nSV;
}
//Debug.WriteLine("Total nSV = " + nnz + "\n");
model.l = nnz;
model.SV = new svm_node[nnz][];
p = 0;
for (i = 0; i < l; i++)
if (nonzero[i])
model.SV[p++] = x[i];
int[] nz_start = new int[nr_class];
nz_start[0] = 0;
for (i = 1; i < nr_class; i++)
nz_start[i] = nz_start[i - 1] + nz_count[i - 1];
model.sv_coef = new double[nr_class - 1][];
for (i = 0; i < nr_class - 1; i++)
model.sv_coef[i] = new double[nnz];
p = 0;
for (i = 0; i < nr_class; i++)
for (int j = i + 1; j < nr_class; j++)
{
// classifier (i,j): coefficients with
// i are in sv_coef[j-1][nz_start[i]...],
// j are in sv_coef[i][nz_start[j]...]
int si = start[i];
int sj = start[j];
int ci = count[i];
int cj = count[j];
int q = nz_start[i];
int k;
for (k = 0; k < ci; k++)
if (nonzero[si + k])
model.sv_coef[j - 1][q++] = f[p].alpha[k];
q = nz_start[j];
for (k = 0; k < cj; k++)
if (nonzero[sj + k])
model.sv_coef[i][q++] = f[p].alpha[ci + k];
++p;
}
}
return model;
}
public static void svm_predict_values(svm_model model, svm_node[] x, double[] dec_values)
{
if (model.param.svm_type == svm_parameter.ONE_CLASS || model.param.svm_type == svm_parameter.EPSILON_SVR || model.param.svm_type == svm_parameter.NU_SVR)
{
double[] sv_coef = model.sv_coef[0];
double sum = 0;
for (int i = 0; i < model.l; i++)
sum += sv_coef[i] * Kernel.k_function(x, model.SV[i], model.param);
sum -= model.rho[0];
dec_values[0] = sum;
}
else
{
int i;
int nr_class = model.nr_class;
int l = model.l;
double[] kvalue = new double[l];
for (i = 0; i < l; i++)
kvalue[i] = Kernel.k_function(x, model.SV[i], model.param);
int[] start = new int[nr_class];
start[0] = 0;
for (i = 1; i < nr_class; i++)
start[i] = start[i - 1] + model.nSV[i - 1];
int p = 0;
int pos = 0;
for (i = 0; i < nr_class; i++)
for (int j = i + 1; j < nr_class; j++)
{
double sum = 0;
int si = start[i];
int sj = start[j];
int ci = model.nSV[i];
int cj = model.nSV[j];
int k;
double[] coef1 = model.sv_coef[j - 1];
double[] coef2 = model.sv_coef[i];
for (k = 0; k < ci; k++)
sum += coef1[si + k] * kvalue[si + k];
for (k = 0; k < cj; k++)
sum += coef2[sj + k] * kvalue[sj + k];
sum -= model.rho[p++];
dec_values[pos++] = sum;
}
}
}
public static double svm_predict(svm_model model, svm_node[] x)
{
if (model.param.svm_type == svm_parameter.ONE_CLASS || model.param.svm_type == svm_parameter.EPSILON_SVR || model.param.svm_type == svm_parameter.NU_SVR)
{
double[] res = new double[1];
svm_predict_values(model, x, res);
if (model.param.svm_type == svm_parameter.ONE_CLASS)
return (res[0] > 0)?1:- 1;
else
return res[0];
}
else
{
int i;
int nr_class = model.nr_class;
double[] dec_values = new double[nr_class * (nr_class - 1) / 2];
svm_predict_values(model, x, dec_values);
int[] vote = new int[nr_class];
for (i = 0; i < nr_class; i++)
vote[i] = 0;
int pos = 0;
for (i = 0; i < nr_class; i++)
for (int j = i + 1; j < nr_class; j++)
{
if (dec_values[pos++] > 0)
++vote[i];
else
++vote[j];
}
int vote_max_idx = 0;
for (i = 1; i < nr_class; i++)
if (vote[i] > vote[vote_max_idx])
vote_max_idx = i;
return model.label[vote_max_idx];
}
}
public SvmModelBuilder()
{
this.model = null;
}
/// <summary>
/// Train the SVM and save the model
/// </summary>
public void Train()
{
this.model = svm.svm_train(prob, param);
}
/// <summary>
/// Import the model from an xml file
/// </summary>
public void Import(string model_file_name)
{
try
{
XmlSerializer serializer = new XmlSerializer(typeof(svm_model));
FileStream fs = new FileStream(model_file_name, FileMode.Open);
this.model = (svm_model) serializer.Deserialize(fs);
fs.Close();
}
catch (Exception ex)
{
