/// <summary>
/// Determines all categories --> categories
/// Determines category numbers of each attributes -->> categoryTypeNumber
/// Determines target numbers and amounts of each categories of each attributes -->> categoryTypeTargetNumber
/// [i][j][k] i means attributes, j means categories, k means targets
/// </summary>
/// <param name="insts"></param>
private void DataPreparation(weka.core.Instances insts)
{
for (int i = 0; i < insts.numAttributes(); i++)
{
string[] categoryType = new string[insts.attribute(i).numValues()];
for (int j = 0; j < insts.attribute(i).numValues(); j++)
{
categoryType[j] = insts.attribute(i).value(j).ToString();
}
categories.Add(categoryType);
}
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++)
{
lst[lst.Count - 1].Add(insts.instance(i).toString(j));
}
}
List <int[]> categoryTypeNumber = new List <int[]>();
List <int[, ]> categoryTypeTargetNumber = new List <int[, ]>();
for (int i = 0; i < categories.Count; i++)
{
categoryTypeNumber.Add(new int[categories[i].Length]);
categoryTypeTargetNumber.Add(new int[categories[i].Length, categories[categories.Count - 1].Length]);
}
for (int i = 0; i < lst.Count; i++) //Satır
{
for (int j = 0; j < lst[i].Count; j++) //Sütün
{
for (int k = 0; k < categories[j].Length; k++) //Kategori Sayısı
{
string targetValue = lst[i][lst[i].Count - 1];
if (lst[i][j].Contains(categories[j][k]))
{
categoryTypeNumber[j][k] += 1;
for (int trgt = 0; trgt < categories[categories.Count - 1].Length; trgt++)
{
if (targetValue == categories[categories.Count - 1][trgt])
{
categoryTypeTargetNumber[j][k, trgt] += 1;
}
}
}
}
}
}
Twoing(insts, categoryTypeNumber, categoryTypeTargetNumber);
Gini(insts, categoryTypeNumber, categoryTypeTargetNumber);
LogInfo("Dataset is saved.\r\n\r\n");
LogInfo("TWOING : " + twoingPath + "\r\n\r\n");
LogInfo("GINI : " + giniPath + "\r\n");
}
public void Build()
{
this.featureIndex = new int[this.features.Count];
for(int i=0;(i< this.features.Count);i++)
{
for (int j = 0; (j < Extractor.ArffAttributeLabels.Length); j++)
if (((string)this.features[i]).Equals(Extractor.ArffAttributeLabels[j]))
{
this.featureIndex[i] = j;
break;
}
}
instances = new Instances(new StreamReader(this.filename));
instances.Class = instances.attribute(this.features.Count);
classifier = new J48();
classifier.buildClassifier(instances);
//setup the feature vector
//fvWekaAttributes = new FastVector(this.features.Count + 1);
//for (i = 0; (i < this.features.Count); i++)
// fvWekaAttributes.addElement(new weka.core.Attribute(this.features[i]));
//Setup the class attribute
//FastVector fvClassVal = new FastVector();
//for (i = 0; (i < this.classes.Count); i++)
// fvClassVal.addElement(this.classes[i]);
//weka.core.Attribute ClassAttribute = new weka.core.Attribute("activity", fvClassVal);
}
/// <summary>
/// Adds teta results of gini results to the list
/// Change the attributes of the arff file
/// Adds the attributes to arff file
/// </summary>
/// <param name="insts"></param>
/// <param name="result"></param>
/// <param name="path"></param>
private void CreateNewDataset(weka.core.Instances insts, List <double[]> result, string path)
{
//Tetaları Listeye Ekle
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() - 1; j++)
{
string value = insts.instance(i).toString(j);
for (int k = 0; k < categories[j].Length; k++)
{
if (insts.instance(i).toString(j) == categories[j][k])
{
lst[lst.Count - 1].Add(String.Format("{0:0.00}", result[j][k]));
break;
}
}
}
}
//Attiribute Değiştir
for (int i = 0; i < insts.numAttributes() - 1; i++)
{
string name = insts.attribute(i).name().ToString();
insts.deleteAttributeAt(i);
weka.core.Attribute att = new weka.core.Attribute(name);
insts.insertAttributeAt(att, i);
}
//Attiributeları yaz
for (int i = 0; i < insts.numInstances(); i++)
{
for (int j = 0; j < insts.instance(i).numValues() - 1; j++)
{
insts.instance(i).setValue(j, Convert.ToDouble(lst[i][j]));
}
}
if (File.Exists(path))
{
File.Delete(path);
}
var saver = new ArffSaver();
saver.setInstances(insts);
saver.setFile(new java.io.File(path));
saver.writeBatch();
}
private void button1_Click(object sender, EventArgs e)
{
weka.core.Instances insts = new weka.core.Instances(new java.io.FileReader(file));
double[] Data = new double[insts.numAttributes()];
for (int i = 0; i < list.Count; i++)
{
if (list[i].GetType() == typeof(TextBox))
{
TextBox txt = (TextBox)list[i];
string value = txt.Text.Replace('.', ',');
Data[i] = Convert.ToDouble(value);
}
else
{
ComboBox combobox = (ComboBox)list[i];
Data[i] = Convert.ToDouble(combobox.SelectedIndex);
}
}
// Data[(insts.numAttributes() - 1] = 0;
insts.setClassIndex(insts.numAttributes() - 1);
Instance newInsts = new Instance(1.0, Data);
insts.add(newInsts);
string type = model.GetType().ToString();
if (type == "weka.classifiers.bayes.NaiveBayes")
{
weka.filters.Filter myDiscretize = new weka.filters.unsupervised.attribute.Discretize();
myDiscretize.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myDiscretize);
}
else if (type == "weka.classifiers.lazy.IBk")
{
weka.filters.Filter myDummy = new weka.filters.unsupervised.attribute.NominalToBinary();
myDummy.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myDummy);
weka.filters.Filter myNormalize = new weka.filters.unsupervised.instance.Normalize();
myNormalize.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myNormalize);
}
double index = model.classifyInstance(insts.lastInstance());
string result = insts.attribute(insts.numAttributes() - 1).value(Convert.ToInt16(index));
MessageBox.Show(result);
}
/// <summary> Prints left side of condition..
///
/// </summary>
/// <param name="data">training set.
/// </param>
public override System.String leftSide(Instances data)
{
return data.attribute(m_attIndex).name();
}
/// <summary> Creates a C4.5-type split on the given data. Assumes that none of
/// the class values is missing.
