/// <summary>
/// Uses the classifier to classify an instance (from its featureValues).
/// </summary>
/// <param name="featureValues">An array of doubles that describe the instance.</param>
/// <returns>The string name of the classification of the instance.</returns>
public string classify(double[] featureValues)
{
//if (!classifierBuilt) { _classifier.buildClassifier(_dataSet); classifierBuilt = true; }
weka.core.Instance inst = new weka.core.Instance(1, featureValues);
inst.setDataset(_dataSet);
double result = _classifier.classifyInstance(inst);
weka.core.Attribute attribute = _dataSet.attribute(_dataSet.numAttributes() - 1);
string resultName = attribute.value((int)result);
// Get rid of this line once ARFF files are rewritten
if (resultName == "Label")
{
resultName = "Text";
}
//Console.WriteLine(resultName);
return(resultName);
}
private void testButton_Click(object sender, EventArgs e)
{
var form = Form.ActiveForm as Form1;
if (readyToTest)
{
weka.classifiers.Classifier cl = classifiers[highestSuccessRate.Key];
weka.core.Instance inst = new weka.core.Instance(insts.numAttributes() - 1);
inst.setDataset(insts);
for (int i = 0; i < inputObjects.Count; i++)
{
if (inputObjects[i].numeric)
{
inst.setValue(i, Decimal.ToDouble(inputObjects[i].num.Value));
}
else
{
inst.setValue(i, inputObjects[i].nom.SelectedItem.ToString());
}
}
try
{
string[] values = insts.attribute(insts.numAttributes() - 1).toString().Split('{', '}')[1].Split(',');
double classOfData = cl.classifyInstance(inst);
int idx = Convert.ToInt32(classOfData);
form.testResult.Text = values[idx];
}
catch (Exception ex)
{
MessageBox.Show(ex.Message, "Error", MessageBoxButtons.OK, MessageBoxIcon.Error);
}
}
else
{
MessageBox.Show("Program is not ready to test, probably needs to process data first.", "Not ready", MessageBoxButtons.OK, MessageBoxIcon.Information);
}
}
/// <summary> Sets the format of the input instances.
///
/// </summary>
/// <param name="instanceInfo">an Instances object containing the input instance
/// structure (any instances contained in the object are ignored - only the
/// structure is required).
/// </param>
/// <exception cref="UnsupportedAttributeTypeException">if the specified attribute
/// is neither numeric or nominal.
/// </exception>
public override bool setInputFormat(Instances instanceInfo)
{
base.setInputFormat(instanceInfo);
m_AttIndex.Upper=instanceInfo.numAttributes() - 1;
if (!Numeric && !Nominal)
{
throw new Exception("Can only handle numeric " + "or nominal attributes.");
}
m_Values.Upper=instanceInfo.attribute(m_AttIndex.Index).numValues() - 1;
if (Nominal && m_ModifyHeader)
{
instanceInfo = new Instances(instanceInfo, 0); // copy before modifying
Attribute oldAtt = instanceInfo.attribute(m_AttIndex.Index);
int[] selection = m_Values.Selection;
FastVector newVals = new FastVector();
for (int i = 0; i < selection.Length; i++)
{
newVals.addElement(oldAtt.value_Renamed(selection[i]));
}
instanceInfo.deleteAttributeAt(m_AttIndex.Index);
instanceInfo.insertAttributeAt(new Attribute(oldAtt.name(), newVals), m_AttIndex.Index);
m_NominalMapping = new int[oldAtt.numValues()];
for (int i = 0; i < m_NominalMapping.Length; i++)
{
bool found = false;
for (int j = 0; j < selection.Length; j++)
{
if (selection[j] == i)
{
m_NominalMapping[i] = j;
found = true;
break;
}
}
if (!found)
{
m_NominalMapping[i] = - 1;
}
}
}
setOutputFormat(instanceInfo);
return true;
}
/// <summary> Gets an array containing the indices of all string attributes.
///
/// </summary>
/// <param name="insts">the Instances to scan for string attributes.
/// </param>
/// <returns> an array containing the indices of string attributes in
/// the input structure. Will be zero-length if there are no
/// string attributes
/// </returns>
protected internal virtual int[] getStringIndices(Instances insts)
{
// Scan through getting the indices of String attributes
int[] index = new int[insts.numAttributes()];
int indexSize = 0;
for (int i = 0; i < insts.numAttributes(); i++)
{
if (insts.attribute(i).type() == Attribute.STRING)
{
index[indexSize++] = i;
}
}
int[] result = new int[indexSize];
Array.Copy(index, 0, result, 0, indexSize);
return result;
}
/// <summary> Takes string values referenced by an Instance and copies them from a
/// source dataset to a destination dataset. The instance references are
/// updated to be valid for the destination dataset. The instance may have the
/// structure (i.e. number and attribute position) of either dataset (this
/// affects where references are obtained from). Only works if the number
/// of string attributes is the same in both indices (implicitly these string
/// attributes should be semantically same but just with shifted positions).
///
/// </summary>
/// <param name="instance">the instance containing references to strings in the source
/// dataset that will have references updated to be valid for the destination
/// dataset.
/// </param>
/// <param name="instSrcCompat">true if the instance structure is the same as the
/// source, or false if it is the same as the destination (i.e. which of the
/// string attribute indices contains the correct locations for this instance).
/// </param>
/// <param name="srcDataset">the dataset for which the current instance string
/// references are valid (after any position mapping if needed)
/// </param>
/// <param name="srcStrAtts">an array containing the indices of string attributes
/// in the source datset.
/// </param>
/// <param name="destDataset">the dataset for which the current instance string
/// references need to be inserted (after any position mapping if needed)
/// </param>
/// <param name="destStrAtts">an array containing the indices of string attributes
/// in the destination datset.
