public static double k_function(SvmNode[] x, SvmNode[] y, SvmParameter param)
{
switch (param.KernelType)
{
case KernelType.Linear:
return dot(x, y);
case KernelType.Poly:
return powi(param.Gamma*dot(x, y) + param.Coef0, param.Degree);
case KernelType.Rbf:
double sum = 0;
int xlen = x.Length;
int ylen = y.Length;
int i = 0;
int j = 0;
while (i < xlen && j < ylen)
{
if (x[i].Index == y[j].Index)
{
double d = x[i++].Value - y[j++].Value;
sum += d * d;
}
else
{
if (x[i].Index > y[j].Index)
{
sum += y[j].Value*y[j].Value;
++j;
}
else
{
sum += x[i].Value*x[i].Value;
++i;
}
}
}
while (i < xlen)
{
sum += x[i].Value*x[i].Value;
++i;
}
while (j < ylen)
{
sum += y[j].Value*y[j].Value;
++j;
}
return Math.Exp(-param.Gamma*sum);
case KernelType.Sigmoid:
return Math.Tanh(param.Gamma*dot(x, y) + param.Coef0);
case KernelType.Precomputed:
return x[(int) (y[0].Value)].Value;
default:
throw new ApplicationException("Bad kernel_type");
}
}
public static SvmNode[] ToSvmNodes(this double[] vector)
{
var result = new SvmNode[vector.Length];
for (int i = 0; i < vector.Length; i++)
{
result[i] = new SvmNode(i, vector[i]);
}
return result;
}
protected Kernel(int l, SvmNode[][] x_, SvmParameter param)
{
this.kernel_type = param.KernelType;
this.degree = param.Degree;
this.gamma = param.Gamma;
this.coef0 = param.Coef0;
x = (SvmNode[][])x_.Clone();
if (kernel_type == KernelType.Rbf)
{
x_square = new double[l];
for (int i = 0; i < l; i++)
x_square[i] = dot(x[i], x[i]);
}
else x_square = null;
}
public override LibSvm.SvmNode[] GetSvmNode(ItemRating rating)
{
int followersCount = _container.Tweets[rating].FollowersCount;
double followersFeature = followersCount > 1000 ? 1.0 : (double)followersCount / 1000;
int friendsCount = _container.Tweets[rating].FriendsCount;
double friendsFeature = friendsCount > 1000 ? 1.0 : (double)friendsCount / 1000;
var svmNode = new SvmNode[6] {
//new SvmNode(Mapper.ToInternalID("RetweetCount"), _container.Tweets[rating].RetweetCount),
new SvmNode(Mapper.ToInternalID("Rating"), rating.Rating),
new SvmNode(Mapper.ToInternalID("FollowersCount"), followersFeature),
new SvmNode(Mapper.ToInternalID("FriendsCount"), friendsFeature),
new SvmNode(Mapper.ToInternalID(rating.User.Id), 1),
new SvmNode(Mapper.ToInternalID(rating.Item.Id + rating.Domain.Id), 1),
new SvmNode(Mapper.ToInternalID(_container.Tweets[rating].MovieUrl), 1),
};
return svmNode;
}
//
// 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);
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)
Console.Error.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;
}
static double dot(SvmNode[] x, SvmNode[] y)
{
double sum = 0;
int xlen = x.Length;
int ylen = y.Length;
int i = 0;
int j = 0;
while (i < xlen && j < ylen)
{
if (x[i].Index == y[j].Index)
{
sum += x[i++].Value * y[j++].Value;
}
else
{
if (x[i].Index > y[j].Index)
{
++j;
}
else
{
++i;
}
}
}
return sum;
}
//
// 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);
}