///
/// </summary>
/// <exception cref="Exception">if something goes wrong
/// </exception>
public override void buildClassifier(Instances trainInstances)
{
// Initialize the remaining instance variables.
m_numSubsets = 0;
//UPGRADE_TODO: The equivalent in .NET for field 'java.lang.Double.MAX_VALUE' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
m_splitPoint = System.Double.MaxValue;
m_infoGain = 0;
m_gainRatio = 0;
// Different treatment for enumerated and numeric
// attributes.
if (trainInstances.attribute(m_attIndex).Nominal)
{
m_complexityIndex = trainInstances.attribute(m_attIndex).numValues();
m_index = m_complexityIndex;
handleEnumeratedAttribute(trainInstances);
}
else
{
m_complexityIndex = 2;
m_index = 0;
trainInstances.sort(trainInstances.attribute(m_attIndex));
handleNumericAttribute(trainInstances);
}
}
/// <summary> Returns a string containing java source code equivalent to the test
/// made at this node. The instance being tested is called "i".
///
/// </summary>
/// <param name="index">index of the nominal value tested
/// </param>
/// <param name="data">the data containing instance structure info
/// </param>
/// <returns> a value of type 'String'
/// </returns>
public override System.String sourceExpression(int index, Instances data)
{
System.Text.StringBuilder expr = null;
if (index < 0)
{
return "i[" + m_attIndex + "] == null";
}
if (data.attribute(m_attIndex).Nominal)
{
if (index == 0)
{
expr = new System.Text.StringBuilder("i[");
}
else
{
expr = new System.Text.StringBuilder("!i[");
}
expr.Append(m_attIndex).Append("]");
//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'"
expr.Append(".equals(\"").Append(data.attribute(m_attIndex).value_Renamed((int) m_splitPoint)).Append("\")");
}
else
{
expr = new System.Text.StringBuilder("((Double) i[");
expr.Append(m_attIndex).Append("])");
if (index == 0)
{
expr.Append(".doubleValue() <= ").Append(m_splitPoint);
}
else
{
expr.Append(".doubleValue() > ").Append(m_splitPoint);
}
}
return expr.ToString();
}
/// <summary> Prints the condition satisfied by instances in a subset.
///
/// </summary>
/// <param name="index">of subset and training set.
/// </param>
public override System.String rightSide(int index, Instances data)
{
System.Text.StringBuilder text;
text = new System.Text.StringBuilder();
if (data.attribute(m_attIndex).Nominal)
{
if (index == 0)
{
//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'"
text.Append(" = " + data.attribute(m_attIndex).value_Renamed((int) m_splitPoint));
}
else
{
//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'"
text.Append(" != " + data.attribute(m_attIndex).value_Renamed((int) m_splitPoint));
}
}
else if (index == 0)
text.Append(" <= " + m_splitPoint);
else
text.Append(" > " + m_splitPoint);
return text.ToString();
}
public MITesDataCollectionForm(string dataDirectory, string arffFile, bool isHierarchical)
{
//where data is being stored
this.dataDirectory = dataDirectory;
//Initialize high resolution unix timer
UnixTime.InitializeTime();
//Initialize and start GUI progress thread
progressMessage = null;
aProgressThread = new Thread(new ThreadStart(ProgressThread));
aProgressThread.Start();
#region Load Configuration files
//load the activity and sensor configuration files
progressMessage = "Loading XML protocol and sensors ...";
AXML.Reader reader = new AXML.Reader(Constants.MASTER_DIRECTORY, dataDirectory);
#if (!PocketPC)
if (reader.validate() == false)
{
throw new Exception("Error Code 0: XML format error - activities.xml does not match activities.xsd!");
}
else
{
#endif
this.annotation = reader.parse();
this.annotation.DataDirectory = dataDirectory;
SXML.Reader sreader = new SXML.Reader(Constants.MASTER_DIRECTORY, dataDirectory);
#if (!PocketPC)
if (sreader.validate() == false)
{
throw new Exception("Error Code 0: XML format error - sensors.xml does not match sensors.xsd!");
}
else
{
#endif
this.sensors = sreader.parse(Constants.MAX_CONTROLLERS);
progressMessage += " Completed\r\n";
//TODO: remove BT components
progressMessage += "Loading configuration file ...";
MITesFeatures.core.conf.ConfigurationReader creader = new MITesFeatures.core.conf.ConfigurationReader(dataDirectory);
this.configuration = creader.parse();
progressMessage += " Completed\r\n";
#if (!PocketPC)
}
}
#endif
#endregion Load Configuration files
#region Initialize External Data Reception Channels
//Initialize 1 master decoder
this.masterDecoder = new MITesDecoder();
//Initialize the software mode
isExtracting = false;
isCollectingDetailedData = false;
isPlotting = true;
isClassifying = true;
#region Initialize Feature Extraction
this.isExtracting = false;
if (this.sensors.TotalReceivers > 0) // if there is at least 1 MIT
//Extractor.Initialize(this.mitesDecoders[0], dataDirectory, this.annotation, this.sensors, this.configuration);
Extractor.Initialize(this.masterDecoder, dataDirectory, this.annotation, this.sensors, this.configuration);
else if (this.sensors.Sensors.Count > 0) // only built in
Extractor.Initialize(this.masterDecoder, dataDirectory, this.annotation, this.sensors, this.configuration);
#endregion Initialize Feature Extraction
labelIndex = new Hashtable();
instances = new Instances(new StreamReader(arffFile));
instances.Class = instances.attribute(Extractor.ArffAttributeLabels.Length);
classifier = new J48();
if (!File.Exists("model.xml"))
{
classifier.buildClassifier(instances);
TextWriter tc = new StreamWriter("model.xml");
classifier.toXML(tc);
tc.Flush();
tc.Close();
}
else
classifier.buildClassifier("model.xml", instances);
fvWekaAttributes = new FastVector(Extractor.ArffAttributeLabels.Length + 1);
for (int i = 0; (i < Extractor.ArffAttributeLabels.Length); i++)
fvWekaAttributes.addElement(new weka.core.Attribute(Extractor.ArffAttributeLabels[i]));
FastVector fvClassVal = new FastVector();
labelCounters = new int[((AXML.Category)this.annotation.Categories[0]).Labels.Count + 1];
activityLabels = new string[((AXML.Category)this.annotation.Categories[0]).Labels.Count + 1];
for (int i = 0; (i < ((AXML.Category)this.annotation.Categories[0]).Labels.Count); i++)
{
labelCounters[i] = 0;
string label = "";
int j = 0;
