/// <summary>
/// Performs cross validation.
/// </summary>
/// <param name="problem">The training data</param>
/// <param name="parameters">The parameters to test</param>
/// <param name="nrfold">The number of cross validations to use</param>
/// <returns>The cross validation score</returns>
public static double PerformCrossValidation(Problem problem, Parameter parameters, int nrfold)
{
string error = Procedures.svm_check_parameter(problem, parameters);
if (error == null)
return doCrossValidation(problem, parameters, nrfold);
else throw new Exception(error);
}
/// <summary>
/// Scales a problem using the provided range. This will not affect the parameter.
/// </summary>
/// <param name="prob">The problem to scale</param>
/// <param name="range">The Range transform to use in scaling</param>
/// <returns>The Scaled problem</returns>
public static Problem Scale(this IRangeTransform range, Problem prob)
{
Problem scaledProblem = new Problem(prob.Count, new double[prob.Count], new Node[prob.Count][], prob.MaxIndex);
for (int i = 0; i < scaledProblem.Count; i++)
{
scaledProblem.X[i] = new Node[prob.X[i].Length];
for (int j = 0; j < scaledProblem.X[i].Length; j++)
scaledProblem.X[i][j] = new Node(prob.X[i][j].Index, range.Transform(prob.X[i][j].Value, prob.X[i][j].Index));
scaledProblem.Y[i] = prob.Y[i];
}
return scaledProblem;
}
/// <summary>
/// Determines the Gaussian transform for the provided problem.
/// </summary>
/// <param name="prob">The Problem to analyze</param>
/// <returns>The Gaussian transform for the problem</returns>
public static GaussianTransform Compute(Problem prob)
{
int[] counts = new int[prob.MaxIndex];
double[] means = new double[prob.MaxIndex];
foreach (Node[] sample in prob.X)
{
for (int i = 0; i < sample.Length; i++)
{
means[sample[i].Index - 1] += sample[i].Value;
counts[sample[i].Index - 1]++;
}
}
for (int i = 0; i < prob.MaxIndex; i++)
{
if (counts[i] == 0)
counts[i] = 2;
means[i] /= counts[i];
}
double[] stddevs = new double[prob.MaxIndex];
foreach (Node[] sample in prob.X)
{
for (int i = 0; i < sample.Length; i++)
{
double diff = sample[i].Value - means[sample[i].Index - 1];
stddevs[sample[i].Index - 1] += diff * diff;
}
}
for (int i = 0; i < prob.MaxIndex; i++)
{
if (stddevs[i] == 0)
continue;
stddevs[i] /= (counts[i] - 1);
stddevs[i] = Math.Sqrt(stddevs[i]);
}
return new GaussianTransform(means, stddevs);
}
private void DoSearch(
Problem problem,
Parameter parameters,
List<double> CValues,
List<double> GammaValues,
StreamWriter output,
int nrfold,
ref double C,
ref double Gamma,
ref double crossValidation)
{
for (int i = 0; i < CValues.Count; i++)
{
for (int j = 0; j < GammaValues.Count; j++)
{
if (!_Cs.Contains(CValues[i]) || !_Gammas.Contains(GammaValues[j]))
{
parameters.C = CValues[i];
parameters.Gamma = GammaValues[j];
double test = Training.PerformCrossValidation(problem, parameters, nrfold);
Console.Write("{0} {1} {2}", parameters.C, parameters.Gamma, test);
if (output != null)
output.WriteLine("{0} {1} {2}", parameters.C, parameters.Gamma, test);
if (test > crossValidation)
{
C = parameters.C;
Gamma = parameters.Gamma;
crossValidation = test;
Console.WriteLine(" New Maximum!");
}
else Console.WriteLine();
_Gammas.Add(GammaValues[j]);
}
_crossIterations++;
OnEndEpoch();
}
_Cs.Add(CValues[i]);
}
}
/// <summary>
/// Performs a Grid parameter selection, trying all possible combinations of the two lists and returning the
/// combination which performed best. Use this method if validation data isn't available, as it will
/// divide the training data and train on a portion of it and test on the rest.
