public void TestTrainInconsistentTrainingDataLength()
{
int numTrainingExamples = 6;
int numDataElements = 5;
List <List <object> > trainingData = new List <List <object> >();
List <object> targetData = GenerateValidData(numTrainingExamples);
Random rand = new Random();
bool hasInconsistentData = false;
for (int i = 0; i < numTrainingExamples; i++)
{
if (rand.Next(2) == 0)
{
trainingData.Add(GenerateValidData(rand.Next(numTrainingExamples)));
hasInconsistentData = true;
}
else
{
trainingData.Add(GenerateValidData(numDataElements));
}
}
if (!hasInconsistentData)
{
trainingData[rand.Next(numTrainingExamples)] = GenerateValidData(rand.Next(numTrainingExamples, 1000));
}
try
{
NaiveBayesModel.Train(trainingData, targetData);
Assert.Fail("Model was required to throw an InvalidDataFormatException, but did not");
}
catch (InvalidDataFormatException)
{
//All ok...
}
}
private void buttonTrain_Click(object sender, RoutedEventArgs e)
{
try
{
if (textBoxDescription.Text.Length > 0 && textBoxGenre.Text.Length > 0)
{
List <string> genresArray = parseGenres();
if (genresArray.Count == 0)
{
throw new Exception("Genres not found!");
}
StringBuilder genres = new StringBuilder();
foreach (var genre in genresArray)
{
genres.Append("'" + genre + "'");
if (genre != genresArray.Last())
{
genres.Append("; ");
}
classifier.Train(textBoxDescription.Text, genre);
}
showlog();
MessageBox.Show("Train successfull!\n" + "Trained genres: " + genres);
textBoxGenre.Text = "";
}
}
catch (Exception ex)
{
MessageBox.Show(ex.Message);
}
}
public static void Main(string[] args)
{
var smsCollection = new DataReader($@"{Environment.CurrentDirectory}\Data\SMSSpamCollection").Read();
var trainingData = smsCollection.Skip(1000);
var verificationData = smsCollection.Take(1000);
ITokenizer tokenizer = new ToLowerWordsTokenizer();
var classifier = new NaiveBayes(tokenizer);
IVocabularyGenerator vacabulary = new TopWordsVocabulary();
classifier.Train(trainingData.ToArray(), vacabulary.GetVocabulary(tokenizer, trainingData));
Evaluate(classifier, verificationData);
Console.WriteLine("___________________________________");
trainingData = smsCollection.Take(4800);
verificationData = smsCollection.Skip(4800);
tokenizer = new WordsTokenizer();
classifier.Train(trainingData.ToArray(), new string[] { "FREE", "txt", "car", "call", "i", "mobile", "you", "me" });
Evaluate(classifier, verificationData);
Console.ReadKey();
}
public void TestTrain()
{
var naiveBayes = new NaiveBayes();
naiveBayes.Train(iris.GetInstanceList(), null);
Assert.AreEqual(5.33, 100 * naiveBayes.Test(iris.GetInstanceList()).GetErrorRate(), 0.01);
naiveBayes.Train(bupa.GetInstanceList(), null);
Assert.AreEqual(38.55, 100 * naiveBayes.Test(bupa.GetInstanceList()).GetErrorRate(), 0.01);
naiveBayes.Train(dermatology.GetInstanceList(), null);
Assert.AreEqual(69.40, 100 * naiveBayes.Test(dermatology.GetInstanceList()).GetErrorRate(), 0.01);
naiveBayes.Train(car.GetInstanceList(), null);
Assert.AreEqual(12.91, 100 * naiveBayes.Test(car.GetInstanceList()).GetErrorRate(), 0.01);
naiveBayes.Train(tictactoe.GetInstanceList(), null);
Assert.AreEqual(30.17, 100 * naiveBayes.Test(tictactoe.GetInstanceList()).GetErrorRate(), 0.01);
naiveBayes.Train(nursery.GetInstanceList(), null);
Assert.AreEqual(9.70, 100 * naiveBayes.Test(nursery.GetInstanceList()).GetErrorRate(), 0.01);
}
public static void Main(string[] args)
{
var smsCollection = new DataReader($@"{Environment.CurrentDirectory}\Data\SMSSpamCollection").Read();
var trainingData = smsCollection.Skip(1000);
var verificationData = smsCollection.Take(1000);
var tokenizer = new WordsTokenizer();
Run("Using HAM classifier ... ", () =>
{
var hamClassifier = new HamClassifier();
Evaluate(hamClassifier, verificationData);
});
Run("Using Primitive classifier ... ", () =>
{
var primitiveSpamClassifier = new PrimitiveSpamClassifier();
Evaluate(primitiveSpamClassifier, verificationData);
});
Run("Using Primitive Naive Bayer classifier #1 (automatic token selection - 30 most popular tokens) ... ", () =>
{
var naiveBayesClassifier = new NaiveBayes(tokenizer);
naiveBayesClassifier.Train(trainingData.ToArray(), new TopWordsVocabulary().GetVocabulary(tokenizer, trainingData));
Evaluate(naiveBayesClassifier, verificationData);
});
Run("Using Primitive Naive Bayer classifier #2 (manually selected tokens) ... ", () =>
{
var naiveBayesClassifier = new NaiveBayes(tokenizer);
naiveBayesClassifier.Train(trainingData.ToArray(), new [] { "FREE", "txt", "car", "call", "i", "mobile", "you", "me" });
Evaluate(naiveBayesClassifier, verificationData);
});
Console.WriteLine("Press any key to terminate.");
Console.ReadKey();
}
public void Train(List <List <object> > X, List <object> Y)
{
Model = new NaiveBayes();
Model.Train(X, Y);
}