for (j = 0; (j < this.annotation.Categories.Count - 1); j++)
label += ((AXML.Label)((AXML.Category)this.annotation.Categories[j]).Labels[i]).Name.Replace(' ', '_') + "_";
label += ((AXML.Label)((AXML.Category)this.annotation.Categories[j]).Labels[i]).Name.Replace(' ', '_');
activityLabels[i] = label;
labelIndex.Add(label, i);
fvClassVal.addElement(label);
}
weka.core.Attribute ClassAttribute = new weka.core.Attribute("activity", fvClassVal);
isClassifying = true;
this.aMITesActivityCounters = new Hashtable();
if (!((this.sensors.Sensors.Count == 1) && (this.sensors.HasBuiltinSensors)))
{
//Initialize arrays to store USB and Bluetooth controllers
this.mitesControllers = new MITesReceiverController[this.sensors.TotalWiredReceivers];
#if (PocketPC)
this.bluetoothControllers = new BluetoothController[this.sensors.TotalBluetoothReceivers];
//this.ts = new Thread[this.sensors.TotalBluetoothReceivers];
#endif
//Initialize array to store Bluetooth connection status
//this.bluetoothConnectionStatus = new bool[this.sensors.TotalBluetoothReceivers];
//Initialize a decoder for each sensor
this.mitesDecoders = new MITesDecoder[this.sensors.TotalReceivers];
#if (PocketPC)
#region Bluetooth reception channels initialization
//Initialize and search for wockets connections
progressMessage += "Initializing Bluetooth receivers ... searching " + this.sensors.TotalBluetoothReceivers + " BT receivers\r\n";
//Try to initialize all Bluetooth receivers 10 times then exit
int initializationAttempt = 0;
while (initializationAttempt <= 10)
{
if (InitializeBluetoothReceivers() == false)
{
initializationAttempt++;
if (initializationAttempt == 10)
{
MessageBox.Show("Exiting: Some Bluetooth receivers in your configuration were not initialized.");
Application.Exit();
System.Diagnostics.Process.GetCurrentProcess().Kill();
}
else
progressMessage += "Failed to initialize all BT connections. Retrying (" + initializationAttempt + ")...\r\n";
}
else
break;
Thread.Sleep(2000);
}
#endregion Bluetooth reception channels initialization
#endif
#region USB reception channels initialization
if (InitializeUSBReceivers() == false)
{
MessageBox.Show("Exiting: Some USB receivers in your configuration were not initialized.");
#if (PocketPC)
Application.Exit();
System.Diagnostics.Process.GetCurrentProcess().Kill();
#else
Environment.Exit(0);
#endif
}
#endregion USB reception channels initialization
}
//}
#endregion Initialize External Data Reception Channels
#if (PocketPC)
#region Initialize Builtin Data Reception Channels
if (InitializeBuiltinReceivers() == false)
{
MessageBox.Show("Exiting: A built in receiver channel was not found.");
Application.Exit();
System.Diagnostics.Process.GetCurrentProcess().Kill();
}
#endregion Initialize Builtin Data Reception Channels
#endif
#region Initialize GUI Components
//initialize the interface components
InitializeComponent();
//Initialize GUI timers
progressMessage += "Initializing Timers ...";
InitializeTimers();
progressMessage += " Completed\r\n";
//Initialize different GUI components
progressMessage += "Initializing GUI ...";
InitializeInterface();
progressMessage += " Completed\r\n";
this.isPlotting = true;
//count the number of accelerometers
if (this.sensors.IsHR)
this.maxPlots = this.sensors.Sensors.Count - 1;
else
this.maxPlots = this.sensors.Sensors.Count;
SetFormPositions();
if (this.sensors.TotalReceivers > 0)
aMITesPlotter = new MITesScalablePlotter(this.panel1, MITesScalablePlotter.DeviceTypes.IPAQ, maxPlots, this.masterDecoder, GetGraphSize(false));
else
aMITesPlotter = new MITesScalablePlotter(this.panel1, MITesScalablePlotter.DeviceTypes.IPAQ, maxPlots, this.masterDecoder, GetGraphSize(false));
//Override the resize event
#if (PocketPC)
this.Resize += new EventHandler(OnResize);
#else
this.form1.Resize += new EventHandler(OnResizeForm1);
this.form1.FormClosing += new FormClosingEventHandler(form_FormClosing);
this.form2.Resize += new EventHandler(OnResizeForm2);
this.form2.FormClosing += new FormClosingEventHandler(form_FormClosing);
this.form3.Resize += new EventHandler(OnResizeForm3);
this.form3.FormClosing += new FormClosingEventHandler(form_FormClosing);
this.form4.Resize += new EventHandler(OnResizeForm4);
this.form4.FormClosing += new FormClosingEventHandler(form_FormClosing);
#endif
//Initialize the quality interface
progressMessage += "Initializing MITes Quality GUI ...";
InitializeQualityInterface();
progressMessage += " Completed\r\n";
//Remove classifier tabs
#if (PocketPC)
this.tabControl1.TabPages.RemoveAt(4);
this.tabControl1.SelectedIndex = 0;
#else
this.ShowForms();
#endif
#endregion Initialize GUI Components
#region Initialize Quality Tracking variables
InitializeQuality();
#endregion Initialize Quality Tracking variables
#region Initialize Logging
InitializeLogging(dataDirectory);
#endregion Initialize Logging
#region Initialize CSV Storage (PC Only)
#if (!PocketPC)
//create some counters for activity counts
averageX = new int[this.sensors.MaximumSensorID + 1];
averageY = new int[this.sensors.MaximumSensorID + 1];
averageZ = new int[this.sensors.MaximumSensorID + 1];
averageRawX = new int[this.sensors.MaximumSensorID + 1];
averageRawY = new int[this.sensors.MaximumSensorID + 1];
averageRawZ = new int[this.sensors.MaximumSensorID + 1];
prevX = new int[this.sensors.MaximumSensorID + 1];
prevY = new int[this.sensors.MaximumSensorID + 1];
prevZ = new int[this.sensors.MaximumSensorID + 1];
acCounters = new int[this.sensors.MaximumSensorID + 1];
activityCountWindowSize = 0;
activityCountCSVs = new StreamWriter[this.sensors.MaximumSensorID + 1];
samplingCSVs = new StreamWriter[this.sensors.MaximumSensorID + 1];
averagedRaw = new StreamWriter[this.sensors.MaximumSensorID + 1];
masterCSV = new StreamWriter(dataDirectory + "\\MITesSummaryData.csv");
hrCSV = new StreamWriter(dataDirectory + "\\HeartRate_MITes.csv");
string csv_line1 = "UnixTimeStamp,TimeStamp,X,Y,Z";
string csv_line2 = "UnixTimeStamp,TimeStamp,Sampling";
string hr_csv_header = "UnixTimeStamp,TimeStamp,HR";
string master_csv_header = "UnixTimeStamp,TimeStamp";
foreach (Category category in this.annotation.Categories)
master_csv_header += "," + category.Name;
foreach (Sensor sensor in this.sensors.Sensors)
