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));
}
}
/// <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;
}
/// <summary>
/// foamliu, 2008/12/30.
/// Notes: the order of presentation of training examples should be randomized from epoch
/// to epoch.
///
/// </summary>
private void ShuffleTrainSet()
{
ExampleSet t_set = this.TrainSet;
int num = t_set.Examples.Count;
Random rand = new Random();
int[] cards = new int[num];
for (int i = 0; i < num; i++)
cards[i] = i;
for (int i = 0; i < num; i++)
{
int temp;
int j = (int)(rand.NextDouble() * num); // 0 - (num-1)
temp = cards[i];
cards[i] = cards[j];
cards[j] = temp;
}
Example[] examples = new Example[num];
for (int i = 0; i < num; i++)
{
examples[i] = t_set.Examples[cards[i]];
}
t_set.Examples.Clear();
for (int i = 0; i < num; i++)
{
t_set.Examples.Add(examples[i]);
}
}
public ExampleDistancePair(Example example, double distance)
{
this.m_example = example;
this.m_distance = distance;
}
public void AddExample(Example example)
{
m_Collection.Add(example);
}
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;
}
}
public void AddExample(Example example)
{
m_Collection.Add(example);
}
public int Predict(Example example)
{
return +1;
}
private int PredictText(Example example)
{
double f;
f = SparseVector.DotProduct(m_weight, example.X)/* + m_b*/;
if (f >= 0)
return +1;
else
return -1;
}