throw new Exception("An error occured when importing svm model: " + ex.Message);
}
}
public void TrainLibSVM(double[][] vektoren, double[] labels, double currentC, double currentG, out int errorCount)
{
int nrdocs = vektoren.Length;
svm_problem prob = new svm_problem();
prob.l = vektoren.Length - 1;
prob.y = labels;
svm_node[][] nodes = new svm_node[nrdocs][];
for (int i = 0; i < vektoren.Length; i++)
{
int dim = vektoren[i].Length;
nodes[i] = new svm_node[dim + 1];
for (int j = 0; j < dim; j++)
{
svm_node n = new svm_node();
n.index = j;
n.value_Renamed = vektoren[i][j];
nodes[i][j] = n;
}
svm_node ln = new svm_node();
ln.index = -1;
ln.value_Renamed = 0;
nodes[i][dim] = ln;
}
prob.x = nodes;
svm_parameter param = new svm_parameter();
param.cache_size = 256.0;
param.C = 1000.0;
//param.weight = new double[] { 1.0, 1.0, 1.0, 1.0, 1.0 };
//param.weight_label = new int[] { 1, 1, 1, 1, 1 };
param.svm_type = svm_parameter.C_SVC;
param.kernel_type = svm_parameter.SIGMOID;
param.gamma = 0.00000001;
param.eps = 0.0001;
//param.nr_weight = 0;
param.probability = 1;
//double[] cs;
//double[] gs;
double[] cergs = new double[labels.Length];
int minfehler = labels.Length;
int fehler = 0;
double c = 0.0;
double g = 0.0;
#region Parameterabstimmung
//cs = new double[] { Math.Pow(2.0, -15.0), Math.Pow(2.0, -11.0), Math.Pow(2.0, -9.0), Math.Pow(2.0, -7.0), Math.Pow(2.0, -5.0), Math.Pow(2.0, -3.0), Math.Pow(2.0, -1.0), Math.Pow(2.0, 1.0), Math.Pow(2.0, 3.0), Math.Pow(2.0, 5.0), Math.Pow(2.0, 7.0), Math.Pow(2.0, 12.0), Math.Pow(2.0, 15.0) };
//gs = new double[] { Math.Pow(2.0, -15.0), Math.Pow(2.0, -12.0), Math.Pow(2.0, -9.0), Math.Pow(2.0, -7.0), Math.Pow(2.0, -5.0), Math.Pow(2.0, -3.0), Math.Pow(2.0, -1.0), Math.Pow(2.0, 1.0), Math.Pow(2.0, 3.0) };
//cs = new double[] { Math.Pow(2.0, -3.0), Math.Pow(2.0, -1.0), Math.Pow(2.0, 1.0), Math.Pow(2.0, 3.0), Math.Pow(2.0, 5.0), Math.Pow(2.0, 7.0), Math.Pow(2.0, 12.0) };
//gs = new double[] { Math.Pow(2.0, -7.0), Math.Pow(2.0, -5.0), Math.Pow(2.0, -3.0), Math.Pow(2.0, -1.0), Math.Pow(2.0, 1.0), Math.Pow(2.0, 3.0) };
//for (int i = 0; i < cs.Length; i++)
//{
// param.C = cs[i];
// for (int j = 0; j < gs.Length; j++)
// {
// fehler = 0;
// param.gamma = gs[j];
// string res = svm.svm_check_parameter(prob, param);
// if (res == null)
// {
// svm.svm_cross_validation(prob, param, vektoren.Length/4, cergs);
// for (int k = 0; k < labels.Length; k++)
// {
// if (cergs[k] != labels[k])
// fehler++;
// }
// if (fehler < minfehler)
// {
// minfehler = fehler;
// c = param.C;
// g = param.gamma;
// }
// }
// }
//}
param.C = currentC;
fehler = 0;
param.gamma = currentG;
string res = svm.svm_check_parameter(prob, param);
if (res == null)
{
svm.svm_cross_validation(prob, param, vektoren.Length / 4, cergs);
for (int k = 0; k < labels.Length; k++)
{
if (cergs[k] != labels[k])
{
fehler++;
}
}
if (fehler < minfehler)
{
minfehler = fehler;
c = param.C;
g = param.gamma;
}
}
#endregion
#region Feinabstimmung
//cs = new double[] { c * 0.3, c * 0.4, c * 0.5, c * 0.6, c * 0.7, c * 0.8, c * 0.9, c, c * 2.0, c * 3.0, c * 4.0, c * 5.0, c * 6.0 };
//gs = new double[] { g * 0.5, g * 0.6, g * 0.7, g * 0.8, g * 0.9, g, g * 2.0, g * 3.0, g * 4.0 };
double[] csF = new double[] { c * 0.6, c * 0.7, c * 0.8, c * 0.9, c, c * 2.0, c * 3.0 };
double[] gsF = new double[] { g * 0.7, g * 0.8, g * 0.9, g, g * 2.0, g * 3.0 };
for (int i = 0; i < csF.Length; i++)
{
param.C = csF[i];
for (int j = 0; j < gsF.Length; j++)
{
fehler = 0;
param.gamma = gsF[j];
res = svm.svm_check_parameter(prob, param);
if (res == null)
{
svm.svm_cross_validation(prob, param, vektoren.Length / 4, cergs);