{
int sensor_id = Convert.ToInt32(sensor.ID);
string location = sensor.Location.Replace(' ', '-');
if (sensor_id > 0) //exclude HR
{
activityCountCSVs[sensor_id] = new StreamWriter(dataDirectory + "\\MITes_" + sensor_id.ToString("00") + "_ActivityCount_" + location + ".csv");
activityCountCSVs[sensor_id].WriteLine(csv_line1);
averagedRaw[sensor_id] = new StreamWriter(dataDirectory + "\\MITes_" + sensor_id.ToString("00") + "_1s-RawMean_" + location + ".csv");
averagedRaw[sensor_id].WriteLine(csv_line1);
samplingCSVs[sensor_id] = new StreamWriter(dataDirectory + "\\MITes_" + sensor_id.ToString("00") + "_SampleRate_" + location + ".csv");
samplingCSVs[sensor_id].WriteLine(csv_line2);
master_csv_header += ",MITes" + sensor_id.ToString("00") + "_SR," + "MITes" + sensor_id.ToString("00") + "_AVRaw_X," +
"MITes" + sensor_id.ToString("00") + "_AVRaw_Y," + "MITes" + sensor_id.ToString("00") + "_AVRaw_Z," + "MITes" + sensor_id.ToString("00") + "_AC_X," +
"MITes" + sensor_id.ToString("00") + "_AC_Y," + "MITes" + sensor_id.ToString("00") + "_AC_Z";
}
}
master_csv_header += ",HR";
this.masterCSV.WriteLine(master_csv_header);
this.hrCSV.WriteLine(hr_csv_header);
#endif
#endregion Initialize CSV Storage (PC Only)
#region Start Collecting Data
//if (this.sensors.TotalReceivers > 0)
// isStartedReceiver = true;
//Start the built in polling thread
#if (PocketPC)
if (this.sensors.HasBuiltinSensors)
{
this.pollingThread = new Thread(new ThreadStart(this.pollingData));
this.pollingThread.Priority = ThreadPriority.Lowest;
this.pollingThread.Start();
}
#endif
//Terminate the progress thread
progressThreadQuit = true;
//Enable all timer functions
this.readDataTimer.Enabled = true;
this.qualityTimer.Enabled = true;
if (this.sensors.IsHR)
this.HRTimer.Enabled = true;
#endregion Start Collecting Data
}
/// <summary> Returns the minsAndMaxs of the index.th subset.</summary>
public double[][] minsAndMaxs(Instances data, double[][] minsAndMaxs, int index)
{
double[][] newMinsAndMaxs = new double[data.numAttributes()][];
for (int i = 0; i < data.numAttributes(); i++)
{
newMinsAndMaxs[i] = new double[2];
}
for (int i = 0; i < data.numAttributes(); i++)
{
newMinsAndMaxs[i][0] = minsAndMaxs[i][0];
newMinsAndMaxs[i][1] = minsAndMaxs[i][1];
if (i == m_attIndex)
if (data.attribute(m_attIndex).Nominal)
newMinsAndMaxs[m_attIndex][1] = 1;
else
newMinsAndMaxs[m_attIndex][1 - index] = m_splitPoint;
}
return newMinsAndMaxs;
}
/// <summary>
/// Build the learning model for classification
/// </summary>
/// <param name="InstancesList">list of instances </param>
/// <param name="NumberofClusters">Number of Clusters</param>
/// <param name="TextBoxForFeedback">Text box for the results (can be NULL)</param>
/// <param name="PanelForVisualFeedback">Panel to display visual results if avalaible (can be NULL)</param>
public Classifier PerformTraining(FormForClassificationInfo WindowForClassificationParam, Instances InstancesList, /*int NumberofClusters,*/ RichTextBox TextBoxForFeedback,
Panel PanelForVisualFeedback, out weka.classifiers.Evaluation ModelEvaluation, bool IsCellular)
{
// weka.classifiers.Evaluation ModelEvaluation = null;
// FormForClassificationInfo WindowForClassificationParam = new FormForClassificationInfo(GlobalInfo);
ModelEvaluation = null;
// if (WindowForClassificationParam.ShowDialog() != System.Windows.Forms.DialogResult.OK) return null;
// weka.classifiers.Evaluation ModelEvaluation = new Evaluation(
cParamAlgo ClassifAlgoParams = WindowForClassificationParam.GetSelectedAlgoAndParameters();
if (ClassifAlgoParams == null) return null;
//this.Cursor = Cursors.WaitCursor;
// cParamAlgo ClassificationAlgo = WindowForClassificationParam.GetSelectedAlgoAndParameters();
cListValuesParam Parameters = ClassifAlgoParams.GetListValuesParam();
//Classifier this.CurrentClassifier = null;
// -------------------------- Classification -------------------------------
// create the instances
// InstancesList = this.ListInstances;
this.attValsWithoutClasses = new FastVector();
if (IsCellular)
for (int i = 0; i < cGlobalInfo.ListCellularPhenotypes.Count; i++)
this.attValsWithoutClasses.addElement(cGlobalInfo.ListCellularPhenotypes[i].Name);
else
for (int i = 0; i < cGlobalInfo.ListWellClasses.Count; i++)
this.attValsWithoutClasses.addElement(cGlobalInfo.ListWellClasses[i].Name);
InstancesList.insertAttributeAt(new weka.core.Attribute("Class", this.attValsWithoutClasses), InstancesList.numAttributes());
//int A = Classes.Count;
for (int i = 0; i < Classes.Count; i++)
InstancesList.get(i).setValue(InstancesList.numAttributes() - 1, Classes[i]);
InstancesList.setClassIndex(InstancesList.numAttributes() - 1);
weka.core.Instances train = new weka.core.Instances(InstancesList, 0, InstancesList.numInstances());
if (PanelForVisualFeedback != null)
PanelForVisualFeedback.Controls.Clear();
#region List classifiers
#region J48
if (ClassifAlgoParams.Name == "J48")
{
this.CurrentClassifier = new weka.classifiers.trees.J48();
((J48)this.CurrentClassifier).setMinNumObj((int)Parameters.ListDoubleValues.Get("numericUpDownMinInstLeaf").Value);
((J48)this.CurrentClassifier).setConfidenceFactor((float)Parameters.ListDoubleValues.Get("numericUpDownConfFactor").Value);
((J48)this.CurrentClassifier).setNumFolds((int)Parameters.ListDoubleValues.Get("numericUpDownNumFolds").Value);
((J48)this.CurrentClassifier).setUnpruned((bool)Parameters.ListCheckValues.Get("checkBoxUnPruned").Value);
((J48)this.CurrentClassifier).setUseLaplace((bool)Parameters.ListCheckValues.Get("checkBoxLaplacianSmoothing").Value);
((J48)this.CurrentClassifier).setSeed((int)Parameters.ListDoubleValues.Get("numericUpDownSeedNumber").Value);
((J48)this.CurrentClassifier).setSubtreeRaising((bool)Parameters.ListCheckValues.Get("checkBoxSubTreeRaising").Value);
// CurrentClassif.SetJ48Tree((J48)this.CurrentClassifier, Classes.Length);
this.CurrentClassifier.buildClassifier(train);
// display results training
// display tree
if (PanelForVisualFeedback != null)
{
GViewer GraphView = DisplayTree(GlobalInfo, ((J48)this.CurrentClassifier), IsCellular).gViewerForTreeClassif;
GraphView.Size = new System.Drawing.Size(PanelForVisualFeedback.Width, PanelForVisualFeedback.Height);
