private void btn_buildNgramfromDB_Click(object sender, EventArgs e)
{
String[] Languages = "'eu';,'ca';,'gl';,'es';,'en';,'pt';".Split(',');
FileWriter FW = new FileWriter();
for (int i = 0; i < Languages.Length; i++)
{
FetchFromDB fetchFromDatabase = new FetchFromDB();
DataTable dataTable = fetchFromDatabase.getTrainingDataFor(Languages[i]);
fetchFromDatabase.closeConnection();
DataParser DP = new DataParser();
DataTable cleanTable = new DataTable();
cleanTable = DP.getCleanTable(dataTable);
NgramBuilder NB = new NgramBuilder();
DataTable uniGram = new DataTable();
uniGram = NB.GetGram(cleanTable, 1);
double uniGramN = NB.getTotalFrequency();
DataTable smoothedUniGram = new DataTable();
smoothedUniGram = NB.applySmoothing(uniGram, 0.1);
double uniGramSmoothedN = NB.getTotalFrequency();
DataTable biGram = new DataTable();
biGram = NB.GetGram(cleanTable, 2);
double biGramN = NB.getTotalFrequency();
DataTable smoothedBiGram = new DataTable();
smoothedBiGram = NB.applySmoothing(biGram, 0.1);
double BiGramSmoothedN = NB.getTotalFrequency();
//FileWriter FW = new FileWriter();
FW.writeUniGram(uniGram, Languages[i], "False", uniGramN);
FW.writeUniGram(smoothedUniGram, Languages[i], "True", uniGramSmoothedN);
FW.writeBiGram(biGram, Languages[i], "False", biGramN);
FW.writeBiGram(smoothedBiGram, Languages[i], "True", BiGramSmoothedN);
MessageBox.Show("Done " + Languages[i]);
}
FW.closeWriter();
}
public void testFromDB()
{
NaiveBayesClassifier NB;
RegexDataParser RDP;
FetchFromDB fetchFromDb;
UtilityFunctions utilityFunction = new UtilityFunctions();
Hashtable Vocabulary = utilityFunction.TableToHashSumAdded((new FetchFromDB()).getVocabulary());
DBProgressBar.ForeColor = Color.Blue;
DBProgressBar.Value = 0;
DBProgressBar.Visible = true;
for (int i = 0; i < freqTables.Length; i++)
{
NB = new NaiveBayesClassifier(freqTables);
RDP = new RegexDataParser();
fetchFromDb = new FetchFromDB();
DataTable dataTable = fetchFromDb.getTrainingDataFor(rawTables[i], 0);
foreach (DataRow row in dataTable.Rows) // Loop over the rows.
foreach (var item in row.ItemArray) // Loop over the items.
{
String Lyrics = RDP.StripTagsRegexCompiled(item.ToString());
String[] lyric = Lyrics.Split(' ');
List<string> containinginVocab = new List<string>();
for (int l = 0; l < lyric.Length; l++)
{
if (Vocabulary.ContainsKey(lyric[l]))
containinginVocab.Add(lyric[l]);
}
Double[] classification = NB.ApplyBayes(containinginVocab.ToArray());
int indx = NB.getMaxConfidence(classification);
confusionMatrix[i, indx] = confusionMatrix[i, indx] + 1;
}
dataTable = null;
DBProgressBar.Value = DBProgressBar.Value + 100 / freqTables.Length;
}
Double[] rowFrequency = utilityFunction.getRowCount(confusionMatrix);
Double[,] PercentageMatrix = new Double[rawTables.Length, rawTables.Length];
for (int i = 0; i < 5; i++)
for (int j = 0; j < 5; j++)
PercentageMatrix[i, j] = (confusionMatrix[i, j] * 100) / rowFrequency[i];
String[] Genres = { "Rap", "Country", "Religion", "Rock", "Reggae" };
InsertIntoDB insertMatrix = new InsertIntoDB();
insertMatrix.insertConfusionMatrix(PercentageMatrix, Genres);
ReportForm rf = new ReportForm();
rf.Show();
}
public void trainFromDB()
{
DBProgressBar.ForeColor = Color.Blue;
for (int i = 0; i < rawTables.Length; i++)
{
FetchFromDB Fetch = new FetchFromDB();
UtilityFunctions UF = new UtilityFunctions();
DataTable dt = Fetch.getTrainingDataFor(rawTables[i], 1);
Hashtable ht = UF.TableToHashSumAdded(dt);
InsertIntoDB insertToDB = new InsertIntoDB();
insertToDB.InsertDataFor(freqTables[i], ht);
DBProgressBar.Value = DBProgressBar.Value + 100 / rawTables.Length;
}
}
