/// <summary> /// Creates a classifier of the desired type from an .arff file /// </summary> /// <param name="ARFFfile">The arff file to read from. Should be a full path.</param> /// <param name="classifier">The type of classifier you want to make.</param> /// <returns>The classifier you created</returns> public void createModel(string ARFFfile, Classifier myClassifier) { if (debug) { Console.WriteLine("Loading ARFF file " + ARFFfile); } _classifier = GetClassifier(myClassifier); try { _dataSet = new weka.core.Instances(new java.io.FileReader(ARFFfile)); if (debug) { Console.WriteLine("You have " + _dataSet.numAttributes() + " attributes."); } _dataSet.setClassIndex(_dataSet.numAttributes() - 1); _classifier.buildClassifier(_dataSet); if (debug) { Console.WriteLine(_classifier.toString()); } } catch (Exception e) { Console.WriteLine("You failed. End of Game. Poor Weka."); Console.WriteLine(e); } }
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 "; } } }
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"; }