/// </param>
protected internal virtual void copyStringValues(Instance instance, bool instSrcCompat, Instances srcDataset, int[] srcStrAtts, Instances destDataset, int[] destStrAtts)
{
if (srcDataset == destDataset)
{
return ;
}
if (srcStrAtts.Length != destStrAtts.Length)
{
throw new System.ArgumentException("Src and Dest string indices differ in length!!");
}
for (int i = 0; i < srcStrAtts.Length; i++)
{
int instIndex = instSrcCompat?srcStrAtts[i]:destStrAtts[i];
Attribute src = srcDataset.attribute(srcStrAtts[i]);
Attribute dest = destDataset.attribute(destStrAtts[i]);
if (!instance.isMissing(instIndex))
{
//System.err.println(instance.value(srcIndex)
// + " " + src.numValues()
// + " " + dest.numValues());
//UPGRADE_WARNING: Data types in Visual C# might be different. Verify the accuracy of narrowing conversions. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1042'"
int valIndex = dest.addStringValue(src, (int) instance.value_Renamed(instIndex));
// setValue here shouldn't be too slow here unless your dataset has
// squillions of string attributes
instance.setValue(instIndex, (double) valIndex);
}
}
}
private void Classify(string path)
{
readyToTest = false; // initialize flag
// Try reading file, if failed exit function
insts = ReadFile(path);
if (insts == null)
{
// Error occured reading file, display error message
MessageBox.Show("Instances are null!", "Error", MessageBoxButtons.OK, MessageBoxIcon.Error);
return;
}
var form = Form.ActiveForm as Form1; // get the current form object
// Reset UI and lists
succesRates.Clear();
classifiers.Clear();
form.inputPanel.Controls.Clear();
inputObjects.Clear();
form.textMostSuccessful.Text = "";
form.testResult.Text = "";
// Place attribute inputs on UI, max 18, numeric and nominal
int offsetV = 60;
int offsetH = 10;
int width = 75;
int height = 30;
for (int i = 0; i < insts.numAttributes() - 1; i++)
{
// Create and place label
Label label = new Label();
label.Width = width;
label.Height = height;
label.Text = insts.attribute(i).name();
label.Parent = form.inputPanel;
label.Location = new Point((width * (i % 8)) + offsetH, (height * (i / 8)) + (offsetV * (i / 8)));
// NumericUpDown for numeric and ComboBox for nominal values
if (insts.attribute(i).isNumeric())
{
NumericUpDown nud = new NumericUpDown();
nud.Width = width - 10;
nud.Height = height;
nud.Parent = form.inputPanel;
nud.Location = new Point((width * (i % 8)) + offsetH, (height * (i / 8)) + (offsetV * (i / 8)) + height);
inputObjects.Add(new UserInput(nud));
}
else
{
string[] values = insts.attribute(i).toString().Split('{', '}')[1].Split(',');
ComboBox comboBox = new ComboBox();
comboBox.DataSource = values;
comboBox.Width = width - 10;
comboBox.Height = height;
comboBox.Parent = form.inputPanel;
comboBox.Location = new Point((width * (i % 8)) + offsetH, (height * (i / 8)) + (offsetV * (i / 8)) + height);
inputObjects.Add(new UserInput(comboBox));
}
}
// Set train and test sizes
trainSize = insts.numInstances() * percentSplit / 100;
testSize = insts.numInstances() - trainSize;
// Set target attribute
insts.setClassIndex(insts.numAttributes() - 1);
// Randomize
weka.filters.Filter rndFilter = new weka.filters.unsupervised.instance.Randomize();
rndFilter.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, rndFilter);
// Start threads for each method
Thread t_SuccessNb = new Thread(() => CalculateSuccessForNb(insts));
t_SuccessNb.Start();
Thread t_SuccessKn = new Thread(() => CalculateSuccessForKn(insts));
t_SuccessKn.Start();
Thread t_SuccessDt = new Thread(() => CalculateSuccessForDt(insts));
t_SuccessDt.Start();
Thread t_SuccessAnn = new Thread(() => CalculateSuccessForAnn(insts));
t_SuccessAnn.Start();
Thread t_SuccessSvm = new Thread(() => CalculateSuccessForSvm(insts));
t_SuccessSvm.Start();
// Wait for threads
t_SuccessNb.Join();
t_SuccessKn.Join();
t_SuccessDt.Join();
t_SuccessAnn.Join();
t_SuccessSvm.Join();
// Find out which algorithm has the best success rate
foreach (var item in succesRates)
{
if (highestSuccessRate.Equals(default(KeyValuePair <Classifier, double>)) || highestSuccessRate.Value < item.Value)
{
highestSuccessRate = item;
}
}
form.textMostSuccessful.Text = "Most successful algorithm is " + highestSuccessRate.Key + " and it will be used for testing.";
readyToTest = true; // switch flag
}
private void btnDiscover_Click(object sender, EventArgs e)
{
string type = model.GetType().ToString();
bool flag = false;
bool flag2 = false;
//input kontrolleri
if (nominal != null)
{
for (int i = 0; i < nominal.Length; i++)
{
if (nominal[i].SelectedIndex == -1)
{
flag = true;
break;
}
}
}
if (numeric != null)
{
for (int i = 0; i < numeric.Length; i++)
{
if (String.IsNullOrEmpty(numeric[i].Text))
{
flag2 = true;
break;
}
}
}
if (numAtt == numeric.Length && flag2 == true)
{
MessageBox.Show("Please select value!", "Error Message!");
}
else if (numAtt == nominal.Length && flag == true)
{
MessageBox.Show("Please select value!", "Error Message!");
}
else if ((nominal.Length + numeric.Length) == numAtt && (flag == true || flag2 == true))
{
MessageBox.Show("Please select value!", "Error Message!");
}
else
{
weka.core.Instance newIns = new weka.core.Instance(numAtt + 1);
newIns.setDataset(insts);
int i1 = 0, i2 = 0;
for (int i = 0; i < numAtt; i++)
{
//nominal
if (typeAtt[i])
{
newIns.setValue(i, nominal[i1].SelectedItem.ToString());
i1++;
}
//numeric
else
{
newIns.setValue(i, double.Parse(numeric[i2].Text));
i2++;
}
}
weka.core.Instances insts2 = new weka.core.Instances(insts);
insts2.add(newIns);
if (type == "weka.classifiers.bayes.NaiveBayes")
{
weka.filters.Filter myDiscretize = new weka.filters.unsupervised.attribute.Discretize();
myDiscretize.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, myDiscretize);
}
else if (type == "weka.classifiers.functions.Logistic")
{
weka.filters.Filter myDummy = new weka.filters.unsupervised.attribute.NominalToBinary();
myDummy.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, myDummy);
weka.filters.Filter myNormalize = new weka.filters.unsupervised.instance.Normalize();
myNormalize.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, myNormalize);
}
else if (type == "new weka.classifiers.lazy.IBk")
{
weka.filters.Filter myDummy = new weka.filters.unsupervised.attribute.NominalToBinary();
myDummy.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, myDummy);
weka.filters.Filter myNormalize = new weka.filters.unsupervised.instance.Normalize();
