public ExampleSet GetProof(SparseVector x)
{
ExampleSet res = new ExampleSet();
List<ExampleDistancePair> list = new List<ExampleDistancePair>();
foreach (Example e in m_t_set.Examples)
{
list.Add(new ExampleDistancePair(e, SparseVector.Distance(x, e.X)));
}
list.Sort();
int[] votes = new int[m_catnum];
for (int i = 0; i < votes.Length; i++)
{
votes[i] = 0;
}
for (int i = 0; i < this.m_k; i++)
{
ExampleDistancePair pair = list[i];
res.AddExample(pair.Example);
}
return res;
}
public LinearLeraningMachine(ClassificationProblem problem)
{
this.m_problem = problem;
this.m_t_set = problem.TrainingSet;
//this.m_problem.RetrieveVocabulary(out this.m_voc);
this.m_l = m_t_set.Examples.Count;
//this.m_weight = new SparseVector(m_voc.Count);
}
public AdaBoost(ExampleSet t_set, int t, int n)
{
m_t_set = t_set;
m_m = m_t_set.Examples.Count;
m_dist = new double[this.m_m];
m_t = t;
m_n = n;
m_a = new double[m_t];
m_h = new WeakLearn[m_t];
}
public void Test()
{
int l = 30;
int k = 10;
double ratioSeparable = 0;
int numSeparable = 0;
ExampleSet set = new ExampleSet();
for (int d = 10; d < 50; d=d+10)
{
numSeparable = 0;
for (int n = 0; n < k; n++)
{
set.Examples.Clear();
for (int i = 0; i < l; i++)
{
SparseVector x = new SparseVector(d);
for (int j = 0; j < d; j++)
{
x[j] = m_rand.NextDouble();
}
Category c = GetRandCategory();
Example e = new Example(c);
e.X = x;
set.AddExample(e);
}
SimpleLLM llm = new SimpleLLM(set, d);
//Logging.Info(string.Format("IsLinearSeparable: {0}", llm.IsLinearSeparable()));
//System.Console.WriteLine(string.Format("IsLinearSeparable: {0}", llm.IsLinearSeparable()));
if (llm.IsLinearSeparable())
{
numSeparable++;
}
}
ratioSeparable = 1.0 * numSeparable / k;
System.Console.WriteLine(string.Format("d: {0}, l: {1}, Separable ratio: {2}", d, l, ratioSeparable));
}
}
private SparseVector m_weight; // weight vector
#endregion Fields
#region Constructors
public Binary_SVM_SMO(ClassificationProblem problem)
{
this.m_problem = problem;
this.m_t_set = this.m_problem.TrainingSet;
// this.m_problem.RetrieveVocabulary(out this.m_voc);
this.m_l = m_t_set.Examples.Count;
this.m_alpha = new double[m_l];
this.m_error = new double[m_l];
this.m_kernel = new LinearKernel();
this.m_NonBound = new List<int>();
this.m_rand = new Random();
this.m_weight = new SparseVector(problem.Dimension);
// foamliu, 2009/01/12, default values
this.m_c = Constants.SVM_C;
this.m_eta = Constants.SVM_Eta;
this.m_tolerance = Constants.SVM_Tolerance;
this.m_epsilon = Constants.SVM_Epsilon;
}
/// <summary>
/// foamliu, 2009/12/21, please make sure you've uncompressed "2_newsgroups.7z" in the "data" folder.
/// </summary>
/// <returns></returns>
private static ClassificationProblem CreateText()
{
const string DataFolder = @"..\data\2_newsgroups";
ClassificationProblem problem = new ClassificationProblem();
ExampleSet t_set = new ExampleSet();
ExampleSet v_set = new ExampleSet();
CategoryCollection collect = new CategoryCollection();
collect.Add(new Category(+1, "+1"));
collect.Add(new Category(-1, "-1"));
problem.Dimension = 2;
problem.CategoryCollection = collect;
DirectoryInfo dataFolder = new DirectoryInfo(DataFolder);
DirectoryInfo[] subfolders = dataFolder.GetDirectories();
int count = 0;
for (int i = 0; i < subfolders.Count(); i++)
{
DirectoryInfo categoryFolder = subfolders[i];
int cat = i * 2 - 1;
// for all the text files in each category
FileInfo[] files = categoryFolder.GetFiles();
count = 0;
int trainSetCount = Convert.ToInt32(Constants.TrainingSetRatio * files.Count());
for (int j = 0; j < files.Count(); j++)
{
FileInfo textFile = files[j];
Example e = new Example();
if (++count < trainSetCount)
{
t_set.AddExample(e);
}
else
{
v_set.AddExample(e);
}
}
}
problem.TrainingSet = t_set;
problem.ValidationSet = v_set;
return problem;
}
/// <summary>
/// foamliu, 2009/04/15, 生成样本.
/// </summary>
/// <param name="set"></param>
private static ExampleSet GetExamples(CategoryCollection collect)
{
const int Rows = 4;
const int Columns = 4;
const int CellWidth = 100;
const int CellHeight = 100;
const int ExampleNumber = 640;
ExampleSet set = new ExampleSet();
set.Examples.Clear();
Random rand = new Random();
for (int i = 0; i < ExampleNumber; i++)
{
int x = (int)(rand.NextDouble() * Columns * CellWidth);
int y = (int)(rand.NextDouble() * Rows * CellHeight);
Example e = new Example();
e.X = new SparseVector(2);
e.X[0] = x;
e.X[1] = y;
e.Label = collect.GetCategoryById(
GetCat(x, y, CellWidth, CellHeight));
set.AddExample(e);
}
return set;
}
public WeakLearn(int index, ExampleSet t_set)
{
m_index = index;
m_t_set = t_set;
m_m = t_set.Count;
}
public SimpleLLM(ExampleSet t_set, int d)
{
this.m_t_set = t_set;
this.m_l = t_set.Examples.Count;
this.m_weight = new SparseVector(d);
}
/// <summary>
/// No bias
/// </summary>
/// <param name="t_Set"></param>
/// <param name="x"></param>
/// <returns></returns>
private double Calculate_F(ExampleSet t_Set, SparseVector x)
{
double f = 0.0;
for (int i = 0; i < m_Alpha.Length; i++)
{
f += m_Alpha[i] * t_Set.Examples[i].Label.Id * m_kernel.Compute(t_Set.Examples[i].X, x);
}
return f;
}
private void CalculateWeight(ExampleSet t_Set)
{
for (int i = 0; i < l; i++)
{
m_weight.Add((t_Set.Examples[i].Label.Id * m_Alpha[i]) * t_Set.Examples[i].X);
}
}
private double CalculateSVM_W(ExampleSet t_Set)
{
double W = 0.0;
double temp = 0.0;
for (int i = 0; i < m_Alpha.Length; i++)
{
temp += m_Alpha[i];
}
W = temp;
temp = 0.0;
for (int i = 0; i < m_Alpha.Length; i++)
{
for (int j = 0; j < m_Alpha.Length; j++)
{
temp += t_Set.Examples[i].Label.Id * t_Set.Examples[j].Label.Id * m_Alpha[i] * m_Alpha[j] * m_kernel.Compute(t_Set.Examples[i].X, t_Set.Examples[j].X);
}
}
W = W - temp / 2;
return W;
}
public void PredictText(ExampleSet t_Set, Example text, ref ClassificationResult result)
{
double f;
f = Calculate_F(t_Set, text.X);
if (f >= 0)
{
result.ResultCategoryId = +1;
}
else
{
result.ResultCategoryId = -1;
}
}