/// </summary>
/// <param name="problem">The training data</param>
/// <param name="parameters">The parameters to use when optimizing</param>
/// <param name="CValues">The set of C values to use</param>
/// <param name="GammaValues">The set of Gamma values to use</param>
/// <param name="outputFile">Output file for the parameter results.</param>
/// <param name="nrfold">The number of times the data should be divided for validation</param>
/// <param name="C">The optimal C value will be placed in this variable</param>
/// <param name="Gamma">The optimal Gamma value will be placed in this variable</param>
public void Grid(
Problem problem,
Parameter parameters,
List<double> CValues,
List<double> GammaValues,
string outputFile,
int nrfold,
out double C,
out double Gamma)
{
C = 0;
Gamma = 0;
double crossValidation = double.MinValue;
StreamWriter output = null;
if (outputFile != null)
output = new StreamWriter(outputFile);
_Cs = new List<double>();
_Gammas = new List<double>();
_cycles = CValues.Count * GammaValues.Count + (int)Math.Pow(FINE_STEP_WIDTH * 2 + 1, 2);
_crossIterations = 0;
DoSearch(problem, parameters, CValues, GammaValues, output, nrfold, ref C, ref Gamma, ref crossValidation);
// Tính lại các giá trị cho search kỹ
double dblCurrentCPow = Math.Log(C, 2);
double dblCurrentGammaPow = Math.Log(Gamma, 2);
CValues = GetList(dblCurrentCPow - C_FINE_STEP * FINE_STEP_WIDTH, dblCurrentCPow + C_FINE_STEP * FINE_STEP_WIDTH, C_FINE_STEP);
GammaValues = GetList(dblCurrentGammaPow - G_FINE_STEP * FINE_STEP_WIDTH, dblCurrentGammaPow + G_FINE_STEP * FINE_STEP_WIDTH, G_FINE_STEP);
DoSearch(problem, parameters, CValues, GammaValues, output, nrfold, ref C, ref Gamma, ref crossValidation);
if (output != null)
output.Close();
}
/// <summary>
/// Performs a Grid parameter selection, trying all possible combinations of the two lists and returning the
/// combination which performed best. Use this method if there is no validation data available, and it will
/// divide it 5 times to allow 5-fold validation (training on 4/5 and validating on 1/5, 5 times).
/// </summary>
/// <param name="problem">The training data</param>
/// <param name="parameters">The parameters to use when optimizing</param>
/// <param name="CValues">The set of C values to use</param>
/// <param name="GammaValues">The set of Gamma values to use</param>
/// <param name="outputFile">Output file for the parameter results.</param>
/// <param name="C">The optimal C value will be put into this variable</param>
/// <param name="Gamma">The optimal Gamma value will be put into this variable</param>
public void Grid(
Problem problem,
Parameter parameters,
List<double> CValues,
List<double> GammaValues,
string outputFile,
out double C,
out double Gamma)
{
Grid(problem, parameters, CValues, GammaValues, outputFile, NFOLD, out C, out Gamma);
}
/// <summary>
/// Performs a Grid parameter selection, trying all possible combinations of the two lists and returning the
/// combination which performed best. The default ranges of C and Gamma values are used. Use this method if there is no validation data available, and it will
/// divide it 5 times to allow 5-fold validation (training on 4/5 and validating on 1/5, 5 times).
/// </summary>
/// <param name="problem">The training data</param>
/// <param name="parameters">The parameters to use when optimizing</param>
/// <param name="outputFile">Output file for the parameter results.</param>
/// <param name="C">The optimal C value will be put into this variable</param>
/// <param name="Gamma">The optimal Gamma value will be put into this variable</param>
public void Grid(
Problem problem,
Parameter parameters,
string outputFile,
out double C,
out double Gamma)
{
Grid(problem, parameters, GetList(MIN_C, MAX_C, C_STEP), GetList(MIN_G, MAX_G, G_STEP), outputFile, NFOLD, out C, out Gamma);
}
/// <summary>
/// Performs a Grid parameter selection, trying all possible combinations of the two lists and returning the
/// combination which performed best.
/// </summary>
/// <param name="problem">The training data</param>
/// <param name="validation">The validation data</param>
/// <param name="parameters">The parameters to use when optimizing</param>
/// <param name="CValues">The C values to use</param>
/// <param name="GammaValues">The Gamma values to use</param>
/// <param name="outputFile">The output file for the parameter results</param>
/// <param name="C">The optimal C value will be placed in this variable</param>
/// <param name="Gamma">The optimal Gamma value will be placed in this variable</param>
public static void Grid(
Problem problem,
Problem validation,
Parameter parameters,
List<double> CValues,
List<double> GammaValues,
string outputFile,
out double C,
out double Gamma)
{
C = 0;
Gamma = 0;
double maxScore = double.MinValue;
StreamWriter output = null;
if (outputFile != null)
output = new StreamWriter(outputFile);
for (int i = 0; i < CValues.Count; i++)
for (int j = 0; j < GammaValues.Count; j++)
{
parameters.C = CValues[i];
parameters.Gamma = GammaValues[j];
Model model = Training.Train(problem, parameters);
double test = Prediction.Predict(validation, "tmp.txt", model, false);
Console.Write("{0} {1} {2}", parameters.C, parameters.Gamma, test);
if (output != null)
output.WriteLine("{0} {1} {2}", parameters.C, parameters.Gamma, test);
if (test > maxScore)
{
C = parameters.C;
Gamma = parameters.Gamma;
maxScore = test;
Console.WriteLine(" New Maximum!");
}
else Console.WriteLine();
}
if (output != null)
output.Close();
}
/// <summary>
/// Trains a model using the provided training data and parameters.