myNormalize.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, myNormalize);
}
else if (type == "weka.classifiers.trees.J48")
{
}
else if (type == "weka.classifiers.trees.RandomForest")
{
}
else if (type == "weka.classifiers.trees.RandomTree")
{
}
else if (type == "weka.classifiers.functions.MultilayerPerceptron")
{
weka.filters.Filter myDummy = new weka.filters.unsupervised.attribute.NominalToBinary();
myDummy.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, myDummy);
weka.filters.Filter myNormalize = new weka.filters.unsupervised.instance.Normalize();
myNormalize.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, myNormalize);
}
else if (type == "weka.classifiers.functions.SMO")
{
weka.filters.Filter myDummy = new weka.filters.unsupervised.attribute.NominalToBinary();
myDummy.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, myDummy);
weka.filters.Filter myNormalize = new weka.filters.unsupervised.instance.Normalize();
myNormalize.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, myNormalize);
}
double index = model.classifyInstance(insts2.lastInstance());
//Model okuma kısmı
weka.classifiers.Classifier cls = (weka.classifiers.Classifier)weka.core.SerializationHelper.read("models/mdl.model");
lblResult2.Text = "Result= " + insts2.attribute(insts2.numAttributes() - 1).value(Convert.ToInt16(index));
}
}
private void btnBrowse_Click(object sender, EventArgs e)
{
panel1.Controls.Clear();
panel2.Controls.Clear();
testValues = new List <object>();
classes = new List <string>();
algoritmName = String.Empty;
SuccessfulAlgorithm = new List <AlgorithmModel>();
labelNames = new List <string>();
DialogResult result = openFileDialog.ShowDialog();
if (result == DialogResult.OK)
{
txtPath.Text = openFileDialog.FileName;
}
staticInsts = new weka.core.Instances(new java.io.FileReader(txtPath.Text));
for (int i = 0; i < staticInsts.attribute(staticInsts.numAttributes() - 1).numValues(); i++)
{
classes.Add(staticInsts.attribute(staticInsts.numAttributes() - 1).value(i));
}
AlgoritmAccurancy(staticInsts, new weka.classifiers.bayes.NaiveBayes(), "Naive Bayes", true);
AlgoritmAccurancy(staticInsts, new weka.classifiers.lazy.IBk(3), "KNN with k = 3", false);
AlgoritmAccurancy(staticInsts, new weka.classifiers.trees.RandomForest(), "Random Forest");
AlgoritmAccurancy(staticInsts, new weka.classifiers.trees.RandomTree(), "Random Tree");
AlgoritmAccurancy(staticInsts, new weka.classifiers.trees.J48(), "J48");
pointY = 20;
pointX = 20;
for (int i = 0; i < staticInsts.numAttributes() - 1; i++)
{
if (staticInsts.attribute(i).numValues() == 0)
{
pointX = 0;
string attName = staticInsts.attribute(i).name(); // Bunlar numeric textbox aç
Label attributeName = new Label();
attributeName.Size = new Size(70, 20);
attributeName.Text = attName + "\t :";
labelNames.Add(attributeName.Text);
attributeName.Location = new Point(pointX, pointY);
panel1.Controls.Add(attributeName);
pointX += 70;
TextBox txtValue = new TextBox();
txtValue.Location = new Point(pointX, pointY);
panel1.Controls.Add(txtValue);
panel1.Show();
pointY += 30;
testValues.Add(txtValue);
}
else
{
pointX = 0;
string attName = staticInsts.attribute(i).name(); // Bunlar numeric textbox aç
Label attributeName = new Label();
attributeName.Size = new Size(70, 20);
attributeName.Text = attName + "\t :";
labelNames.Add(attributeName.Text);
attributeName.Location = new Point(pointX, pointY);
panel1.Controls.Add(attributeName);
pointX += 70;
ComboBox cb = new ComboBox();
cb.DropDownStyle = ComboBoxStyle.DropDownList;
cb.Location = new Point(pointX, pointY);
List <string> items = new List <string>();
for (int j = 0; j < staticInsts.attribute(i).numValues(); j++)
{
items.Add(staticInsts.attribute(i).value(j).ToString()); // Bu gelen valueları dropdowna koy
}
cb.Items.AddRange(items.ToArray());
cb.SelectedIndex = 0;
panel1.Controls.Add(cb);
panel1.Show();
pointY += 30;
testValues.Add(cb);
}
}
double maxRatio = Double.MinValue;
foreach (var item in SuccessfulAlgorithm)
{
if (item.SuccessRatio > maxRatio)
{
maxRatio = item.SuccessRatio;
algoritmName = item.AlgorithName;
predictor = item.TrainModel.classifier;
}
}
string _maxRatio = string.Format("{0:0.00}", maxRatio);
lblSuccessulAlgorithm.Text = "The most Successful Algoritm is " + algoritmName + " and the ratio of accurancy is %" + _maxRatio;
Button btn = new Button();
btn.Click += Btn_Click;
btn.Location = new Point(pointX, pointY);
btn.Size = new Size(80, 20);
btn.Text = "DISCOVER";
btn.BackColor = Color.White;
panel1.Controls.Add(btn);
panel1.Show();
}
/// <summary> Sets the format of the input instances.
///
/// </summary>
/// <param name="instanceInfo">an Instances object containing the input instance
/// structure (any instances contained in the object are ignored - only the
/// structure is required).
/// </param>
/// <returns> true if the outputFormat may be collected immediately
/// </returns>
/// <exception cref="Exception">if the format couldn't be set successfully
/// </exception>
public override bool setInputFormat(Instances instanceInfo)
{
base.setInputFormat(instanceInfo);
m_SelectCols.Upper = instanceInfo.numAttributes() - 1;
// Create the output buffer
FastVector attributes = new FastVector();
int outputClass = - 1;
m_SelectedAttributes = m_SelectCols.Selection;
int inStrKeepLen = 0;
int[] inStrKeep = new int[m_SelectedAttributes.Length];
for (int i = 0; i < m_SelectedAttributes.Length; i++)
{
int current = m_SelectedAttributes[i];
if (instanceInfo.classIndex() == current)
{
outputClass = attributes.size();
}
Attribute keep = (Attribute) instanceInfo.attribute(current).copy();
if (keep.type() == Attribute.STRING)
{
inStrKeep[inStrKeepLen++] = current;
}
attributes.addElement(keep);
}
m_InputStringIndex = new int[inStrKeepLen];
Array.Copy(inStrKeep, 0, m_InputStringIndex, 0, inStrKeepLen);
Instances outputFormat = new Instances(instanceInfo.relationName(), attributes, 0);
outputFormat.ClassIndex = outputClass;
setOutputFormat(outputFormat);
return true;
}
//Dosya seçim bölümü ve yüzde hesabı bölümü
private void btnBrowse_Click(object sender, EventArgs e)
{
clears();
OpenFileDialog file = new OpenFileDialog();
file.Filter = "Files (ARFF)|*.ARFF";
file.Multiselect = false;
file.Title = "Please select a dataset file!";
if (file.ShowDialog() == DialogResult.OK)
{
txtPath.Text = file.FileName;
fileName = file.SafeFileName;
//dosya seçildikten sonra işlemi gerçekleştiriyor.
