public static svm_model svm_load_model(StreamReader reader) {
var savedCulture = Thread.CurrentThread.CurrentCulture;
Thread.CurrentThread.CurrentCulture = CultureInfo.InvariantCulture;
// 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) {
String cmd = reader.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], StringComparison.InvariantCultureIgnoreCase) != -1) {
param.svm_type = i;
break;
}
}
if (i == svm_type_table.Length) {
Console.Error.WriteLine("unknown svm type.");
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], StringComparison.InvariantCultureIgnoreCase) != -1) {
param.kernel_type = i;
break;
}
}
if (i == kernel_type_table.Length) {
Console.Error.WriteLine("unknown kernel function.");
return null;
}
} else if (cmd.StartsWith("degree"))
param.degree = atoi(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];
var st = arg.Split(' ', '\t', '\n', '\r', '\f');
for (int i = 0; i < n; i++)
model.rho[i] = atof(st[i]);
} else if (cmd.StartsWith("label")) {
int n = model.nr_class;
model.label = new int[n];
var st = arg.Split(' ', '\t', '\n', '\r', '\f');
for (int i = 0; i < n; i++)
model.label[i] = atoi(st[i]);
} else if (cmd.StartsWith("probA")) {
int n = model.nr_class * (model.nr_class - 1) / 2;
model.probA = new double[n];
var st = arg.Split(' ', '\t', '\n', '\r', '\f');
for (int i = 0; i < n; i++)
model.probA[i] = atof(st[i]);
} else if (cmd.StartsWith("probB")) {
int n = model.nr_class * (model.nr_class - 1) / 2;
model.probB = new double[n];
var st = arg.Split(' ', '\t', '\n', '\r', '\f');
for (int i = 0; i < n; i++)
model.probB[i] = atof(st[i]);
} else if (cmd.StartsWith("nr_sv")) {
int n = model.nr_class;
model.nSV = new int[n];
var st = arg.Split(' ', '\t', '\n', '\r', '\f');
for (int i = 0; i < n; i++)
model.nSV[i] = atoi(st[i]);
} else if (cmd.StartsWith("SV")) {
break;
} else {
Console.Error.WriteLine("unknown text in model file: [" + cmd + "]");
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 k = 0; k < m; k++)
model.sv_coef[k] = new double[l];
model.SV = new svm_node[l][];
for (int i = 0; i < l; i++) {
String line = reader.ReadLine();
var st = line.Split(' ', '\t', '\n', '\r', '\f', ':');
for (int k = 0; k < m; k++) {
model.sv_coef[k][i] = atof(st[k]);
}
// skip y value
st = st.Skip(1).ToArray();
int n = st.Length / 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[2 * j]);
model.SV[i][j].value = atof(st[2 * j + 1]);
}
}
Thread.CurrentThread.CurrentCulture = savedCulture;
return model;
}
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;
}
public static void svm_save_model(string model_file_name, svm_model model) {
//DataOutputStream fp = new DataOutputStream(new BufferedOutputStream(new FileOutputStream(model_file_name)));
var writer = new StreamWriter(model_file_name);
svm_save_model(writer, model);
}
public static void svm_save_model(StreamWriter writer, svm_model model) {
var savedCulture = Thread.CurrentThread.CurrentCulture;
Thread.CurrentThread.CurrentCulture = CultureInfo.InvariantCulture;
svm_parameter param = model.param;
writer.Write("svm_type " + svm_type_table[param.svm_type] + Environment.NewLine);
writer.Write("kernel_type " + kernel_type_table[param.kernel_type] + Environment.NewLine);
if (param.kernel_type == svm_parameter.POLY)
writer.Write("degree " + param.degree + Environment.NewLine);
if (param.kernel_type == svm_parameter.POLY ||
param.kernel_type == svm_parameter.RBF ||
param.kernel_type == svm_parameter.SIGMOID)
writer.Write("gamma " + param.gamma.ToString("r") + Environment.NewLine);
if (param.kernel_type == svm_parameter.POLY ||
param.kernel_type == svm_parameter.SIGMOID)
writer.Write("coef0 " + param.coef0.ToString("r") + Environment.NewLine);
int nr_class = model.nr_class;
int l = model.l;
writer.Write("nr_class " + nr_class + Environment.NewLine);
writer.Write("total_sv " + l + Environment.NewLine);
{
writer.Write("rho");
for (int i = 0; i < nr_class * (nr_class - 1) / 2; i++)
writer.Write(" " + model.rho[i].ToString("r"));
writer.Write(Environment.NewLine);
}
if (model.label != null) {
writer.Write("label");
for (int i = 0; i < nr_class; i++)
writer.Write(" " + model.label[i]);
writer.Write(Environment.NewLine);
}
if (model.probA != null) // regression has probA only
{
writer.Write("probA");
for (int i = 0; i < nr_class * (nr_class - 1) / 2; i++)
writer.Write(" " + model.probA[i].ToString("r"));
writer.Write(Environment.NewLine);
}
if (model.probB != null) {
writer.Write("probB");
for (int i = 0; i < nr_class * (nr_class - 1) / 2; i++)
writer.Write(" " + model.probB[i].ToString("r"));
writer.Write(Environment.NewLine);
}
if (model.nSV != null) {
writer.Write("nr_sv");