GraphView.Anchor = (AnchorStyles.Bottom | AnchorStyles.Top | AnchorStyles.Left | AnchorStyles.Right);
PanelForVisualFeedback.Controls.Clear();
PanelForVisualFeedback.Controls.Add(GraphView);
}
}
#endregion
#region Random Tree
else if (ClassifAlgoParams.Name == "RandomTree")
{
this.CurrentClassifier = new weka.classifiers.trees.RandomTree();
if ((bool)Parameters.ListCheckValues.Get("checkBoxMaxDepthUnlimited").Value)
((RandomTree)this.CurrentClassifier).setMaxDepth(0);
else
((RandomTree)this.CurrentClassifier).setMaxDepth((int)Parameters.ListDoubleValues.Get("numericUpDownMaxDepth").Value);
((RandomTree)this.CurrentClassifier).setSeed((int)Parameters.ListDoubleValues.Get("numericUpDownSeed").Value);
((RandomTree)this.CurrentClassifier).setMinNum((double)Parameters.ListDoubleValues.Get("numericUpDownMinWeight").Value);
if ((bool)Parameters.ListCheckValues.Get("checkBoxIsBackfitting").Value)
{
((RandomTree)this.CurrentClassifier).setNumFolds((int)Parameters.ListDoubleValues.Get("numericUpDownBackFittingFolds").Value);
}
else
{
((RandomTree)this.CurrentClassifier).setNumFolds(0);
}
this.CurrentClassifier.buildClassifier(train);
//string StringForTree = ((RandomTree)this.CurrentClassifier).graph().Remove(0, ((RandomTree)this.CurrentClassifier).graph().IndexOf("{") + 2);
//Microsoft.Msagl.GraphViewerGdi.GViewer GraphView = new GViewer();
//GraphView.Graph = GlobalInfo.WindowHCSAnalyzer.ComputeAndDisplayGraph(StringForTree);//.Remove(StringForTree.Length - 3, 3));
//GraphView.Size = new System.Drawing.Size(panelForGraphicalResults.Width, panelForGraphicalResults.Height);
//GraphView.Anchor = (AnchorStyles.Bottom | AnchorStyles.Top | AnchorStyles.Left | AnchorStyles.Right);
//this.panelForGraphicalResults.Controls.Clear();
//this.panelForGraphicalResults.Controls.Add(GraphView);
}
#endregion
#region Random Forest
else if (ClassifAlgoParams.Name == "RandomForest")
{
this.CurrentClassifier = new weka.classifiers.trees.RandomForest();
if ((bool)Parameters.ListCheckValues.Get("checkBoxMaxDepthUnlimited").Value)
((RandomForest)this.CurrentClassifier).setMaxDepth(0);
else
((RandomForest)this.CurrentClassifier).setMaxDepth((int)Parameters.ListDoubleValues.Get("numericUpDownMaxDepth").Value);
((RandomForest)this.CurrentClassifier).setNumTrees((int)Parameters.ListDoubleValues.Get("numericUpDownNumTrees").Value);
((RandomForest)this.CurrentClassifier).setSeed((int)Parameters.ListDoubleValues.Get("numericUpDownSeed").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region KStar
else if (ClassifAlgoParams.Name == "KStar")
{
this.CurrentClassifier = new weka.classifiers.lazy.KStar();
((KStar)this.CurrentClassifier).setGlobalBlend((int)Parameters.ListDoubleValues.Get("numericUpDownGlobalBlend").Value);
((KStar)this.CurrentClassifier).setEntropicAutoBlend((bool)Parameters.ListCheckValues.Get("checkBoxBlendAuto").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region SVM
else if (ClassifAlgoParams.Name == "SVM")
{
this.CurrentClassifier = new weka.classifiers.functions.SMO();
((SMO)this.CurrentClassifier).setC((double)Parameters.ListDoubleValues.Get("numericUpDownC").Value);
((SMO)this.CurrentClassifier).setKernel(WindowForClassificationParam.GeneratedKernel);
((SMO)this.CurrentClassifier).setRandomSeed((int)Parameters.ListDoubleValues.Get("numericUpDownSeed").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region KNN
else if (ClassifAlgoParams.Name == "KNN")
{
this.CurrentClassifier = new weka.classifiers.lazy.IBk();
string OptionDistance = " -K " + (int)Parameters.ListDoubleValues.Get("numericUpDownKNN").Value + " -W 0 ";
string WeightType = (string)Parameters.ListTextValues.Get("comboBoxDistanceWeight").Value;
switch (WeightType)
{
case "No Weighting":
OptionDistance += "";
break;
case "1/Distance":
OptionDistance += "-I";
break;
case "1-Distance":
OptionDistance += "-F";
break;
default:
break;
}
OptionDistance += " -A \"weka.core.neighboursearch.LinearNNSearch -A \\\"weka.core.";
string DistanceType = (string)Parameters.ListTextValues.Get("comboBoxDistance").Value;
// OptionDistance += " -A \"weka.core.";
switch (DistanceType)
{
case "Euclidean":
OptionDistance += "EuclideanDistance";
break;
case "Manhattan":
OptionDistance += "ManhattanDistance";
break;
case "Chebyshev":
OptionDistance += "ChebyshevDistance";
break;
default:
break;
}
if (!(bool)Parameters.ListCheckValues.Get("checkBoxNormalize").Value)
OptionDistance += " -D";
OptionDistance += " -R ";
OptionDistance += "first-last\\\"\"";
((IBk)this.CurrentClassifier).setOptions(weka.core.Utils.splitOptions(OptionDistance));
//((IBk)this.CurrentClassifier).setKNN((int)Parameters.ListDoubleValues.Get("numericUpDownKNN").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region Multilayer Perceptron
else if (ClassifAlgoParams.Name == "Perceptron")
{
this.CurrentClassifier = new weka.classifiers.functions.MultilayerPerceptron();
((MultilayerPerceptron)this.CurrentClassifier).setMomentum((double)Parameters.ListDoubleValues.Get("numericUpDownMomentum").Value);
((MultilayerPerceptron)this.CurrentClassifier).setLearningRate((double)Parameters.ListDoubleValues.Get("numericUpDownLearningRate").Value);
((MultilayerPerceptron)this.CurrentClassifier).setSeed((int)Parameters.ListDoubleValues.Get("numericUpDownSeed").Value);
((MultilayerPerceptron)this.CurrentClassifier).setTrainingTime((int)Parameters.ListDoubleValues.Get("numericUpDownTrainingTime").Value);
((MultilayerPerceptron)this.CurrentClassifier).setNormalizeAttributes((bool)Parameters.ListCheckValues.Get("checkBoxNormAttribute").Value);
((MultilayerPerceptron)this.CurrentClassifier).setNormalizeNumericClass((bool)Parameters.ListCheckValues.Get("checkBoxNormNumericClasses").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region ZeroR
else if (ClassifAlgoParams.Name == "ZeroR")
{
this.CurrentClassifier = new weka.classifiers.rules.OneR();
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region OneR
else if (ClassifAlgoParams.Name == "OneR")
{
this.CurrentClassifier = new weka.classifiers.rules.OneR();
((OneR)this.CurrentClassifier).setMinBucketSize((int)Parameters.ListDoubleValues.Get("numericUpDownMinBucketSize").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region Naive Bayes