try
{
if (txtPath.Text.Length < 1)
{
MessageBox.Show("Please select file!", "Error Message!");
txtPath.Text = "";
}
else
{
this.Text = "Processing...";
insts = new weka.core.Instances(new java.io.FileReader(txtPath.Text));
//naive bayes
double max_value = NaiveBayesTest(insts);
model = NaiveBayescl;
name = "Naïve Bayes";
//logistic regression
double LogRegressionvalue = LogRegressionTest(insts);
if (LogRegressionvalue > max_value)
{
max_value = LogRegressionvalue;
model = LogRegressioncl;
name = "Logistic Regression";
}
//knn
double KnnValue = Knn(insts);
if (KnnValue > max_value)
{
max_value = KnnValue;
model = Knncl;
name = "K-Nearest Neighbour";
}
//J48
double J48Value = J48classifyTest(insts);
if (J48Value > max_value)
{
max_value = J48Value;
model = J48cl;
name = "Decision Tree(J48)";
}
//Random forest
double RFvalue = RandomForestTest(insts);
if (RFvalue > max_value)
{
max_value = RFvalue;
model = RandomForestcl;
name = "Decision Tree(Random Forest)";
}
//Random Tree
double RTvalue = RandomTreeTest(insts);
if (RTvalue > max_value)
{
max_value = RTvalue;
model = RandomTreecl;
name = "Decision Tree(Random Tree)";
}
//Artificial nn
double AnnValue = ArtificialNN(insts);
if (AnnValue > max_value)
{
max_value = AnnValue;
model = Anncl;
name = "Artificial Neural Network";
}
//Svm
double SvmValue = SVM(insts);
if (SvmValue > max_value)
{
max_value = SvmValue;
model = Svmcl;
name = "Support Vector Machine";
}
//Model kaydetme kısmı
weka.core.SerializationHelper.write("models/mdl.model", model);
lblResult.Text = name + " is the most successful algorithm for this data set (%" + string.Format("{0:0.00}", max_value) + ")";
this.Text = "DEUCENG - ML Classification Tool";
//seçme işlemleri
numAtt = insts.numAttributes() - 1;
int x = 30, y = 130, t = 35, l = 110;
int txt = 0, cmb = 0, r1 = 0, r2 = 0;
labels = new Label[insts.numAttributes()];
for (int i = 0; i < numAtt; i++)
{
if (insts.attribute(i).isNumeric())
{
txt++;
}
else if (insts.attribute(i).isNominal())
{
cmb++;
}
}
nominal = new ComboBox[cmb];
numeric = new TextBox[txt];
typeAtt = new bool[numAtt];
this.Height += (numAtt + 1) * t;
for (int i = 0; i < numAtt; i++)
{
if (insts.attribute(i).isNominal())
{
string[] s1 = insts.attribute(i).toString().Split('{');
string[] s2 = s1[1].Split('}');
string[] s3 = s2[0].Split(',');
nominal[r1] = new ComboBox();
labels[i] = new Label();
for (int j = 0; j < s3.Length; j++)
{
nominal[r1].Items.Add(s3[j].Replace('\'', ' ').Trim());
}
labels[i].Text = insts.attribute(i).name();
labels[i].Left = x;
labels[i].Top = y;
nominal[r1].Left = x + l;
nominal[r1].Top = y;
nominal[r1].DropDownStyle = ComboBoxStyle.DropDownList;
y += t;
Controls.Add(nominal[r1]);
Controls.Add(labels[i]);
r1++;
typeAtt[i] = true;
}
else if (insts.attribute(i).isNumeric())
{
numeric[r2] = new TextBox();
labels[i] = new Label();
labels[i].Text = insts.attribute(i).name();
labels[i].Left = x;
labels[i].Top = y;
numeric[r2].Left = x + l;
numeric[r2].Top = y;
y += t;
Controls.Add(numeric[r2]);
Controls.Add(labels[i]);
r2++;
typeAtt[i] = false;
}
btnDiscover.Enabled = true;
}
}
}
catch (Exception e2)
{
MessageBox.Show(e2.Message, "Error Message!");
}
}
}
private void button1_Click(object sender, EventArgs e)
{
OpenFileDialog file = new OpenFileDialog();
if (file.ShowDialog() == DialogResult.OK)
{
string filename = file.FileName;
string filee = Path.GetFileName(filename);
bool attributeType;
string attributeName = " ";
int numAttributeValue = 0;
string attributeValueName = " ";
textBox1.Text = filee + " chosen succesfully!";
///////Decision Tree
weka.core.Instances insts = new weka.core.Instances(new java.io.FileReader(filename));
insts.setClassIndex(insts.numAttributes() - 1);
//find nominal or numeric attributes and create dropbox or textbox
int numofAttributes = insts.numAttributes() - 1;
for (int i = 0; i < numofAttributes; i++)
{
attributeType = insts.attribute(i).isNumeric();
attributeName = insts.attribute(i).name();
dataGridView1.Rows.Add(attributeName);
if (attributeType == true)
{
}
else
{
numAttributeValue = insts.attribute(i).numValues();
string[] name = new string[numAttributeValue];
for (int j = 0; j < numAttributeValue; j++)
{
attributeValueName = insts.attribute(i).value(j);
name[j] += attributeValueName;
}
DataGridViewComboBoxCell combo = new DataGridViewComboBoxCell();
combo.DataSource = name.ToList();
dataGridView1.Rows[i].Cells[1] = combo;
}
}
cl = new weka.classifiers.trees.J48();
textBox2.Text = "Performing " + percentSplit + "% split evaluation.";
//filling missing values
weka.filters.Filter missingval = new weka.filters.unsupervised.attribute.ReplaceMissingValues();
missingval.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, missingval);
weka.filters.Filter myNormalized = new weka.filters.unsupervised.instance.Normalize();
myNormalized.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myNormalized);
//randomize the order of the instances in the dataset.
