public NaiveBayesCategoryCollection(CategoryCollection categoryCollection)
{
m_CategoryMap = new SortedDictionary<Category, NaiveBayesCategory>();
foreach (Category c in categoryCollection.Collection)
{
m_CategoryMap.Add(c, new NaiveBayesCategory());
}
}
public CostSensitiveNaiveBayes(CategoryCollection collect)
: base(collect)
{
int i = 0;
foreach (Category c in collect.Collection)
{
className[i++] = c.Name;
}
}
private static ClassificationProblem CreateChessBoard()
{
ClassificationProblem problem = new ClassificationProblem();
CategoryCollection collect = new CategoryCollection();
collect.Add(new Category(+1, "+1"));
collect.Add(new Category(-1, "-1"));
problem.Dimension = 2;
problem.CategoryCollection = collect;
problem.TrainingSet = GetExamples(collect);
problem.ValidationSet = GetExamples(collect);
return problem;
}
/// <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 NaiveBayesClassifier(CategoryCollection collect)
{
m_CategoryCollection = collect;
}
public Binary_SVM_GradientDescent(CategoryCollection collect)
{
m_categoryCollection = collect;
// It was said that for text classification, linear kernel is the best choice,
// because of the already-high-enough feature dimension
m_kernel = new LinearKernel();
}
