public void TrainAndTest(IEnumerable <ItemRating> trainSet, IEnumerable <ItemRating> testSet)
{
var problem = new SvmProblem()
{
X = trainSet.Select(ir => FeatureBuilder.GetSvmNode(ir)).ToArray(),
Y = trainSet.Select(ir => LabelSelector(ir)).ToArray()
};
Parameters.Check(problem);
Console.WriteLine("Writing training samples...");
WriteSvmFile(problem, "train.libsvm");
Console.WriteLine("LibSvm training...");
LibSvm.SvmModel model = Svm.Train(problem, Parameters);
var predictedClasses = new List <float>();
Console.WriteLine("LibSvm testing...");
foreach (var ir in testSet)
{
ir.PredictedRating = (float)model.Predict(FeatureBuilder.GetSvmNode(ir));
predictedClasses.Add(ir.PredictedRating);
}
Console.WriteLine("Writing output...");
File.WriteAllLines("output.libsvm", predictedClasses.Select(i => i.ToString()));
}
//
// Interface functions
//
public static SvmModel Train(SvmProblem prob, SvmParameter param)
{
var model = new SvmModel();
model.Param = param;
if (param.SvmType.IsSVROrOneClass())
{
// regression or one-class-svm
model.NrClass = 2;
model.Label = null;
model.SupportVectorsNumbers = null;
model.ProbA = null; model.ProbB = null;
model.SupportVectorsCoefficients = new double[1][];
if (param.Probability && param.SvmType.IsSVR())
{
model.ProbA = new double[1];
model.ProbA[0] = svm_svr_probability(prob, param);
}
DecisionFunction 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.Lenght; i++)
{
if (Math.Abs(f.Alpha[i]) > 0)
{
++nSV;
}
}
model.TotalSupportVectorsNumber = nSV;
model.SupportVectors = new SvmNode[nSV][];
model.SupportVectorsCoefficients[0] = new double[nSV];
int j = 0;
for (i = 0; i < prob.Lenght; i++)
{
if (Math.Abs(f.Alpha[i]) > 0)
{
model.SupportVectors[j] = prob.X[i];
model.SupportVectorsCoefficients[0][j] = f.Alpha[i];
++j;
}
}
}
else
{
// classification
int l = prob.Lenght;
int[] perm = new int[l];
int nr_class;
int[] label;
int[] start;
int[] count;
// group training data of the same class
svm_group_classes(prob, out nr_class, out label, out start, out count, perm);
if (nr_class == 1)
{
Svm.info("WARNING: training data in only one class. See README for details.\n");
}
SvmNode[][] x = new SvmNode[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.WeightsCount; i++)
{
int j;
for (j = 0; j < nr_class; j++)
{
if (param.WeightLabel[i] == label[j])
{
break;
}
}
if (j == nr_class)
{
System.Diagnostics.Debug.WriteLine("WARNING: class label " + param.WeightLabel[i] + " specified in weight is not found\n");
}
else
{
weighted_C[j] *= param.Weight[i];
}
}
// train k*(k-1)/2 models
var nonzero = new bool[l];
for (i = 0; i < l; i++)
{
nonzero[i] = false;
}
var f = new DecisionFunction[nr_class * (nr_class - 1) / 2];
double[] probA = null, probB = null;
if (param.Probability)
{
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++)
{
int si = start[i], sj = start[j];
int ci = count[i], cj = count[j];
var subprobLenght = ci + cj;
var sub_prob = new SvmProblem
{
X = new SvmNode[subprobLenght][],
Y = new double[subprobLenght]
};
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)
{
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.NrClass = 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)
{
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.SupportVectorsNumbers = 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.SupportVectorsNumbers[i] = nSV;
nz_count[i] = nSV;
}
Svm.info("Total nSV = " + nnz + "\n");
model.TotalSupportVectorsNumber = nnz;
model.SupportVectors = new SvmNode[nnz][];
p = 0;
for (i = 0; i < l; i++)