for (int k = 0; k < labels.Length; k++)
{
if (cergs[k] != labels[k])
{
fehler++;
}
}
if (fehler < minfehler)
{
minfehler = fehler;
c = param.C;
g = param.gamma;
}
}
//Thread.Sleep(1);
}
//Thread.Sleep(10);
}
#endregion
#region Superfeinabstimmung
//cs = new double[] { c - 7.0, c - 6.0, c - 5.0, c - 4.0, c - 3.0, c - 2.0, c - 1.0, c, c + 1.0, c + 2.0, c + 3.0, c + 4.0, c + 5.0 };
//gs = new double[] { g - 5.0, g - 4.0, g - 3.0, g - 2.0, g - 1.0, g, g + 1.0, g + 2.0, g + 3.0 };
/*cs = new double[] { c - 1.0, c - 0.3, c - 0.1, c, c + 0.1, c + 0.3, c + 1.0, };
* gs = new double[] { g - 1.0, g - 0.3, g - 0.1, g, g + 0.1, g + 0.3, g + 1.0 };
* for (int i = 0; i < cs.Length; i++)
* {
* param.C = cs[i];
*
* for (int j = 0; j < gs.Length; j++)
* {
* fehler = 0;
* param.gamma = gs[j];
* string res = svm.svm_check_parameter(prob, param);
* if (res == null)
* {
* svm.svm_cross_validation(prob, param, 6, cergs);
*
* for (int k = 0; k < labels.Length; k++)
* {
* if (cergs[k] != labels[k])
* fehler++;
* }
* if (fehler < minfehler)
* {
* minfehler = fehler;
* c = param.C;
* g = param.gamma;
* }
* }
* }
* }*/
#endregion
param.C = c;
param.gamma = g;
this._model = new svm_model();
this._model = svm.svm_train(prob, param);
int anzKlassen = svm.svm_get_nr_class(this._model);
double[] probs = new double[anzKlassen];
double erg;
erg = svm.svm_predict_probability(this._model, nodes[0], probs);
//erg = svm.svm_predict_probability(this._model, nodes[11], probs);
//klazzifiziere(this.testvektor);
//klazzifiziere(vektoren[6]);
errorCount = minfehler;
}
public static double svm_get_svr_probability(svm_model model)
{
if ((model.param.svm_type == svm_parameter.EPSILON_SVR || model.param.svm_type == svm_parameter.NU_SVR) && model.probA != null)
return model.probA[0];
else
{
System.Console.Error.Write("Model doesn't contain information for SVR probability inference\n");
return 0;
}
}
public static svm_model svm_load_model(System.String model_file_name)
{
//UPGRADE_TODO: The differences in the expected value of parameters for constructor 'java.io.BufferedReader.BufferedReader' may cause compilation errors. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1092_3"'
//UPGRADE_WARNING: At least one expression was used more than once in the target code. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1181_3"'
//UPGRADE_TODO: Constructor 'java.io.FileReader.FileReader' was converted to 'System.IO.StreamReader' which has a different behavior. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1073_3"'
/*Original System.IO.StreamReader fp = new System.IO.StreamReader(new System.IO.StreamReader(model_file_name, System.Text.Encoding.Default).BaseStream, new System.IO.StreamReader(model_file_name, System.Text.Encoding.Default).CurrentEncoding);*/
System.IO.StreamReader fp = new System.IO.StreamReader(new System.IO.FileStream(model_file_name, System.IO.FileMode.Open));
// read parameters
svm_model model = new svm_model();
svm_parameter param = new svm_parameter();
model.param = param;
model.rho = null;
model.probA = null;
model.probB = null;
model.label = null;
model.nSV = null;
while (true)
{
System.String cmd = fp.ReadLine();
System.String arg = cmd.Substring(cmd.IndexOf((System.Char) ' ') + 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.Console.Error.Write("unknown svm type.\n");
return null;
}
}
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.Console.Error.Write("unknown kernel function.\n");
return null;
}
}
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];
SupportClass.Tokenizer st = new SupportClass.Tokenizer(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];