else if (ClassifAlgoParams.Name == "NaiveBayes")
{
this.CurrentClassifier = new weka.classifiers.bayes.NaiveBayes();
((NaiveBayes)this.CurrentClassifier).setUseKernelEstimator((bool)Parameters.ListCheckValues.Get("checkBoxKernelEstimator").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region Logistic
else if (ClassifAlgoParams.Name == "Logistic")
{
this.CurrentClassifier = new weka.classifiers.functions.Logistic();
((Logistic)this.CurrentClassifier).setUseConjugateGradientDescent((bool)Parameters.ListCheckValues.Get("checkBoxUseConjugateGradientDescent").Value);
((Logistic)this.CurrentClassifier).setRidge((double)Parameters.ListDoubleValues.Get("numericUpDownRidge").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
//weka.classifiers.functions.SMO
//BayesNet
#endregion
if (TextBoxForFeedback != null)
{
TextBoxForFeedback.Clear();
TextBoxForFeedback.AppendText(this.CurrentClassifier.ToString());
}
TextBoxForFeedback.AppendText("\n" + (InstancesList.numAttributes() - 1) + " attributes:\n\n");
for (int IdxAttributes = 0; IdxAttributes < InstancesList.numAttributes() - 1; IdxAttributes++)
{
TextBoxForFeedback.AppendText(IdxAttributes + "\t: " + InstancesList.attribute(IdxAttributes).name() + "\n");
}
#region evaluation of the model and results display
if ((WindowForClassificationParam.numericUpDownFoldNumber.Enabled) && (TextBoxForFeedback != null))
{
TextBoxForFeedback.AppendText("\n-----------------------------\nModel validation\n-----------------------------\n");
ModelEvaluation = new weka.classifiers.Evaluation(InstancesList);
ModelEvaluation.crossValidateModel(this.CurrentClassifier, InstancesList, (int)WindowForClassificationParam.numericUpDownFoldNumber.Value, new java.util.Random(1));
TextBoxForFeedback.AppendText(ModelEvaluation.toSummaryString());
TextBoxForFeedback.AppendText("\n-----------------------------\nConfusion Matrix:\n-----------------------------\n");
double[][] ConfusionMatrix = ModelEvaluation.confusionMatrix();
string NewLine = "";
for (int i = 0; i < ConfusionMatrix[0].Length; i++)
{
NewLine += "c" + i + "\t";
}
TextBoxForFeedback.AppendText(NewLine + "\n\n");
for (int j = 0; j < ConfusionMatrix.Length; j++)
{
NewLine = "";
for (int i = 0; i < ConfusionMatrix[0].Length; i++)
{
NewLine += ConfusionMatrix[j][i] + "\t";
}
// if
TextBoxForFeedback.AppendText(NewLine + "| c" + j + " <=> " + cGlobalInfo.ListCellularPhenotypes[j].Name + "\n");
}
}
#endregion
return this.CurrentClassifier;
}
/// <summary>
/// Evalute and display a WEKA clusterer
/// </summary>
/// <param name="SelectedClusterer">weka clusterer</param>
/// <param name="InstancesList">list of instances for the validation</param>
/// <param name="RichTextBoxToDisplayResults">Text box for the results (can be NULL)</param>
/// <param name="PanelTodisplayGraphicalResults">Panel to display visual results if avalaible (can be NULL)</param>
/// <returns></returns>
public ClusterEvaluation EvaluteAndDisplayClusterer(RichTextBox RichTextBoxToDisplayResults,
Panel PanelTodisplayGraphicalResults, Instances ListInstanceForValid)
{
ClusterEvaluation eval = new ClusterEvaluation();
eval.setClusterer(SelectedClusterer);
eval.evaluateClusterer(ListInstanceForValid);
if (RichTextBoxToDisplayResults != null)
{
if ((RichTextBoxToDisplayResults != null) && (eval.getNumClusters() > cGlobalInfo.ListCellularPhenotypes.Count))
{
RichTextBoxToDisplayResults.Clear();
RichTextBoxToDisplayResults.AppendText("Error: " + eval.getNumClusters() + " clusters identifed.");
RichTextBoxToDisplayResults.AppendText("The maximum number of cluster is " + cGlobalInfo.ListCellularPhenotypes.Count + ".");
return null;
}
if (RichTextBoxToDisplayResults != null)
{
RichTextBoxToDisplayResults.Clear();
RichTextBoxToDisplayResults.AppendText(eval.clusterResultsToString());
}
RichTextBoxToDisplayResults.AppendText("\n" + ListInstanceForValid.numAttributes() + " attributes:\n\n");
for (int IdxAttributes = 0; IdxAttributes < ListInstanceForValid.numAttributes(); IdxAttributes++)
{
RichTextBoxToDisplayResults.AppendText(IdxAttributes + "\t: " + ListInstanceForValid.attribute(IdxAttributes).name() + "\n");
}
}
if (PanelTodisplayGraphicalResults != null) PanelTodisplayGraphicalResults.Controls.Clear();
if ((PanelTodisplayGraphicalResults != null) && (SelectedClusterer.GetType().Name == "HierarchicalClusterer"))
{
Button ButtonToDisplayHierarchicalClustering = new Button();
ButtonToDisplayHierarchicalClustering.Text = "Display Hierarchical Tree";
ButtonToDisplayHierarchicalClustering.Width *= 2;
ButtonToDisplayHierarchicalClustering.Location = new System.Drawing.Point((PanelTodisplayGraphicalResults.Width - ButtonToDisplayHierarchicalClustering.Width) / 2,
(PanelTodisplayGraphicalResults.Height - ButtonToDisplayHierarchicalClustering.Height) / 2);
ButtonToDisplayHierarchicalClustering.Anchor = AnchorStyles.None;
ButtonToDisplayHierarchicalClustering.Click += new EventHandler(ClickToDisplayHierarchicalTree);
PanelTodisplayGraphicalResults.Controls.Add(ButtonToDisplayHierarchicalClustering);
}
return eval;
}
// ---- OPERATIONS ----
///
/// <summary> * Sets the format of the input instances. If the filter is able to
/// * determine the output format before seeing any input instances, it
/// * does so here. This default implementation clears the output format
/// * and output queue, and the new batch flag is set. Overriders should
/// * call <code>super.setInputFormat(Instances)</code>
/// * </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 inputFormat can't be set successfully </exception>
///
//JAVA TO VB & C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public boolean setInputFormat(Instances instanceInfo) throws Exception
public override bool setInputFormat(Instances instanceInfo)
{
base.setInputFormat(instanceInfo);
for (int i = 0; i < instanceInfo.numAttributes(); ++i)
{
if (!instanceInfo.attribute(i).isNumeric())
{
throw new UnsupportedAttributeTypeException("All attributes must be numeric");
}
}
// Create the output buffer
setOutputFormat();
return true;
}
/// <summary> Checks if two headers are equivalent.