/// </summary>
/// <param name="problem">The training data</param>
/// <param name="parameters">The parameters to use</param>
/// <returns>A trained SVM Model</returns>
public static Model Train(Problem problem, Parameter parameters)
{
string error = Procedures.svm_check_parameter(problem, parameters);
if (error == null)
return Procedures.svm_train(problem, parameters);
else throw new Exception(error);
}
private static void parseCommandLine(string[] args, out Parameter parameters, out Problem problem, out bool crossValidation, out int nrfold, out string modelFilename)
{
int i;
parameters = new Parameter();
// default values
crossValidation = false;
nrfold = 0;
// parse options
for (i = 0; i < args.Length; i++)
{
if (args[i][0] != '-')
break;
++i;
switch (args[i - 1][1])
{
case 's':
parameters.SvmType = (SvmType)int.Parse(args[i]);
break;
case 't':
parameters.KernelType = (KernelType)int.Parse(args[i]);
break;
case 'd':
parameters.Degree = int.Parse(args[i]);
break;
case 'g':
parameters.Gamma = double.Parse(args[i]);
break;
case 'r':
parameters.Coefficient0 = double.Parse(args[i]);
break;
case 'n':
parameters.Nu = double.Parse(args[i]);
break;
case 'm':
parameters.CacheSize = double.Parse(args[i]);
break;
case 'c':
parameters.C = double.Parse(args[i]);
break;
case 'e':
parameters.EPS = double.Parse(args[i]);
break;
case 'p':
parameters.P = double.Parse(args[i]);
break;
case 'h':
parameters.Shrinking = int.Parse(args[i]) == 1;
break;
case 'b':
parameters.Probability = int.Parse(args[i]) == 1;
break;
case 'v':
crossValidation = true;
nrfold = int.Parse(args[i]);
if (nrfold < 2)
{
throw new ArgumentException("n-fold cross validation: n must >= 2");
}
break;
case 'w':
parameters.Weights[int.Parse(args[i - 1].Substring(2))] = double.Parse(args[1]);
break;
default:
throw new ArgumentException("Unknown Parameter");
}
}
// determine filenames
if (i >= args.Length)
throw new ArgumentException("No input file specified");
problem = Problem.Read(args[i]);
if (parameters.Gamma == 0)
parameters.Gamma = 1.0 / problem.MaxIndex;
if (i < args.Length - 1)
modelFilename = args[i + 1];
else
{
int p = args[i].LastIndexOf('/') + 1;
modelFilename = args[i].Substring(p) + ".model";
}
}
private static double doCrossValidation(Problem problem, Parameter parameters, int nr_fold)
{
int i;
double[] target = new double[problem.Count];
Procedures.svm_cross_validation(problem, parameters, nr_fold, target);
int total_correct = 0;
double total_error = 0;
double sumv = 0, sumy = 0, sumvv = 0, sumyy = 0, sumvy = 0;
if (parameters.SvmType == SvmType.EPSILON_SVR || parameters.SvmType == SvmType.NU_SVR)
{
for (i = 0; i < problem.Count; i++)
{
double y = problem.Y[i];
double v = target[i];
total_error += (v - y) * (v - y);
sumv += v;
sumy += y;
sumvv += v * v;
sumyy += y * y;
sumvy += v * y;
}
return (problem.Count * sumvy - sumv * sumy) / (Math.Sqrt(problem.Count * sumvv - sumv * sumv) * Math.Sqrt(problem.Count * sumyy - sumy * sumy));
}
else
for (i = 0; i < problem.Count; i++)
if (target[i] == problem.Y[i])
++total_correct;
return (double)total_correct / problem.Count;
}
/// <summary>
/// Determines the Range transform for the provided problem. Uses the default lower and upper bounds.
/// </summary>
/// <param name="prob">The Problem to analyze</param>
/// <returns>The Range transform for the problem</returns>
public static RangeTransform Compute(Problem prob)
{
return Compute(prob, DEFAULT_LOWER_BOUND, DEFAULT_UPPER_BOUND);
}
/// <summary>
/// Determines the Range transform for the provided problem.