{
if (nonzero[i])
{
model.SupportVectors[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.SupportVectorsCoefficients = new double[nr_class - 1][];
for (i = 0; i < nr_class - 1; i++)
{
model.SupportVectorsCoefficients[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.SupportVectorsCoefficients[j - 1][q++] = f[p].Alpha[k];
}
}
q = nz_start[j];
for (k = 0; k < cj; k++)
{
if (nonzero[sj + k])
{
model.SupportVectorsCoefficients[i][q++] = f[p].Alpha[ci + k];
}
}
++p;
}
}
}
return(model);
}
public static SvmModel LoadModel(IEnumerable <string> lines)
{
// read parameters
var model = new SvmModel();
var param = new SvmParameter();
model.Param = param;
model.Rho = null;
model.ProbA = null;
model.ProbB = null;
model.Label = null;
model.SupportVectors = null;
var done = false;
int m = 0;
int l = 0;
int currentVector = 0;
foreach (var cmd in lines)
{
var splitted = cmd.Split((char[])null, StringSplitOptions.RemoveEmptyEntries);
if (!done)
{
switch (splitted[0])
{
case "svm_type":
param.SvmType = (SvmType)Enum.Parse(typeof(SvmType), splitted[1], ignoreCase: true);
break;
case "kernel_type":
param.KernelType = (KernelType)Enum.Parse(typeof(KernelType), splitted[1], ignoreCase: true);
break;
case "degree":
param.Degree = atoi(splitted[1]);
break;
case "gamma":
param.Gamma = atof(splitted[1]);
break;
case "coef0":
param.Coef0 = atof(splitted[1]);
break;
case "nr_class":
model.NrClass = atoi(splitted[1]);
break;
case "total_sv":
model.TotalSupportVectorsNumber = atoi(splitted[1]);
break;
case "rho":
int n = model.NrClass * (model.NrClass - 1) / 2;
model.Rho = new double[n];
for (int i = 0; i < n; i++)
{
if (i + 1 < splitted.Length)
{
model.Rho[i] = atof(splitted[i + 1]);
}
}
break;
case "label":
int n2 = model.NrClass;
model.Label = new int[n2];
for (int i = 0; i < n2; i++)
{
if (i + 1 < splitted.Length)
{
model.Label[i] = atoi(splitted[i + 1]);
}
}
break;
case "probA":
int n3 = model.NrClass * (model.NrClass - 1) / 2;
model.ProbA = new double[n3];
for (int i = 0; i < n3; i++)
{
if (i + 1 < splitted.Length)
{
model.ProbA[i] = atof(splitted[i + 1]);
}
}
break;
case "probB":
int n4 = model.NrClass * (model.NrClass - 1) / 2;
model.ProbB = new double[n4];
for (int i = 0; i < n4; i++)
{
if (i + 1 < splitted.Length)
{
model.ProbB[i] = atof(splitted[i + 1]);
}
}
break;
case "nr_sv":
int n5 = model.NrClass;
model.SupportVectorsNumbers = new int[n5];
for (int i = 0; i < n5; i++)
{
if (i + 1 < splitted.Length)
{
model.SupportVectorsNumbers[i] = atoi(splitted[i + 1]);
}
}
break;
case "SV":
done = true;
m = model.NrClass - 1;
l = model.TotalSupportVectorsNumber;
model.SupportVectorsCoefficients = new double[m][];
for (int i = 0; i < m; i++)
{
model.SupportVectorsCoefficients[i] = new double[l];
}
model.SupportVectors = new SvmNode[l][];
break;
default:
System.Diagnostics.Debug.WriteLine("unknown text in model file: [" + cmd + "]");
return(null);
}
}
else if (currentVector < l)
{
// read sv_coef and SV
for (int k = 0; k < m; k++)
{
model.SupportVectorsCoefficients[k][currentVector] = atof(splitted[k]);
}
int n = splitted.Length - m;
model.SupportVectors[currentVector] = new SvmNode[n];
for (int j = 0; j < n; j++)
{
var pair = splitted[m + j].Split(new char[] { ':' }, 2);
model.SupportVectors[currentVector][j] = new SvmNode(atoi(pair[0]), atof(pair[1]));
}
currentVector++;
}
}
return(model);
}
internal SaveModelEnumerator(SvmModel model)
{
this.model = model;
}
public static IEnumerable <string> SaveModel(SvmModel model)
{
return(new SaveModelEnumerator(model));
}