for (int i = 0; i < nr_class; i++)
writer.Write(" " + model.nSV[i]);
writer.Write(Environment.NewLine);
}
writer.WriteLine("SV");
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++)
writer.Write(sv_coef[j][i].ToString("r") + " ");
svm_node[] p = SV[i];
if (param.kernel_type == svm_parameter.PRECOMPUTED)
writer.Write("0:" + (int)(p[0].value));
else
for (int j = 0; j < p.Length; j++)
writer.Write(p[j].index + ":" + p[j].value.ToString("r") + " ");
writer.Write(Environment.NewLine);
}
writer.Flush();
Thread.CurrentThread.CurrentCulture = savedCulture;
}
public static double svm_predict(svm_model model, svm_node[] x) {
int nr_class = model.nr_class;
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)
dec_values = new double[1];
else
dec_values = new double[nr_class * (nr_class - 1) / 2];
double pred_result = svm_predict_values(model, x, dec_values);
return pred_result;
}
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[][] pairwise_prob = new double[nr_class][];
int k = 0;
for (i = 0; i < nr_class; i++)
pairwise_prob[i] = new double[nr_class];
for (int j = i + 1; j < nr_class; j++) {
pairwise_prob[i][j] =
Math.Min(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);
}
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 {
Console.Error.WriteLine("Model doesn't contain information for SVR probability inference");
return 0;
}
}
public static double svm_predict_values(svm_model model, svm_node[] x, double[] dec_values) {
int i;
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 (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;
if (model.param.svm_type == svm_parameter.ONE_CLASS)
return (sum > 0) ? 1 : -1;
else
return sum;
} else {
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[] vote = new int[nr_class];
for (i = 0; i < nr_class; i++)
vote[i] = 0;
int p = 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[p] = sum;
if (dec_values[p] > 0)
++vote[i];
else
++vote[j];
p++;
}
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 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];
}
public static int svm_get_svm_type(svm_model model) {
return model.param.svm_type;
}
//
// Interface functions
//
public static svm_model svm_train(svm_problem prob, svm_parameter param) {
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 (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 (Math.Abs(f.alpha[i]) > 0) {
model.SV[j] = prob.x[i];
model.sv_coef[0][j] = f.alpha[i];
++j;
}
} else {
// classification
int l = prob.l;
int[] tmp_nr_class = new int[1];
int[][] tmp_label = new int[1][];
int[][] tmp_start = new int[1][];
int[][] tmp_count = new int[1][];
int[] perm = new int[l];
// group training data of the same class
svm_group_classes(prob, tmp_nr_class, tmp_label, tmp_start, tmp_count, perm);
int nr_class = tmp_nr_class[0];
int[] label = tmp_label[0];
int[] start = tmp_start[0];
int[] count = tmp_count[0];
if (nr_class == 1)
svm.info("WARNING: training data in only one class. See README for details." + Environment.NewLine);
svm_node[][] x = new svm_node[l][];
int i;
for (i = 0; i < l; i++)
x[i] = prob.x[perm[i]];
// 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)
Console.Error.WriteLine("WARNING: class label " + param.weight_label[i] +
" specified in weight is not found");
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] && Math.Abs(f[p].alpha[k]) > 0)
nonzero[si + k] = true;
for (k = 0; k < cj; k++)
if (!nonzero[sj + k] && 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;
}
svm.info("Total nSV = " + nnz + Environment.NewLine);
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;
}
private SupportVectorMachineModel(SupportVectorMachineModel original, Cloner cloner)
: base(original, cloner) {
// only using a shallow copy here! (gkronber)
this.model = original.model;
this.rangeTransform = original.rangeTransform;
this.allowedInputVariables = (string[])original.allowedInputVariables.Clone();
if (original.classValues != null)
this.classValues = (double[])original.classValues.Clone();
}
public SupportVectorMachineModel(svm_model model, RangeTransform rangeTransform, string targetVariable, IEnumerable<string> allowedInputVariables)
: base(targetVariable) {
this.name = ItemName;
this.description = ItemDescription;
this.model = model;
this.rangeTransform = rangeTransform;
this.allowedInputVariables = allowedInputVariables.ToArray();
}
public SupportVectorMachineModel(svm_model model, RangeTransform rangeTransform, string targetVariable, IEnumerable<string> allowedInputVariables, IEnumerable<double> classValues)
: this(model, rangeTransform, targetVariable, allowedInputVariables) {
this.classValues = classValues.ToArray();
}