/// </summary>
/// <param name="prob">The Problem to analyze</param>
/// <param name="lowerBound">The lower bound for scaling</param>
/// <param name="upperBound">The upper bound for scaling</param>
/// <returns>The Range transform for the problem</returns>
public static RangeTransform Compute(Problem prob, double lowerBound, double upperBound)
{
double[] minVals = new double[prob.MaxIndex];
double[] maxVals = new double[prob.MaxIndex];
for (int i = 0; i < prob.MaxIndex; i++)
{
minVals[i] = double.MaxValue;
maxVals[i] = double.MinValue;
}
for (int i = 0; i < prob.Count; i++)
{
for (int j = 0; j < prob.X[i].Length; j++)
{
int index = prob.X[i][j].Index - 1;
double value = prob.X[i][j].Value;
minVals[index] = Math.Min(minVals[index], value);
maxVals[index] = Math.Max(maxVals[index], value);
}
}
for (int i = 0; i < prob.MaxIndex; i++)
{
if (minVals[i] == double.MaxValue || maxVals[i] == double.MinValue)
{
minVals[i] = 0;
maxVals[i] = 0;
}
}
return new RangeTransform(minVals, maxVals, lowerBound, upperBound);
}
/// <summary>
/// Writes a problem to a stream.
/// </summary>
/// <param name="stream">The stream to write the problem to.</param>
/// <param name="problem">The problem to write.</param>
public static void Write(Stream stream, Problem problem)
{
TemporaryCulture.Start();
StreamWriter output = new StreamWriter(stream);
for (int i = 0; i < problem.Count; i++)
{
output.Write(problem.Y[i]);
for (int j = 0; j < problem.X[i].Length; j++)
output.Write(" {0}:{1}", problem.X[i][j].Index, problem.X[i][j].Value);
output.WriteLine();
}
output.Flush();
TemporaryCulture.Stop();
}
/// <summary>
/// Predicts the class memberships of all the vectors in the problem.
/// </summary>
/// <param name="problem">The SVM Problem to solve</param>
/// <param name="outputFile">File for result output</param>
/// <param name="model">The Model to use</param>
/// <param name="predict_probability">Whether to output a distribution over the classes</param>
/// <returns>Percentage correctly labelled</returns>
public static double Predict(
Problem problem,
string outputFile,
Model model,
bool predict_probability)
{
int correct = 0;
int total = 0;
double error = 0;
double sumv = 0, sumy = 0, sumvv = 0, sumyy = 0, sumvy = 0;
StreamWriter output = outputFile != null ? new StreamWriter(outputFile) : null;
SvmType svm_type = Procedures.svm_get_svm_type(model);
int nr_class = Procedures.svm_get_nr_class(model);
int[] labels = new int[nr_class];
double[] prob_estimates = null;
if (predict_probability)
{
if (svm_type == SvmType.EPSILON_SVR || svm_type == SvmType.NU_SVR)
{
Console.WriteLine("Prob. model for test data: target value = predicted value + z,\nz: Laplace distribution e^(-|z|/sigma)/(2sigma),sigma=" + Procedures.svm_get_svr_probability(model));
}
else
{
Procedures.svm_get_labels(model, labels);
prob_estimates = new double[nr_class];
if (output != null)
{
output.Write("labels");
for (int j = 0; j < nr_class; j++)
{
output.Write(" " + labels[j]);
}
output.Write("\n");
}
}
}
else
{
Procedures.svm_get_labels(model, labels);
if (output != null)
{
output.Write("labels");
for (int j = 0; j < nr_class; j++)
{
output.Write(" " + labels[j]);
}
output.Write("\n");
}
}
for (int i = 0; i < problem.Count; i++)
{
double target = problem.Y[i];
Node[] x = problem.X[i];
double v;
if (predict_probability && (svm_type == SvmType.C_SVC || svm_type == SvmType.NU_SVC))
{
v = Procedures.svm_predict_probability(model, x, prob_estimates);
if (output != null)
{
output.Write(target + " " + v + " ");
for (int j = 0; j < nr_class; j++)
{
output.Write(prob_estimates[j] + " ");
}
output.Write("\n");
}
}
else
{
v = Procedures.svm_predict(model, x);
if (output != null)
output.Write(target + " " + 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;
}
if (output != null)
output.Close();
return (double)correct / total;
}
/// <summary>
/// Writes a problem to a file. This will overwrite any previous data in the file.
/// </summary>
/// <param name="filename">The file to write to</param>
/// <param name="problem">The problem to write</param>
public static void Write(string filename, Problem problem)
{
FileStream output = File.Open(filename, FileMode.Create);
try
{
Write(output, problem);
}
finally
{
output.Close();
}
}
/// <summary>
/// Determines the Range transform for the provided problem. Uses the default lower and upper bounds.
/// </summary>
/// <param name="prob">The Problem to analyze</param>
/// <returns>The Range transform for the problem</returns>
public static RangeTransform Compute(Problem prob)
{
return(Compute(prob, DEFAULT_LOWER_BOUND, DEFAULT_UPPER_BOUND));
}
