private void outputError(ClassificationAlgorithmBase <double[][, ]> alg)
{
Console.WriteLine("Errors:");
var sample = new ClassifiedSample <double[][, ]>();
foreach (var obj in Data.Data)
{
var data = obj.Key;
var key = new double[data.Length][, ];
for (int i = 0; i < data.Length; i++)
{
key[i] = new double[1, 1];
}
for (int i = 0; i < data.Length; i++)
{
key[i][0, 0] = data[i];
}
sample[key] = obj.Value;
}
var errors = alg.GetErrors(sample, 0, true);
var ec = errors.Count();
var dc = Data.Data.Count;
var pct = Math.Round(100.0F * ec / dc, 2);
Console.WriteLine("{0} of {1} ({2}%)", ec, dc, pct);
}
private void outputError(ClassificationAlgorithmBase <double[]> alg)
{
Console.WriteLine("Errors:");
var errors = alg.GetErrors(Data.Data, 0, true);
var ec = errors.Count();
var dc = Data.Data.Count;
var pct = Math.Round(100.0F * ec / dc, 2);
Console.WriteLine("{0} of {1} ({2}%)", ec, dc, pct);
}
public void Run(ClassificationAlgorithmBase <double[]> algorithm, int xidx = 0, int yidx = 1, double[] shear = null)
{
m_XIdx = xidx;
m_YIdx = yidx;
m_Shear = shear;
m_InputDim = algorithm.TrainingSample.First().Key.Length;
var fn = string.Format("data/{0}-{1:yyyyMMdd-hhmmss}.csv", algorithm.Name, DateTime.Now);
var dir = Path.GetDirectoryName(fn);
Directory.CreateDirectory(dir);
using (var file = File.Create(fn))
using (var writer = new StreamWriter(file))
{
prepareCanvas();
doCalc(algorithm, writer);
}
}
private void init()
{
using (var spam = Assembly.GetExecutingAssembly().GetManifestResourceStream("ML.TextDemo.data.SPAM_p2.42.mld"))
{
var proc = new TextPreprocessor(new EnglishSimpleTokenizer(),
new EnglishStopwords(),
new EnglishSimpleNormalizer(),
new EnglishPorterStemmer());
m_SpamAlgorithm = new ComplementNaiveBayesianAlgorithm()
{
Preprocessor = proc
};
m_SpamAlgorithm.Deserialize(spam);
}
using (var r8 = Assembly.GetExecutingAssembly().GetManifestResourceStream("ML.TextDemo.data.RR8_p4.37.mld"))
{
var proc = new TextPreprocessor(new EnglishSimpleTokenizer(),
new EnglishStopwords(),
new EnglishSimpleNormalizer(),
new EnglishPorterStemmer());
m_ReutersR8Algorithm = new MultinomialNaiveBayesianAlgorithm()
{
Preprocessor = proc
};
m_ReutersR8Algorithm.Deserialize(r8);
}
using (var n20 = Assembly.GetExecutingAssembly().GetManifestResourceStream("ML.TextDemo.data.N20_p17.35.mld"))
{
var proc = new TextPreprocessor(new EnglishSimpleTokenizer(),
new EnglishStopwords(),
new EnglishSimpleNormalizer(),
new EnglishPorterStemmer());
m_Newsgroups20Algorithm = new TFIDFNaiveBayesianAlgorithm()
{
Preprocessor = proc
};
m_Newsgroups20Algorithm.Deserialize(n20);
}
}
private void doCalc(ClassificationAlgorithmBase <double[]> algorithm, StreamWriter writer)
{
for (var k = 0; k < Math.Max(m_XCnt, m_YCnt); k++)
{
var px = (k < m_XCnt) ? getProjPoint(k, 0)[0].ToString(CultureInfo.InvariantCulture) : string.Empty;
var py = (k < m_YCnt) ? getProjPoint(0, k)[1].ToString(CultureInfo.InvariantCulture) : string.Empty;
var pd = string.Empty;
if (k < m_YCnt)
{
var data = new double[m_XCnt];
for (int i = 0; i < m_XCnt; i++)
{
var point = getPoint(i, k);
var cls = algorithm.Predict(point);
data[i] = cls.Value;
}
pd = string.Join(COMMA, data);
}
writer.WriteLine("{0},{1},{2}", px, py, pd);
}
}
