Can anyone help me with this problem,
I have 2 textboxes in which i load 2 text files.
And now in the third textbox i need to display the word frequency ( the word and how many times is been used that word in those 2 texboxes). And finally calculating the Jaccard Coefficient which will show the similarities of the two text documents
Please if anyone can help me with this
Take a look at this thread - http://stackoverflow.com/questions/83777/are-there-any-fuzzy-search-or-string-similarity-functions-libraries-written-for-c
well i need specifically to use Jaccard's Coefficient for string similarities
public partial class Window1 : Window
{
public Window1()
{
InitializeComponent();
}
private void button1_Click(object sender, RoutedEventArgs e)
{
Microsoft.Win32.OpenFileDialog dlg = new Microsoft.Win32.OpenFileDialog();
dlg.FileName = "Document";
dlg.DefaultExt = ".txt";
dlg.Filter = "Text documents (.txt)|*.txt";
Nullable<bool> result = dlg.ShowDialog();
if (result == true)
{
StreamReader stReader = new StreamReader(dlg.FileName);
textBox2.Text = stReader.ReadToEnd();
}
}
private void button2_Click(object sender, RoutedEventArgs e)
{
Microsoft.Win32.OpenFileDialog dlg = new Microsoft.Win32.OpenFileDialog();
dlg.FileName = "Document";
dlg.DefaultExt = ".txt";
dlg.Filter = "Text documents (.txt)|*.txt";
Nullable<bool> result = dlg.ShowDialog();
if (result == true)
{
StreamReader stReader2 = new StreamReader(dlg.FileName);
textBox1.Text = stReader2.ReadToEnd();
}
}
private void button3_Click(object sender, RoutedEventArgs e)
{
StringBuilder str = new StringBuilder();
for(int a=0;a<textBox1.Text.Count();a++)
{
str.Append(textBox1.Text[a]);
}
string s = str.ToString();
ArrayList gatherSplit = new ArrayList(s.Split(new char[] { '\t', ' ', '.', ',', '?', '!', ':', ';' }));
HashSet<string> hs = new HashSet<string>();
for (int d = 0; d < gatherSplit.Count; d++)
{
hs.Add(gatherSplit[d].ToString());
}
ArrayList harr = new ArrayList();
for (int f = 0; f < hs.Count; f++)
{
harr.Insert(f, hs.ElementAt(f));
}
StringBuilder str1 = new StringBuilder();
for (int t = 0; t < textBox2.Text.Count(); t++)
{
str1.Append(textBox2.Text[t]);
}
string s1 = str1.ToString();
ArrayList gatherSplit1 = new ArrayList(s1.Split(new char[] { '\t', ' ', '.', ',', '?', '!', ':', ';' }));
HashSet<string> hs1 = new HashSet<string>();
for (int y = 0; y < gatherSplit1.Count; y++)
{
hs1.Add(gatherSplit1[y].ToString());
}
ArrayList harr1 = new ArrayList();
for (int f1 = 0; f1 < hs1.Count; f1++)
{
harr1.Insert(f1, hs1.ElementAt(f1));
}
HashSet<string> interhs = new HashSet<string>();
interhs = hs;
interhs.IntersectWith(hs1);
ArrayList wordfreq1 = new ArrayList();
for (int w = 0; w < interhs.Count; w++)
{
int z = 0;
for (int q = 0; q < gatherSplit.Count; q++)
{
if (interhs.ElementAt(w) == gatherSplit[q].ToString())
{
z += 1;
}
}
wordfreq1.Insert(w, z.ToString());
}
ArrayList wordfreq2 = new ArrayList();
for (int w1 = 0; w1 < interhs.Count; w1++)
{
int z = 0;
for (int q1 = 0; q1 < gatherSplit1.Count; q1++)
{
if (interhs.ElementAt(w1) == gatherSplit1[q1].ToString())
{
z += 1;
}
}
wordfreq2.Insert(w1, z.ToString());
}
for (int ty = 0; ty < wordfreq1.Count; ty++)
{
textBox3.AppendText(interhs.ElementAt(ty) + "\t\t" + wordfreq1[ty].ToString() + "\t\t"+wordfreq2[ty].ToString()+"\r\n");
}
double pprodq=0;
double x = 0;
double y1 = 0;
for(int pp=0;pp<wordfreq1.Count;pp++)
{
pprodq=pprodq+(Convert.ToDouble(wordfreq1[pp])* Convert.ToDouble(wordfreq2[pp]));
x = x + (Convert.ToDouble(wordfreq1[pp]) * Convert.ToDouble(wordfreq1[pp]));
y1 = y1 + (Convert.ToDouble(wordfreq2[pp]) * Convert.ToDouble(wordfreq2[pp]));
}
double jaccard = 0;
jaccard = pprodq / ((x + y1) - (pprodq));
textBox4.Text = jaccard.ToString();We're a friendly, industry-focused community of developers, IT pros, digital marketers, and technology enthusiasts meeting, networking, learning, and sharing knowledge.