weka.filters.Filter myRandom = new weka.filters.unsupervised.instance.Randomize();
myRandom.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myRandom);
int trainSize = insts.numInstances() * percentSplit / 100;
int testSize = insts.numInstances() - trainSize;
weka.core.Instances train = new weka.core.Instances(insts, 0, trainSize);
cl.buildClassifier(train);
string str = cl.toString();
int numCorrect = 0;
for (int i = trainSize; i < insts.numInstances(); i++)
{
weka.core.Instance currentInst = insts.instance(i);
double predictedClass = cl.classifyInstance(currentInst);
if (predictedClass == insts.instance(i).classValue())
{
numCorrect++;
}
}
textBox3.Text = numCorrect + " out of " + testSize + " correct (" +
(double)((double)numCorrect / (double)testSize * 100.0) + "%)";
//////////Naive Bayes
//dosya okuma
weka.core.Instances insts2 = new weka.core.Instances(new java.io.FileReader(filename));
insts2.setClassIndex(insts2.numAttributes() - 1);
//naive bayes
cl2 = new weka.classifiers.bayes.NaiveBayes();
//filling missing values
weka.filters.Filter missingval2 = new weka.filters.unsupervised.attribute.ReplaceMissingValues();
missingval2.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, missingval2);
//for naive bayes
weka.filters.Filter discrete2 = new weka.filters.unsupervised.attribute.Discretize();
discrete2.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, discrete2);
//randomize the order of the instances in the dataset. -ortak
weka.filters.Filter myRandom2 = new weka.filters.unsupervised.instance.Randomize();
myRandom2.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, myRandom2);
//ortak
int trainSize2 = insts2.numInstances() * percentSplit / 100;
int testSize2 = insts2.numInstances() - trainSize2;
weka.core.Instances train2 = new weka.core.Instances(insts2, 0, trainSize2);
cl2.buildClassifier(train2);
string str2 = cl2.toString();
int numCorrect2 = 0;
for (int i = trainSize2; i < insts2.numInstances(); i++)
{
weka.core.Instance currentInst2 = insts2.instance(i);
double predictedClass2 = cl2.classifyInstance(currentInst2);
if (predictedClass2 == insts2.instance(i).classValue())
{
numCorrect2++;
}
}
textBox4.Text = numCorrect2 + " out of " + testSize2 + " correct (" +
(double)((double)numCorrect2 / (double)testSize2 * 100.0) + "%)";
/////////K-Nearest Neigbour
//dosya okuma
weka.core.Instances insts3 = new weka.core.Instances(new java.io.FileReader(filename));
insts3.setClassIndex(insts3.numAttributes() - 1);
cl3 = new weka.classifiers.lazy.IBk();
//filling missing values
weka.filters.Filter missingval3 = new weka.filters.unsupervised.attribute.ReplaceMissingValues();
missingval3.setInputFormat(insts3);
insts3 = weka.filters.Filter.useFilter(insts3, missingval3);
//Convert to dummy attribute knn,svm,neural network
weka.filters.Filter dummy3 = new weka.filters.unsupervised.attribute.NominalToBinary();
dummy3.setInputFormat(insts3);
insts3 = weka.filters.Filter.useFilter(insts3, dummy3);
//normalize numeric attribute
weka.filters.Filter myNormalized3 = new weka.filters.unsupervised.instance.Normalize();
myNormalized3.setInputFormat(insts3);
insts3 = weka.filters.Filter.useFilter(insts3, myNormalized3);
//randomize the order of the instances in the dataset.
weka.filters.Filter myRandom3 = new weka.filters.unsupervised.instance.Randomize();
myRandom3.setInputFormat(insts3);
insts3 = weka.filters.Filter.useFilter(insts3, myRandom3);
int trainSize3 = insts3.numInstances() * percentSplit / 100;
int testSize3 = insts3.numInstances() - trainSize3;
weka.core.Instances train3 = new weka.core.Instances(insts3, 0, trainSize3);
cl3.buildClassifier(train3);
string str3 = cl3.toString();
int numCorrect3 = 0;
for (int i = trainSize3; i < insts3.numInstances(); i++)
{
weka.core.Instance currentInst3 = insts3.instance(i);
double predictedClass3 = cl3.classifyInstance(currentInst3);
if (predictedClass3 == insts3.instance(i).classValue())
{
numCorrect3++;
}
}
textBox5.Text = numCorrect3 + " out of " + testSize3 + " correct (" +
(double)((double)numCorrect3 / (double)testSize3 * 100.0) + "%)";
//////////Artificial neural network
//dosya okuma
weka.core.Instances insts4 = new weka.core.Instances(new java.io.FileReader(filename));
insts4.setClassIndex(insts4.numAttributes() - 1);
cl4 = new weka.classifiers.functions.MultilayerPerceptron();
//filling missing values
weka.filters.Filter missingval4 = new weka.filters.unsupervised.attribute.ReplaceMissingValues();
missingval4.setInputFormat(insts4);
insts4 = weka.filters.Filter.useFilter(insts4, missingval4);
//Convert to dummy attribute
weka.filters.Filter dummy4 = new weka.filters.unsupervised.attribute.NominalToBinary();
dummy4.setInputFormat(insts4);
insts4 = weka.filters.Filter.useFilter(insts4, dummy4);
//normalize numeric attribute
weka.filters.Filter myNormalized4 = new weka.filters.unsupervised.instance.Normalize();
myNormalized4.setInputFormat(insts4);
insts4 = weka.filters.Filter.useFilter(insts4, myNormalized4);
//randomize the order of the instances in the dataset.
weka.filters.Filter myRandom4 = new weka.filters.unsupervised.instance.Randomize();
myRandom4.setInputFormat(insts4);
insts4 = weka.filters.Filter.useFilter(insts4, myRandom4);
int trainSize4 = insts4.numInstances() * percentSplit / 100;
int testSize4 = insts4.numInstances() - trainSize4;
weka.core.Instances train4 = new weka.core.Instances(insts4, 0, trainSize4);
cl4.buildClassifier(train4);
string str4 = cl4.toString();
int numCorrect4 = 0;
for (int i = trainSize4; i < insts4.numInstances(); i++)
{
weka.core.Instance currentInst4 = insts4.instance(i);
double predictedClass4 = cl4.classifyInstance(currentInst4);
if (predictedClass4 == insts4.instance(i).classValue())
{
numCorrect4++;
}
}
textBox6.Text = numCorrect4 + " out of " + testSize4 + " correct (" +
(double)((double)numCorrect4 / (double)testSize4 * 100.0) + "%)";
///////Support Vector Machine
// dosya okuma
weka.core.Instances insts5 = new weka.core.Instances(new java.io.FileReader(filename));
insts5.setClassIndex(insts5.numAttributes() - 1);
cl5 = new weka.classifiers.functions.SMO();
//filling missing values
weka.filters.Filter missingval5 = new weka.filters.unsupervised.attribute.ReplaceMissingValues();
missingval5.setInputFormat(insts5);
insts5 = weka.filters.Filter.useFilter(insts5, missingval5);
//Convert to dummy attribute
weka.filters.Filter dummy5 = new weka.filters.unsupervised.attribute.NominalToBinary();
dummy5.setInputFormat(insts5);
insts5 = weka.filters.Filter.useFilter(insts5, dummy5);
//normalize numeric attribute
weka.filters.Filter myNormalized5 = new weka.filters.unsupervised.instance.Normalize();
myNormalized5.setInputFormat(insts5);
insts5 = weka.filters.Filter.useFilter(insts5, myNormalized5);
//randomize the order of the instances in the dataset.