SupportClass.Tokenizer st = new SupportClass.Tokenizer(arg);
for (int i = 0; i < n; i++)
model.label[i] = atoi(st.NextToken());
}
else if (cmd.StartsWith("probA"))
{
int n = model.nr_class * (model.nr_class - 1) / 2;
model.probA = new double[n];
SupportClass.Tokenizer st = new SupportClass.Tokenizer(arg);
for (int i = 0; i < n; i++)
model.probA[i] = atof(st.NextToken());
}
else if (cmd.StartsWith("probB"))
{
int n = model.nr_class * (model.nr_class - 1) / 2;
model.probB = new double[n];
SupportClass.Tokenizer st = new SupportClass.Tokenizer(arg);
for (int i = 0; i < n; i++)
model.probB[i] = atof(st.NextToken());
}
else if (cmd.StartsWith("nr_sv"))
{
int n = model.nr_class;
model.nSV = new int[n];
SupportClass.Tokenizer st = new SupportClass.Tokenizer(arg);
for (int i = 0; i < n; i++)
model.nSV[i] = atoi(st.NextToken());
}
else if (cmd.StartsWith("SV"))
{
break;
}
else
{
System.Console.Error.Write("unknown text in model file\n");
return null;
}
}
// read sv_coef and SV
int m = model.nr_class - 1;
int l = model.l;
model.sv_coef = new double[m][];
for (int i = 0; i < m; i++)
{
model.sv_coef[i] = new double[l];
}
model.SV = new svm_node[l][];
for (int i = 0; i < l; i++)
{
System.String line = fp.ReadLine();
SupportClass.Tokenizer st = new SupportClass.Tokenizer(line, " \t\n\r\f:");
for (int k = 0; k < m; k++)
model.sv_coef[k][i] = atof(st.NextToken());
int n = st.Count / 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;
}
public void TrainModel(double[] labels, double[][] mlArray)
{
SvmProblemBuilder builder = new SvmProblemBuilder(labels, mlArray);
svm_problem problem = builder.CreateProblem();
svm_parameter param = new svm_parameter()
{
svm_type = 0,
kernel_type = 0,
cache_size = 512,
eps = 0.1,
C = 10,
nr_weight = 0,
weight_label = null,
weight = null
};
this.model = svm.svm_train(problem, param);
}
public static double svm_predict_probability(svm_model model, svm_node[] x, double[] prob_estimates)
{
if ((model.param.svm_type == svm_parameter.C_SVC || model.param.svm_type == svm_parameter.NU_SVC) && model.probA != null && model.probB != null)
{
int i;
int nr_class = model.nr_class;
double[] dec_values = new double[nr_class * (nr_class - 1) / 2];
svm_predict_values(model, x, dec_values);
double min_prob = 1e-7;
double[][] tmpArray = new double[nr_class][];
for (int i2 = 0; i2 < nr_class; i2++)
{
tmpArray[i2] = new double[nr_class];
}
double[][] pairwise_prob = tmpArray;
int k = 0;
for (i = 0; i < nr_class; i++)
for (int j = i + 1; j < nr_class; j++)
{
pairwise_prob[i][j] = System.Math.Min(System.Math.Max(sigmoid_predict(dec_values[k], model.probA[k], model.probB[k]), min_prob), 1 - min_prob);
pairwise_prob[j][i] = 1 - pairwise_prob[i][j];
k++;
}
multiclass_probability(nr_class, pairwise_prob, prob_estimates);
int prob_max_idx = 0;
for (i = 1; i < nr_class; i++)
if (prob_estimates[i] > prob_estimates[prob_max_idx])
prob_max_idx = i;
return model.label[prob_max_idx];
}
else
return svm_predict(model, x);
}
private static void predict(System.IO.StreamReader input, System.IO.BinaryWriter output, svm_model model, int predict_probability)
{
int correct = 0;
int total = 0;
double error = 0;
double sumv = 0, sumy = 0, sumvv = 0, sumyy = 0, sumvy = 0;
int svm_type = svm.svm_get_svm_type(model);
int nr_class = svm.svm_get_nr_class(model);
int[] labels = new int[nr_class];
double[] prob_estimates = null;
if (predict_probability == 1)
{
if (svm_type == svm_parameter.EPSILON_SVR || svm_type == svm_parameter.NU_SVR)
{
