public void Test()
{
var trainingDocuments =
new Dictionary <string, string>
{
{ "sports", File.ReadAllText("..\\..\\TestData\\Sports.txt") },
{ "economy", File.ReadAllText("..\\..\\TestData\\Economy.txt") },
};
var featureExtractor = new BagOfWordsFeatureExtractor();
var trainedModels = new Dictionary <IDistribution <string>, string>();
foreach (var trainingItem in trainingDocuments)
{
var distribution = CreateModel(featureExtractor, trainingItem.Value);
trainedModels.Add(distribution, trainingItem.Key);
}
var classifier =
new KnnMonoCategorizedClassifier <IDistribution <string>, string>(new VectorDistanceCalculator <string>(), trainedModels);
var resultSports = classifier.Classify(CreateModel(featureExtractor,
"Fitch Ratings on Wednesday said Britain's latest budget proposals show commitment to its existing deficit reduction strategy and do not impact its AAA credit rating.")).ToArray();
Assert.GreaterOrEqual(resultSports.Length, 1);
Assert.AreEqual(resultSports[0].Item1, "economy");
var resultFinance = classifier.Classify(CreateModel(featureExtractor,
"Ryan Flannigan strikes a four off the last ball to help Scotland claim a four-wicket win over Canada in the fifth-place play-off at the qualifying tournament for the ICC World Twenty20 in Dubai.")).ToArray();
Assert.GreaterOrEqual(resultFinance.Length, 1);
Assert.AreEqual(resultFinance[0].Item1, "sports");
}
public void Test()
{
var trainingDocuments =
new Dictionary<string, string>
{
{ "sports", File.ReadAllText("..\\..\\TestData\\Sports.txt") },
{ "economy", File.ReadAllText("..\\..\\TestData\\Economy.txt") },
};
var featureExtractor = new BagOfWordsFeatureExtractor();
var trainedModels = new Dictionary<IDistribution<string>, string>();
foreach (var trainingItem in trainingDocuments)
{
var distribution = CreateModel(featureExtractor, trainingItem.Value);
trainedModels.Add(distribution, trainingItem.Key);
}
var classifier =
new KnnMonoCategorizedClassifier<IDistribution<string>, string>(new VectorDistanceCalculator<string>(), trainedModels);
var resultSports = classifier.Classify(CreateModel(featureExtractor,
"Fitch Ratings on Wednesday said Britain's latest budget proposals show commitment to its existing deficit reduction strategy and do not impact its AAA credit rating.")).ToArray();
Assert.GreaterOrEqual(resultSports.Length, 1);
Assert.AreEqual(resultSports[0].Item1, "economy");
var resultFinance = classifier.Classify(CreateModel(featureExtractor,
"Ryan Flannigan strikes a four off the last ball to help Scotland claim a four-wicket win over Canada in the fifth-place play-off at the qualifying tournament for the ICC World Twenty20 in Dubai.")).ToArray();
Assert.GreaterOrEqual(resultFinance.Length, 1);
Assert.AreEqual(resultFinance[0].Item1, "sports");
}
public IEnumerable <Tuple <LanguageInfo, double> > Classify(IDistribution <T> guessedLanguageModel)
{
IDictionary <T, int> rankedGuessedLanguageModel = GetRankedLanguageModel(guessedLanguageModel);
var classifier =
new KnnMonoCategorizedClassifier <IDictionary <T, int>, LanguageInfo>(
new RankingDistanceCalculator <T>(_defaultNgramRankOnAbsence),
_etalonLanguageModel2languageName);
IEnumerable <Tuple <LanguageInfo, double> > likelyLanguages = classifier.Classify(rankedGuessedLanguageModel);
return(likelyLanguages);
}