weka.filters.Filter myRandom5 = new weka.filters.unsupervised.instance.Randomize();
myRandom5.setInputFormat(insts5);
insts5 = weka.filters.Filter.useFilter(insts5, myRandom5);
int trainSize5 = insts5.numInstances() * percentSplit / 100;
int testSize5 = insts5.numInstances() - trainSize5;
weka.core.Instances train5 = new weka.core.Instances(insts5, 0, trainSize5);
cl5.buildClassifier(train5);
string str5 = cl5.toString();
int numCorrect5 = 0;
for (int i = trainSize5; i < insts5.numInstances(); i++)
{
weka.core.Instance currentInst5 = insts5.instance(i);
double predictedClass5 = cl5.classifyInstance(currentInst5);
if (predictedClass5 == insts5.instance(i).classValue())
{
numCorrect5++;
}
}
textBox7.Text = numCorrect5 + " out of " + testSize5 + " correct (" +
(double)((double)numCorrect5 / (double)testSize5 * 100.0) + "%)";
string result1 = textBox3.Text;
string output1 = result1.Split('(', ')')[1];
output1 = output1.Remove(output1.Length - 1);
double r1 = Convert.ToDouble(output1);
string result2 = textBox4.Text;
string output2 = result2.Split('(', ')')[1];
output2 = output2.Remove(output2.Length - 1);
double r2 = Convert.ToDouble(output2);
string result3 = textBox5.Text;
string output3 = result3.Split('(', ')')[1];
output3 = output3.Remove(output3.Length - 1);
double r3 = Convert.ToDouble(output3);
string result4 = textBox6.Text;
string output4 = result4.Split('(', ')')[1];
output4 = output4.Remove(output4.Length - 1);
double r4 = Convert.ToDouble(output4);
string result5 = textBox7.Text;
string output5 = result5.Split('(', ')')[1];
output5 = output5.Remove(output5.Length - 1);
double r5 = Convert.ToDouble(output5);
double[] max_array = new double[] { r1, r2, r3, r4, r5 };
double max = max_array.Max();
if (r1 == max)
{
textBox8.Text = "Best Algoritm is Decision Tree Algorithm ";
}
else if (r2 == max)
{
textBox8.Text = "Best Algoritm is Naive Bayes Algorithm ";
}
else if (r3 == max)
{
textBox8.Text = "Best Algoritm is K-Nearest Neighbour Algorithm ";
}
else if (r4 == max)
{
textBox8.Text = "Best Algoritm is Artificial Neural Network Algorithm ";
}
else if (r5 == max)
{
textBox8.Text = "Best Algoritm is Support Vector Machine Algorithm ";
}
}
}
public bool PrepareDataset()
{
try
{
weka.filters.Filter missingFilter = new weka.filters.unsupervised.attribute.ReplaceMissingValues(); // missing values handled
missingFilter.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, missingFilter);
bool isTargetNumeric = insts.attribute(insts.numAttributes() - 1).isNumeric();
List <bool> isNumeric = new List <bool>();
List <bool> is2Categorical = new List <bool>();
List <List <string> > numericColumns = new List <List <string> >();
List <string> atrNames = new List <string>();
for (int i = 0; i < insts.numAttributes(); i++)
{
atrNames.Add(insts.attribute(i).name());
bool isNum = insts.attribute(i).isNumeric();
isNumeric.Add(isNum);
if (isNum == true)
{
numericColumns.Add(new List <string>());
for (int j = 0; j < insts.numInstances(); j++)
{
numericColumns[numericColumns.Count - 1].Add(insts.instance(j).toString(i));
}
}
}
weka.filters.unsupervised.attribute.Discretize myDiscretize = new weka.filters.unsupervised.attribute.Discretize();
myDiscretize.setInputFormat(insts);
myDiscretize.setFindNumBins(true);
insts = weka.filters.Filter.useFilter(insts, myDiscretize);
List <List <string> > atrs = new List <List <string> >();
for (int i = 0; i < insts.numAttributes(); i++)
{
atrs.Add(new List <string>());
for (int j = 0; j < insts.attribute(i).numValues(); j++)
{
string sub_category = insts.attribute(i).value(j);
string temp = sub_category.Replace("'", string.Empty);
atrs[atrs.Count - 1].Add(temp);
}
if (atrs[atrs.Count - 1].Count == 2)
{
is2Categorical.Add(true);
}
else
{
is2Categorical.Add(false);
}
}
List <List <string> > lst = new List <List <string> >();
for (int i = 0; i < insts.numInstances(); i++)
{
lst.Add(new List <string>());
for (int j = 0; j < insts.instance(i).numValues(); j++)
{
string temp = insts.instance(i).toString(j);
temp = temp.Replace("\\", string.Empty);
temp = temp.Replace("'", string.Empty);
lst[lst.Count - 1].Add(temp);
}
}
List <string> targetValues = atrs[insts.numAttributes() - 1];
List <List <string> > giniDataset = ConvertToNumericWithGini(lst, atrs);
giniDataset = Arrange2CategoricalColumns(giniDataset, lst, is2Categorical);
giniDataset = ChangeBackNumericalColumns(giniDataset, numericColumns, isNumeric);
WriteFile(giniDataset, filename + "-numeric-gini.arff", atrNames, targetValues, isTargetNumeric);
List <List <string> > twoingDataset = ConvertToNumericWithTwoing(lst, atrs);
twoingDataset = Arrange2CategoricalColumns(twoingDataset, lst, is2Categorical);
twoingDataset = ChangeBackNumericalColumns(twoingDataset, numericColumns, isNumeric);
WriteFile(twoingDataset, filename + "-numeric-twoing.arff", atrNames, targetValues, isTargetNumeric);
return(true);
}
catch (Exception e)
{
return(false);
}
}
/// <summary> Calculates the area under the ROC curve. This is normalised so
/// that 0.5 is random, 1.0 is perfect and 0.0 is bizarre.
///
/// </summary>
/// <param name="tcurve">a previously extracted threshold curve Instances.
/// </param>
/// <returns> the ROC area, or Double.NaN if you don't pass in
/// a ThresholdCurve generated Instances.
