private static void TestNaiveBayes()
{
var data = LoadDataFromfCSV("Data.csv");
var fixedData = TableFixedData.FromTableData(data);
var samples = TableFixedData.ToSample(fixedData);
var columnsTypes = fixedData.ColumnDataTypes;
var algorithm = new NaiveBayesClassifierOld(fixedData);
var algorithm1 = new NaiveBayesClassifier(samples, fixedData.ClassesValue.Length, columnsTypes);
var dataRow = data.ToList()[2];
var className = algorithm.Compute(dataRow);
var classId = algorithm1.Compute(fixedData.GetSample(dataRow));
var className1 = fixedData.ClassesValue[classId];
int missed = 0;
for (int index = 0; index < 50; index++)
{
var row = data.ToList()[index];
var estimatedClassName = algorithm.Compute(row);
if (estimatedClassName != row.Class)
{
missed++;
}
}
}
public int Compute(string sentence)
{
var sample = new DataSample();
var sampleDataPoints = new List <DataPoint>();
var sentenceWords = TextParser.SplitToWords(sentence).ToArray();
var isNegated = false;
for (int index = 0; index < sentenceWords.Length; index++)
{
var currentWord = sentenceWords[index].ToLower();
if (_negationWords.Contains(currentWord))
{
isNegated = !isNegated;
}
else
{
if (currentWord.EndsWith("n't"))
{
isNegated = !isNegated;
}
else
{
currentWord = isNegated ? "not_" + currentWord : currentWord;
}
if (_wordDictionary.ContainsKey(currentWord))
{
sampleDataPoints.Add(new DataPoint {
ColumnId = _wordDictionary[currentWord], Value = 1
});
}
}
}
sample.DataPoints = sampleDataPoints.ToArray();
return(_naiveBayesClassifier.Compute(sample));
}