///
/// </summary>
/// <param name="dataset">another dataset
/// </param>
/// <returns> true if the header of the given dataset is equivalent
/// to this header
/// </returns>
public virtual bool equalHeaders(Instances dataset)
{
// Check class and all attributes
if (m_ClassIndex != dataset.m_ClassIndex)
{
return false;
}
if (m_Attributes.size() != dataset.m_Attributes.size())
{
return false;
}
for (int i = 0; i < m_Attributes.size(); i++)
{
if (!(attribute(i).Equals(dataset.attribute(i))))
{
return false;
}
}
return true;
}
/// <summary> Merges two sets of Instances together. The resulting set will have
/// all the attributes of the first set plus all the attributes of the
/// second set. The number of instances in both sets must be the same.
///
/// </summary>
/// <param name="first">the first set of Instances
/// </param>
/// <param name="second">the second set of Instances
/// </param>
/// <returns> the merged set of Instances
/// </returns>
/// <exception cref="IllegalArgumentException">if the datasets are not the same size
/// </exception>
public static Instances mergeInstances(Instances first, Instances second)
{
if (first.numInstances() != second.numInstances())
{
throw new System.ArgumentException("Instance sets must be of the same size");
}
// Create the vector of merged attributes
FastVector newAttributes = new FastVector();
for (int i = 0; i < first.numAttributes(); i++)
{
newAttributes.addElement(first.attribute(i));
}
for (int i = 0; i < second.numAttributes(); i++)
{
newAttributes.addElement(second.attribute(i));
}
// Create the set of Instances
Instances merged = new Instances(first.relationName() + '_' + second.relationName(), newAttributes, first.numInstances());
// Merge each instance
for (int i = 0; i < first.numInstances(); i++)
{
merged.add(first.instance(i).mergeInstance(second.instance(i)));
}
return merged;
}
/// <summary> Prints the condition satisfied by instances in a subset.
///
/// </summary>
/// <param name="index">of subset
/// </param>
/// <param name="data">training set.
/// </param>
public override System.String rightSide(int index, Instances data)
{
System.Text.StringBuilder text;
text = new System.Text.StringBuilder();
if (data.attribute(m_attIndex).Nominal)
text.Append(" = " + data.attribute(m_attIndex).value_Renamed(index));
else if (index == 0)
text.Append(" <= " + Utils.doubleToString(m_splitPoint, 6));
else
text.Append(" > " + Utils.doubleToString(m_splitPoint, 6));
return text.ToString();
}
/// <summary> Returns a string containing java source code equivalent to the test
/// made at this node. The instance being tested is called "i".
///
/// </summary>
/// <param name="index">index of the nominal value tested
/// </param>
/// <param name="data">the data containing instance structure info
/// </param>
/// <returns> a value of type 'String'
/// </returns>
public override System.String sourceExpression(int index, Instances data)
{
System.Text.StringBuilder expr = null;
if (index < 0)
{
return "i[" + m_attIndex + "] == null";
}
if (data.attribute(m_attIndex).Nominal)
{
expr = new System.Text.StringBuilder("i[");
expr.Append(m_attIndex).Append("]");
expr.Append(".equals(\"").Append(data.attribute(m_attIndex).value_Renamed(index)).Append("\")");
}
else
{
expr = new System.Text.StringBuilder("((Double) i[");
expr.Append(m_attIndex).Append("])");
if (index == 0)
{
expr.Append(".doubleValue() <= ").Append(m_splitPoint);
}
else
{
expr.Append(".doubleValue() > ").Append(m_splitPoint);
}
}
return expr.ToString();
}
private void Browse_Click(object sender, EventArgs e)
{
OpenFileDialog ofd = new OpenFileDialog();
ofd.ShowDialog();
file = ofd.SafeFileName;
label2.Text = "Wait process in progress";
weka.core.Instances insts = new weka.core.Instances(new java.io.FileReader(file));
double max_value = J48classifyTest(insts);
model = J48cl;
string name = "J48cl";
double NBvalue = NaiveBayesTest(insts);
if (NBvalue > max_value)
{
max_value = NBvalue;
model = NaiveBayescl;
name = "NaiveBayes";
}
double RFvalue = RandomForestTest(insts);
if (RFvalue > max_value)
{
max_value = RFvalue;
model = RandomForestcl;
name = "RandomForest";
}
double RTvalue = RandomTreeTest(insts);
if (RTvalue > max_value)
{
max_value = RTvalue;
model = RandomTreecl;
name = "RandomTree";
}
double _5IBKvalue = _5IBkTest(insts);
if (_5IBKvalue > max_value)
{
max_value = _5IBKvalue;
model = _5IBKcl;
name = " _5IBK";
}
double _7IBKvalue = _7IBkTest(insts);
if (_7IBKvalue > max_value)
{
max_value = _7IBKvalue;
model = _7IBKcl;
name = " _7IBk";
}
double _9IBKvalue = _9IBkTest(insts);
if (_9IBKvalue > max_value)
{
max_value = _9IBKvalue;
model = _9IBKcl;
name = " _9IBk";
}
double LogRegressionvalue = LogRegressionTest(insts);
if (LogRegressionvalue > max_value)
{
max_value = LogRegressionvalue;
model = LogRegressioncl;
name = "LogRegression";
}
double SVM = SupportVectorMachineTest(insts);
if (SVM > max_value)
{
max_value = SVM;
model = SupportVectorMachine;
name = "SupportVectorMachine";
}
double ArtNN = ArtNeuralNetworkTest(insts);
if (ArtNN > max_value)
{
max_value = ArtNN;
model = ArtNeuralNetwork;
name = "ArtNeuralNetwork";
}
label2.Text = name + " is the most successful algorithm for this data set " + "(%" + Math.Round(max_value, 2) + ")";
for (int i = 0; i < insts.numAttributes() - 1; i++)
{
if (insts.attribute(i).isNominal())
{
Label l = new Label();
flowLayoutPanel2.Controls.Add(l);
l.Top = i * 30 + 175;
l.Left = 100;
l.Text = insts.attribute(i).name().ToString() + ": ";
ComboBox mybox = new ComboBox();
for (int j = 0; j < insts.attribute(i).numValues(); j++)