/// </returns>
public static double getROCArea(Instances tcurve)
{
//UPGRADE_NOTE: Final was removed from the declaration of 'n '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
int n = tcurve.numInstances();
if (!RELATION_NAME.Equals(tcurve.relationName()) || (n == 0))
{
return System.Double.NaN;
}
//UPGRADE_NOTE: Final was removed from the declaration of 'tpInd '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
int tpInd = tcurve.attribute(TRUE_POS_NAME).index();
//UPGRADE_NOTE: Final was removed from the declaration of 'fpInd '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
int fpInd = tcurve.attribute(FALSE_POS_NAME).index();
//UPGRADE_NOTE: Final was removed from the declaration of 'tpVals '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double[] tpVals = tcurve.attributeToDoubleArray(tpInd);
//UPGRADE_NOTE: Final was removed from the declaration of 'fpVals '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double[] fpVals = tcurve.attributeToDoubleArray(fpInd);
//UPGRADE_NOTE: Final was removed from the declaration of 'tp0 '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double tp0 = tpVals[0];
//UPGRADE_NOTE: Final was removed from the declaration of 'fp0 '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double fp0 = fpVals[0];
double area = 0.0;
//starts at high values and goes down
double xlast = 1.0;
double ylast = 1.0;
for (int i = 1; i < n; i++)
{
//UPGRADE_NOTE: Final was removed from the declaration of 'x '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double x = fpVals[i] / fp0;
//UPGRADE_NOTE: Final was removed from the declaration of 'y '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double y = tpVals[i] / tp0;
//UPGRADE_NOTE: Final was removed from the declaration of 'areaDelta '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double areaDelta = (y + ylast) * (xlast - x) / 2.0;
/*
System.err.println("[" + i + "]"
+ " x=" + x
+ " y'=" + y
+ " xl=" + xlast
+ " yl=" + ylast
+ " a'=" + areaDelta);
*/
area += areaDelta;
xlast = x;
ylast = y;
}
//make sure ends at 0,0
if (xlast > 0.0)
{
//UPGRADE_NOTE: Final was removed from the declaration of 'areaDelta '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double areaDelta = ylast * xlast / 2.0;
//System.err.println(" a'=" + areaDelta);
area += areaDelta;
}
//System.err.println(" area'=" + area);
return area;
}
/// <summary> Calculates the n point precision result, which is the precision averaged
/// over n evenly spaced (w.r.t recall) samples of the curve.
///
/// </summary>
/// <param name="tcurve">a previously extracted threshold curve Instances.
/// </param>
/// <param name="n">the number of points to average over.
/// </param>
/// <returns> the n-point precision.
/// </returns>
public static double getNPointPrecision(Instances tcurve, int n)
{
if (!RELATION_NAME.Equals(tcurve.relationName()) || (tcurve.numInstances() == 0))
{
return System.Double.NaN;
}
int recallInd = tcurve.attribute(RECALL_NAME).index();
int precisInd = tcurve.attribute(PRECISION_NAME).index();
double[] recallVals = tcurve.attributeToDoubleArray(recallInd);
int[] sorted = Utils.sort(recallVals);
double isize = 1.0 / (n - 1);
double psum = 0;
for (int i = 0; i < n; i++)
{
int pos = binarySearch(sorted, recallVals, i * isize);
double recall = recallVals[sorted[pos]];
double precis = tcurve.instance(sorted[pos]).value_Renamed(precisInd);
/*
System.err.println("Point " + (i + 1) + ": i=" + pos
+ " r=" + (i * isize)
+ " p'=" + precis
+ " r'=" + recall);
*/
// interpolate figures for non-endpoints
while ((pos != 0) && (pos < sorted.Length - 1))
{
pos++;
double recall2 = recallVals[sorted[pos]];
if (recall2 != recall)
{
double precis2 = tcurve.instance(sorted[pos]).value_Renamed(precisInd);
double slope = (precis2 - precis) / (recall2 - recall);
double offset = precis - recall * slope;
precis = isize * i * slope + offset;
/*
System.err.println("Point2 " + (i + 1) + ": i=" + pos
+ " r=" + (i * isize)
+ " p'=" + precis2
+ " r'=" + recall2
+ " p''=" + precis);
*/
break;
}
}
psum += precis;
}
return psum / n;
}
private void result_Click(object sender, EventArgs e)
{
ArrayList algorithms = new ArrayList();
algorithms.Add("Naive Bayes");
algorithms.Add("K Nearest Neighbor");
algorithms.Add("Decision Tree");
algorithms.Add("Neural Network");
algorithms.Add("Support Vector Machine");
ArrayList successPercent = new ArrayList();
double res_Naive, res_KNN, res_NN, res_Tree, res_SVM = 0.0;
string nameOfAlgo = "";
//NAIVE BAYES ALGORITHM
weka.core.Instances insts = new weka.core.Instances(new java.io.FileReader(fileDirectory));
//CREATIING DYNAMIC GRIDVIEW FOR ADDING NEW INSTANCE
dataGridView1.ColumnCount = 2;
dataGridView1.RowCount = insts.numAttributes();
String[,] matrixOfInstances = new String[insts.numInstances(), insts.numAttributes()];
for (int y = 0; y < insts.numAttributes() - 1; y++)
{
dataGridView1.Rows[y].Cells[0].Value = insts.attribute(y).name();
if (insts.attribute(y).isNominal())
{
//nominalDataValues.Add(insts.attribute(y).toString());
string phrase = insts.attribute(y).toString();
string[] first = phrase.Split('{');
string[] second = first[1].Split('}');
string[] attributeValues = second[0].Split(',');
DataGridViewComboBoxCell comboColumn = new DataGridViewComboBoxCell();
foreach (var a in attributeValues)
{
comboColumn.Items.Add(a);
}
dataGridView1.Rows[y].Cells[1] = comboColumn;
}
}
insts.setClassIndex(insts.numAttributes() - 1);
cl_Naive = new weka.classifiers.bayes.NaiveBayes();
weka.filters.Filter myNominalData = new weka.filters.unsupervised.attribute.Discretize();
myNominalData.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myNominalData);
//randomize the order of the instances in the dataset.
weka.filters.Filter myRandom = new weka.filters.unsupervised.instance.Randomize();
myRandom.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myRandom);
int trainSize = insts.numInstances() * percentSplit / 100;
int testSize = insts.numInstances() - trainSize;
weka.core.Instances train = new weka.core.Instances(insts, 0, trainSize);
cl_Naive.buildClassifier(train);
string str = cl_Naive.toString();
int numCorrect = 0;
for (int i = trainSize; i < insts.numInstances(); i++)
{
weka.core.Instance currentInst = insts.instance(i);
double predictedClass = cl_Naive.classifyInstance(currentInst);
if (predictedClass == insts.instance(i).classValue())
{
numCorrect++;
}
}
res_Naive = (double)((double)numCorrect / (double)testSize * 100.0);
successPercent.Add(res_Naive);
//kNN
weka.core.Instances insts2 = new weka.core.Instances(new java.io.FileReader(fileDirectory));
insts2.setClassIndex(insts2.numAttributes() - 1);
cl_Knn = new weka.classifiers.lazy.IBk();
//Nominal to Binary
weka.filters.Filter myBinaryData = new weka.filters.unsupervised.attribute.NominalToBinary();
myBinaryData.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, myBinaryData);
//Normalization
weka.filters.Filter myNormalized = new weka.filters.unsupervised.instance.Normalize();
myNormalized.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, myNormalized);
//randomize the order of the instances in the dataset.