System.Console.Out.Write("Prob. model for test data: target value = predicted value + z,\nz: Laplace distribution e^(-|z|/sigma)/(2sigma),sigma=" + svm.svm_get_svr_probability(model) + "\n");
}
else
{
svm.svm_get_labels(model, labels);
prob_estimates = new double[nr_class];
//UPGRADE_ISSUE: Method 'java.io.DataOutputStream.Write' was not converted. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1000_javaioDataOutputStreamWrite_javalangString"'
output.Write("labels");
for (int j = 0; j < nr_class; j++)
{
//UPGRADE_ISSUE: Method 'java.io.DataOutputStream.Write' was not converted. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1000_javaioDataOutputStreamWrite_javalangString"'
output.Write(" " + labels[j]);
}
//UPGRADE_ISSUE: Method 'java.io.DataOutputStream.Write' was not converted. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1000_javaioDataOutputStreamWrite_javalangString"'
output.Write("\n");
}
}
while (true)
{
System.String line = input.ReadLine();
if ((System.Object) line == null)
break;
SupportClass.Tokenizer st = new SupportClass.Tokenizer(line, " \t\n\r\f:");
double target = atof(st.NextToken());
int m = st.Count / 2;
svm_node[] x = new svm_node[m];
for (int j = 0; j < m; j++)
{
x[j] = new svm_node();
x[j].index = atoi(st.NextToken());
x[j].value_Renamed = atof(st.NextToken());
}
double v;
if (predict_probability == 1 && (svm_type == svm_parameter.C_SVC || svm_type == svm_parameter.NU_SVC))
{
v = svm.svm_predict_probability(model, x, prob_estimates);
//UPGRADE_ISSUE: Method 'java.io.DataOutputStream.Write' was not converted. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1000_javaioDataOutputStreamWrite_javalangString"'
output.Write(v + " ");
for (int j = 0; j < nr_class; j++)
{
//UPGRADE_ISSUE: Method 'java.io.DataOutputStream.Write' was not converted. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1000_javaioDataOutputStreamWrite_javalangString"'
output.Write(prob_estimates[j] + " ");
}
//UPGRADE_ISSUE: Method 'java.io.DataOutputStream.Write' was not converted. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1000_javaioDataOutputStreamWrite_javalangString"'
output.Write("\n");
}
else
{
v = svm.svm_predict(model, x);
//UPGRADE_ISSUE: Method 'java.io.DataOutputStream.Write' was not converted. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1000_javaioDataOutputStreamWrite_javalangString"'
output.Write(v + "\n");
}
if (v == target)
++correct;
error += (v - target) * (v - target);
sumv += v;
sumy += target;
sumvv += v * v;
sumyy += target * target;
sumvy += v * target;
++total;
}
System.Console.Out.Write("Accuracy = " + (double) correct / total * 100 + "% (" + correct + "/" + total + ") (classification)\n");
System.Console.Out.Write("Mean squared error = " + error / total + " (regression)\n");
System.Console.Out.Write("Squared correlation coefficient = " + ((total * sumvy - sumv * sumy) * (total * sumvy - sumv * sumy)) / ((total * sumvv - sumv * sumv) * (total * sumyy - sumy * sumy)) + " (regression)\n");
}
public static void svm_save_model(System.String model_file_name, svm_model model)
{
//UPGRADE_TODO: Class 'java.io.DataOutputStream' was converted to 'System.IO.BinaryWriter' which has a different behavior. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1073_javaioDataOutputStream_3"'
//UPGRADE_TODO: Constructor 'java.io.FileOutputStream.FileOutputStream' was converted to 'System.IO.FileStream.FileStream' which has a different behavior. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1073_javaioFileOutputStreamFileOutputStream_javalangString_3"'
/* Original System.IO.BinaryWriter fp = new System.IO.BinaryWriter(new System.IO.FileStream(model_file_name, System.IO.FileMode.Create));*/
