private void Button_saveResults_Click(object sender, EventArgs e)
{
var myUniqueFileName = DirectoryManager.GetSpecifiedDirectory("Results") + DirectoryManager.sep + $@"{DateTime.Now.Ticks}.txt";
using (var sw = new StreamWriter(myUniqueFileName))
{
for (int i = 0; i < numberOfUsedWindows; i++)
{
Window w = arrayOfWindows[i];
if (w.Txtb.Text == "")
{
break;
}
sw.WriteLine("Model: " + Path.GetFileName(w.Model));
sw.WriteLine("Input: " + w.Input);
if (w.UsedMorphodita)
{
sw.WriteLine("Output: " + w.Output);
sw.WriteLine("MorphoDiTa: pouzita");
}
else
{
sw.WriteLine("Output: " + w.Output);
sw.WriteLine("MorphoDiTa: nepouzita");
}
sw.WriteLine();
}
}
Reset();
}
/// <summary>
/// This methods loads files into ListBox
/// </summary>
private void LoadFiles()
{
string path = DirectoryManager.GetSpecifiedDirectory("SourceTXTFiles");
string[] files = Directory.GetFiles(path);
if (files.Length == 0)
{
textBox_Error.Text = "Je třeba nejdříve upravit soubor .txt.";
}
else
{
DirectoryName = Path.GetDirectoryName(files[0]);
for (int i = 0; i < files.Length; i++)
{
listBox_modelFiles.Items.Add(Path.GetFileNameWithoutExtension(files[i]));
}
}
}
private void Button_change_TXT_Click(object sender, EventArgs e)
{
Hide();
while (true)
{
OpenFileDialog openFileDialog1 = new OpenFileDialog
{
InitialDirectory = DirectoryManager.GetSpecifiedDirectory("PlainTexts"),
Filter = "Formát txt (*.txt)|*.txt|Všechny formáty (*.*)|*.*",
RestoreDirectory = true
};
if (openFileDialog1.ShowDialog() == DialogResult.OK)
{
try
{
if (openFileDialog1.FileName.EndsWith(".txt"))
{
TransformTXTFile.TransformFile(openFileDialog1.FileName);
MakeResultsVisible(true, ".txt", openFileDialog1.FileName);
break;
}
else
{
MakeResultsVisible(false, ".txt", openFileDialog1.FileName);
Show();
}
}
catch (SecurityException)
{
MessageBox.Show("Chyba při načítání souboru.");
}
}
else
{
ResetWindow();
Show();
break;
}
}
}
/// <summary>
/// This method merges all files multiplied by chosen constant to a single file
/// which will be saved in TMP file.
/// </summary>
/// <returns></returns>
private string MergeAllFiles()
{
string tmpFile = DirectoryManager.GetSpecifiedDirectory("Temp") + DirectoryManager.sep + textBox_fileName.Text + ".txt";
foreach (var item in DictFilesInModel)
{
string source = DirectoryManager.GetSpecifiedDirectory("SourceTXTFiles") + DirectoryManager.sep + item.Key.ToString() + ".txt";
for (int i = 0; i < item.Value[0]; i++)
{
using (Stream input = File.OpenRead(source))
using (Stream output = new FileStream(tmpFile, FileMode.Append,
FileAccess.Write, FileShare.None))
{
input.CopyTo(output);
}
}
}
return(tmpFile);
}
/// <summary>
/// This part trains model
/// </summary>
/// <author>
/// This method with libraries in Word2Vec.Net-master was programmed by GitHub user Eabdullin
/// link to GitHub: https://github.com/eabdullin/Word2Vec.Net
/// </author>
/// <param name="trainfile">This file is located in SourceTXT folder</param>
public static void TrainModel(string trainfile, int sizeOfVectors = 100, int minCount = 5, int iterations = 5)
{
string outputFileName = DirectoryManager.GetSpecifiedDirectory("Models") + DirectoryManager.sep + Path.GetFileName(trainfile);
var word2Vec = Word2VecBuilder.Create()
.WithTrainFile(trainfile) // Use text data to train the model;
.WithOutputFile(outputFileName) //Use to save the resulting word vectors / word clusters
.WithSize(sizeOfVectors) //Set size of word vectors; default is 100
.WithDebug(2) //Set the debug mode (default = 2 = more info during training)
.WithCBow(1) //Use the continuous bag of words model; default is 1 (use 0 for skip-gram model)
.WithAlpha(0.05f) //Set the starting learning rate; default is 0.025 for skip-gram and 0.05 for CBOW
.WithSample((float)1e-3) //Set threshold for occurrence of words.
.WithHs(0) //Use Hierarchical Softmax; default is 0 (not used)
.WithNegative(5) //Number of negative examples; default is 5, common values are 3 - 10 (0 = not used)
.WithThreads(12) //Use <int> threads (default 12)
.WithIter(iterations) //Run more training iterations (default 5)
.WithMinCount(minCount) //This will discard words that appear less than <int> times; default is 5
.Build();
word2Vec.TrainModel();
}
/// <summary>
/// The file will be transformed:
/// all letters except names toLower
/// all interpunction is wrapped by spaces
///
/// </summary>
/// <param name="file"></param>
public static void TransformFile(string file)
{
string basenameOfFileWithoutExtensions = Path.GetFileNameWithoutExtension(file);
string basenameOfFile = basenameOfFileWithoutExtensions + ".txt";
dictThisWordIsName.Clear();
FillDictionaryOfNames(file);
string result = DirectoryManager.GetSpecifiedDirectory("SourceTXTFiles") + DirectoryManager.sep + basenameOfFileWithoutExtensions + ".txt";
if (File.Exists(result))
{
int i = 1;
while (File.Exists(result))
{
result = DirectoryManager.GetSpecifiedDirectory("SourceTXTFiles") + DirectoryManager.sep + basenameOfFileWithoutExtensions + "_" + i + "_.txt";
i++;
}
}
try
{
using (StreamReader MyStreamReader = new StreamReader(file))
{
using (StreamWriter MyStreamWriter = new StreamWriter(result))
{
char oneChar;
StringBuilder sb = new StringBuilder();
while (MyStreamReader.Peek() >= 0)
{
oneChar = (char)MyStreamReader.Read();
if (bigCzechChars.Contains(oneChar) ||
smallCzechChars.Contains(oneChar) ||
numbers.Contains(oneChar))
{
sb.Append(oneChar);
}
else
{
string word = sb.ToString();
sb.Clear();
if (word.Length == 0)
{
MyStreamWriter.Write(ModifyDangerousSymbols(oneChar));
}
else if (word[0] <= 'Z' && word[0] >= 'A')
{
if (dictThisWordIsName.ContainsKey(word.ToLower()) && dictThisWordIsName[word.ToLower()])
{
MyStreamWriter.Write(word);
}
else
{
MyStreamWriter.Write(word.ToLower());
}
}
else
{
MyStreamWriter.Write(word);
}
MyStreamWriter.Write(ModifyDangerousSymbols(oneChar));
}
}
}
}
}
catch (System.Text.EncoderFallbackException)
{
}
}