weka.filters.Filter myRandom2 = new weka.filters.unsupervised.instance.Randomize();
myRandom2.setInputFormat(insts2);
insts2 = weka.filters.Filter.useFilter(insts2, myRandom2);
int trainSize2 = insts2.numInstances() * percentSplit / 100;
int testSize2 = insts2.numInstances() - trainSize2;
weka.core.Instances train2 = new weka.core.Instances(insts2, 0, trainSize2);
cl_Knn.buildClassifier(train2);
string str2 = cl_Knn.toString();
int numCorrect2 = 0;
for (int i = trainSize2; i < insts2.numInstances(); i++)
{
weka.core.Instance currentInst2 = insts2.instance(i);
double predictedClass = cl_Knn.classifyInstance(currentInst2);
if (predictedClass == insts2.instance(i).classValue())
{
numCorrect2++;
}
}
res_KNN = (double)((double)numCorrect2 / (double)testSize2 * 100.0);
successPercent.Add(res_KNN);
//Decision tree
weka.core.Instances insts3 = new weka.core.Instances(new java.io.FileReader(fileDirectory));
insts3.setClassIndex(insts3.numAttributes() - 1);
cl_Tree = new weka.classifiers.trees.J48();
weka.filters.Filter myNormalized2 = new weka.filters.unsupervised.instance.Normalize();
myNormalized2.setInputFormat(insts3);
insts3 = weka.filters.Filter.useFilter(insts3, myNormalized2);
//randomize the order of the instances in the dataset.
weka.filters.Filter myRandom3 = new weka.filters.unsupervised.instance.Randomize();
myRandom3.setInputFormat(insts3);
insts3 = weka.filters.Filter.useFilter(insts3, myRandom3);
int trainSize3 = insts3.numInstances() * percentSplit / 100;
int testSize3 = insts3.numInstances() - trainSize3;
weka.core.Instances train3 = new weka.core.Instances(insts3, 0, trainSize3);
cl_Tree.buildClassifier(train3);
string str3 = cl_Tree.toString();
int numCorrect3 = 0;
for (int i = trainSize3; i < insts3.numInstances(); i++)
{
weka.core.Instance currentInst3 = insts3.instance(i);
double predictedClass = cl_Tree.classifyInstance(currentInst3);
if (predictedClass == insts3.instance(i).classValue())
{
numCorrect3++;
}
}
res_Tree = (double)((double)numCorrect3 / (double)testSize3 * 100.0);
successPercent.Add(res_Tree);
//Neural Network
weka.core.Instances insts4 = new weka.core.Instances(new java.io.FileReader(fileDirectory));
insts4.setClassIndex(insts4.numAttributes() - 1);
cl_NN = new weka.classifiers.functions.MultilayerPerceptron();
//Nominal to Binary
weka.filters.Filter myBinaryData2 = new weka.filters.unsupervised.attribute.NominalToBinary();
myBinaryData2.setInputFormat(insts4);
insts4 = weka.filters.Filter.useFilter(insts4, myBinaryData2);
//Normalization
weka.filters.Filter myNormalized3 = new weka.filters.unsupervised.instance.Normalize();
myNormalized3.setInputFormat(insts4);
insts4 = weka.filters.Filter.useFilter(insts4, myNormalized3);
//randomize the order of the instances in the dataset.
weka.filters.Filter myRandom4 = new weka.filters.unsupervised.instance.Randomize();
myRandom4.setInputFormat(insts4);
insts4 = weka.filters.Filter.useFilter(insts4, myRandom4);
int trainSize4 = insts4.numInstances() * percentSplit / 100;
int testSize4 = insts4.numInstances() - trainSize4;
weka.core.Instances train4 = new weka.core.Instances(insts4, 0, trainSize4);
cl_NN.buildClassifier(train4);
string str4 = cl_NN.toString();
int numCorrect4 = 0;
for (int i = trainSize4; i < insts4.numInstances(); i++)
{
weka.core.Instance currentInst4 = insts4.instance(i);
double predictedClass = cl_NN.classifyInstance(currentInst4);
if (predictedClass == insts4.instance(i).classValue())
{
numCorrect4++;
}
}
res_NN = (double)((double)numCorrect4 / (double)testSize4 * 100.0);
successPercent.Add(res_NN);
//SVM
weka.core.Instances insts5 = new weka.core.Instances(new java.io.FileReader(fileDirectory));
insts5.setClassIndex(insts5.numAttributes() - 1);
cl_SVM = new weka.classifiers.functions.SMO();
//Nominal to Binary
weka.filters.Filter myBinaryData3 = new weka.filters.unsupervised.attribute.NominalToBinary();
myBinaryData3.setInputFormat(insts5);
insts5 = weka.filters.Filter.useFilter(insts5, myBinaryData3);
//Normalization
weka.filters.Filter myNormalized4 = new weka.filters.unsupervised.instance.Normalize();
myNormalized4.setInputFormat(insts5);
insts5 = weka.filters.Filter.useFilter(insts5, myNormalized4);
//randomize the order of the instances in the dataset.
weka.filters.Filter myRandom5 = new weka.filters.unsupervised.instance.Randomize();
myRandom5.setInputFormat(insts5);
insts5 = weka.filters.Filter.useFilter(insts5, myRandom5);
int trainSize5 = insts5.numInstances() * percentSplit / 100;
int testSize5 = insts5.numInstances() - trainSize5;
weka.core.Instances train5 = new weka.core.Instances(insts5, 0, trainSize5);
cl_SVM.buildClassifier(train5);
string str5 = cl_SVM.toString();
int numCorrect5 = 0;
for (int i = trainSize5; i < insts5.numInstances(); i++)
{
weka.core.Instance currentInst5 = insts5.instance(i);
double predictedClass = cl_SVM.classifyInstance(currentInst5);
if (predictedClass == insts5.instance(i).classValue())
{
numCorrect5++;
}
}
res_SVM = (double)((double)numCorrect5 / (double)testSize5 * 100.0);
successPercent.Add(res_SVM);
for (int i = 0; i < successPercent.Count; i++)
{
if ((double)successPercent[i] > max)
{
max = (double)successPercent[i];
count = i + 1;
}
}
for (int i = 0; i < count; i++)
{
nameOfAlgo = (string)algorithms[i];
}
textBox1.Text = nameOfAlgo + " is the most successful algorithm for this data set." + "(" + max + "%)\n";
}