System.IO.StreamWriter fp = new System.IO.StreamWriter(new System.IO.FileStream(model_file_name, System.IO.FileMode.Create));
svm_parameter param = model.param;
fp.Write("svm_type " + svm_type_table[param.svm_type] + "\n");
fp.Write("kernel_type " + kernel_type_table[param.kernel_type] + "\n");
if (param.kernel_type == svm_parameter.POLY)
fp.Write("degree " + param.degree + "\n");
if (param.kernel_type == svm_parameter.POLY || param.kernel_type == svm_parameter.RBF || param.kernel_type == svm_parameter.SIGMOID)
fp.Write("gamma " + param.gamma + "\n");
if (param.kernel_type == svm_parameter.POLY || param.kernel_type == svm_parameter.SIGMOID)
fp.Write("coef0 " + param.coef0 + "\n");
int nr_class = model.nr_class;
int l = model.l;
fp.Write("nr_class " + nr_class + "\n");
fp.Write("total_sv " + l + "\n");
{
fp.Write("rho");
for (int i = 0; i < nr_class * (nr_class - 1) / 2; i++)
fp.Write(" " + model.rho[i]);
fp.Write("\n");
}
if (model.label != null)
{
fp.Write("label");
for (int i = 0; i < nr_class; i++)
fp.Write(" " + model.label[i]);
fp.Write("\n");
}
if (model.probA != null)
// regression has probA only
{
fp.Write("probA");
for (int i = 0; i < nr_class * (nr_class - 1) / 2; i++)
fp.Write(" " + model.probA[i]);
fp.Write("\n");
}
if (model.probB != null)
{
fp.Write("probB");
for (int i = 0; i < nr_class * (nr_class - 1) / 2; i++)
fp.Write(" " + model.probB[i]);
fp.Write("\n");
}
if (model.nSV != null)
{
fp.Write("nr_sv");
for (int i = 0; i < nr_class; i++)
fp.Write(" " + model.nSV[i]);
fp.Write("\n");
}
fp.Write("SV\n");
double[][] sv_coef = model.sv_coef;
svm_node[][] SV = model.SV;
for (int i = 0; i < l; i++)
{
for (int j = 0; j < nr_class - 1; j++)
fp.Write(sv_coef[j][i] + " ");
svm_node[] p = SV[i];
for (int j = 0; j < p.Length; j++)
fp.Write(p[j].index + ":" + p[j].value + " ");
fp.Write("\n");
}
fp.Close();
}
public static int svm_check_probability_model(svm_model model)
{
if (((model.param.svm_type == svm_parameter.C_SVC || model.param.svm_type == svm_parameter.NU_SVC) && model.probA != null && model.probB != null) || ((model.param.svm_type == svm_parameter.EPSILON_SVR || model.param.svm_type == svm_parameter.NU_SVR) && model.probA != null))
return 1;
else
return 0;
}
private static ArrayList[] predict(System.IO.StreamReader input, System.IO.StreamWriter output, svm_model model, int predict_probability)
{
//int correct = 0;
//int total = 0;
//double error = 0;
//double sumv = 0, sumy = 0, sumvv = 0, sumyy = 0, sumvy = 0;
ArrayList[] arrResult = new ArrayList[2];//Mảng thứ 1 chứa kết quả thực sự, mảng thứ 2 chứa kết quả dự đoán
arrResult[0] = new ArrayList();
arrResult[1] = new ArrayList();
int svm_type = svm.svm_get_svm_type(model);
int nr_class = svm.svm_get_nr_class(model);
int[] labels = new int[nr_class];
double[] prob_estimates = null;
if (predict_probability == 1)
{
if (svm_type == svm_parameter.EPSILON_SVR || svm_type == svm_parameter.NU_SVR)
{
System.Console.Out.Write("Prob. model for test data: target value = predicted value + z,\nz: Laplace distribution e^(-|z|/sigma)/(2sigma),sigma=" + svm.svm_get_svr_probability(model) + "\n");
}
else
{
svm.svm_get_labels(model, labels);
prob_estimates = new double[nr_class];
//UPGRADE_ISSUE: Method 'java.io.DataOutputStream.Write' was not converted. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1000_javaioDataOutputStreamWrite_javalangString"'
output.Write("labels");
for (int j = 0; j < nr_class; j++)
{
//UPGRADE_ISSUE: Method 'java.io.DataOutputStream.Write' was not converted. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1000_javaioDataOutputStreamWrite_javalangString"'
output.Write(" " + labels[j]);
}
//UPGRADE_ISSUE: Method 'java.io.DataOutputStream.Write' was not converted. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1000_javaioDataOutputStreamWrite_javalangString"'
output.Write("\n");
}
}
#region [Thêm] Lấy thông tin tiền xử lý từ dòng đầu của file test
System.String strPreprocess = input.ReadLine();
#endregion
while (true)
{
System.String line = input.ReadLine();
if ((System.Object)line == null)
break;
SupportClass.Tokenizer st = new SupportClass.Tokenizer(line, " \t\n\r\f:");
double target = atof(st.NextToken());
int m = st.Count / 2;
svm_node[] x = new svm_node[m];
for (int j = 0; j < m; j++)
{
x[j] = new svm_node();
x[j].index = atoi(st.NextToken());
x[j].value_Renamed = atof(st.NextToken());
}
double v;
if (predict_probability == 1 && (svm_type == svm_parameter.C_SVC || svm_type == svm_parameter.NU_SVC))
{
v = svm.svm_predict_probability(model, x, prob_estimates);
//UPGRADE_ISSUE: Method 'java.io.DataOutputStream.Write' was not converted. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1000_javaioDataOutputStreamWrite_javalangString"'
output.Write(v + " ");
for (int j = 0; j < nr_class; j++)
{
//UPGRADE_ISSUE: Method 'java.io.DataOutputStream.Write' was not converted. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1000_javaioDataOutputStreamWrite_javalangString"'
output.Write(prob_estimates[j] + " ");
}
//UPGRADE_ISSUE: Method 'java.io.DataOutputStream.Write' was not converted. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1000_javaioDataOutputStreamWrite_javalangString"'
output.Write("\n");
}
else
{
v = svm.svm_predict(model, x);
#region [Thêm] Chuyển về dữ liệu nguyên thủy dựa vào cách tiền xử lý
string[] strItems = strPreprocess.Split(' ');
double dblMin;
double dblMax;
double dblDiff;
switch (strItems[0])
{
case "ScaleByMinMax":
dblMin = Convert.ToDouble(strItems[1]);
dblMax = Convert.ToDouble(strItems[2]);
dblDiff = dblMax - dblMin;
v = v * dblDiff + dblMin;
target = target * dblDiff + dblMin;
break;
default:
break;
}
#endregion
arrResult[0].Add(target);
arrResult[1].Add(v);
//UPGRADE_ISSUE: Method 'java.io.DataOutputStream.Write' was not converted. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1000_javaioDataOutputStreamWrite_javalangString"'
output.Write(target + " " + v + "\n");
}
//#region [Thêm] Chuyển về dữ liệu nguyên thủy dựa vào cách tiền xử lý
//string[] strItems = strPreprocess.Split(' ');
//switch (strItems[0])
//{
// case "Scale(0,1)":
// double dblMin = Convert.ToDouble(strItems[1]);
// double dblMax = Convert.ToDouble(strItems[2]);
// double dblDiff = dblMax - dblMin;
// v = (v - 0.15) * dblDiff / 0.7 + dblMin;
// target = (target - 0.15) * dblDiff / 0.7 + dblMin;
// break;
// default:
// break;
//}
//#endregion
//arrResult[0].Add(target);
//arrResult[1].Add(v);
//if (v == target)
// ++correct;
//error += (v - target) * (v - target);
//sumv += v;
//sumy += target;
//sumvv += v * v;
//sumyy += target * target;
//sumvy += v * target;
//++total;
}
return arrResult;
//System.Console.Out.Write("Accuracy = " + (double) correct / total * 100 + "% (" + correct + "/" + total + ") (classification)\n");
//System.Console.Out.Write("Mean squared error = " + error / total + " (regression)\n");
//System.Console.Out.Write("Squared correlation coefficient = " + ((total * sumvy - sumv * sumy) * (total * sumvy - sumv * sumy)) / ((total * sumvv - sumv * sumv) * (total * sumyy - sumy * sumy)) + " (regression)\n");
}
/// <summary>
/// Train the SVM and save the model
/// </summary>
public void Train()
{
this.model = svm.svm_train(prob, param);
}