{
mybox.Items.Add(insts.attribute(i).value(j));
}
// Creating and setting the properties of comboBox
mybox.DropDownStyle = ComboBoxStyle.DropDownList;
mybox.Size = new Size(100, 30);
mybox.Top = i * 30 + 175;
l.Left = 200;
mybox.Tag = i;
flowLayoutPanel2.Controls.Add(mybox);
list.Add(mybox);
}
else
{
Label l = new Label();
flowLayoutPanel2.Controls.Add(l);
l.Text = insts.attribute(i).name().ToString() + ": ";
TextBox txt = new TextBox();
txt.Tag = i;
list.Add(txt);
flowLayoutPanel2.Controls.Add(txt);
}
}
Button button = new Button();
button.Name = "Discover";
button.Text = "Find";
button.Location = new Point(468, 72);
button.Size = new Size(60, 30);
button.BackColor = Color.Red;
button.Font = new Font(button.Font.Name, button.Font.Size, FontStyle.Bold);
button.Click += new EventHandler(button1_Click);
Controls.Add(button);
}
private LabelsMetaData loadLabelsMeta(Instances data, int numLabels)
{
LabelsMetaDataImpl labelsData = new LabelsMetaDataImpl();
int numAttributes = data.numAttributes();
for (int index = numAttributes - numLabels; index < numAttributes; index++) {
String attrName = data.attribute(index).name();
labelsData.addRootNode(new LabelNodeImpl(attrName));
}
return labelsData;
}
/// <summary> Creates split on enumerated attribute.
///
/// </summary>
/// <exception cref="Exception">if something goes wrong
/// </exception>
private void handleEnumeratedAttribute(Instances trainInstances)
{
Distribution newDistribution, secondDistribution;
int numAttValues;
double currIG, currGR;
Instance instance;
int i;
numAttValues = trainInstances.attribute(m_attIndex).numValues();
newDistribution = new Distribution(numAttValues, trainInstances.numClasses());
// Only Instances with known values are relevant.
System.Collections.IEnumerator enu = trainInstances.enumerateInstances();
//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
while (enu.MoveNext())
{
//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
instance = (Instance) enu.Current;
if (!instance.isMissing(m_attIndex))
{
//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'"
newDistribution.add((int) instance.value_Renamed(m_attIndex), instance);
}
}
m_distribution = newDistribution;
// For all values
for (i = 0; i < numAttValues; i++)
{
if (Utils.grOrEq(newDistribution.perBag(i), m_minNoObj))
{
secondDistribution = new Distribution(newDistribution, i);
// Check if minimum number of Instances in the two
// subsets.
if (secondDistribution.check(m_minNoObj))
{
m_numSubsets = 2;
currIG = m_infoGainCrit.splitCritValue(secondDistribution, m_sumOfWeights);
currGR = m_gainRatioCrit.splitCritValue(secondDistribution, m_sumOfWeights, currIG);
if ((i == 0) || Utils.gr(currGR, m_gainRatio))
{
m_gainRatio = currGR;
m_infoGain = currIG;
m_splitPoint = (double) i;
m_distribution = secondDistribution;
}
}
}
}
}
/// <summary> Selects C4.5-type split for the given dataset.</summary>
public override ClassifierSplitModel selectModel(Instances data)
{
double minResult;
//double currentResult;
BinC45Split[] currentModel;
BinC45Split bestModel = null;
NoSplit noSplitModel = null;
double averageInfoGain = 0;
int validModels = 0;
bool multiVal = true;
Distribution checkDistribution;
double sumOfWeights;
int i;
try
{
// Check if all Instances belong to one class or if not
// enough Instances to split.
checkDistribution = new Distribution(data);
noSplitModel = new NoSplit(checkDistribution);
if (Utils.sm(checkDistribution.total(), 2 * m_minNoObj) || Utils.eq(checkDistribution.total(), checkDistribution.perClass(checkDistribution.maxClass())))
return noSplitModel;
// Check if all attributes are nominal and have a
// lot of values.
System.Collections.IEnumerator enu = data.enumerateAttributes();
//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
while (enu.MoveNext())
{
//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
weka.core.Attribute attribute = (weka.core.Attribute)enu.Current;
if ((attribute.Numeric) || (Utils.sm((double) attribute.numValues(), (0.3 * (double) m_allData.numInstances()))))
{
multiVal = false;
break;
}
}
currentModel = new BinC45Split[data.numAttributes()];
sumOfWeights = data.sumOfWeights();
// For each attribute.
for (i = 0; i < data.numAttributes(); i++)
{
// Apart from class attribute.
if (i != (data).classIndex())
{
// Get models for current attribute.
currentModel[i] = new BinC45Split(i, m_minNoObj, sumOfWeights);
currentModel[i].buildClassifier(data);
// Check if useful split for current attribute
// exists and check for enumerated attributes with
// a lot of values.
if (currentModel[i].checkModel())
if ((data.attribute(i).Numeric) || (multiVal || Utils.sm((double) data.attribute(i).numValues(), (0.3 * (double) m_allData.numInstances()))))
{
averageInfoGain = averageInfoGain + currentModel[i].infoGain();
validModels++;
}
}
else
currentModel[i] = null;
}
// Check if any useful split was found.
if (validModels == 0)
return noSplitModel;
averageInfoGain = averageInfoGain / (double) validModels;
// Find "best" attribute to split on.
minResult = 0;
for (i = 0; i < data.numAttributes(); i++)
{
if ((i != (data).classIndex()) && (currentModel[i].checkModel()))
// Use 1E-3 here to get a closer approximation to the original
// implementation.
if ((currentModel[i].infoGain() >= (averageInfoGain - 1e-3)) && Utils.gr(currentModel[i].gainRatio(), minResult))
{
bestModel = currentModel[i];
minResult = currentModel[i].gainRatio();
}
}
// Check if useful split was found.
if (Utils.eq(minResult, 0))
return noSplitModel;
// Add all Instances with unknown values for the corresponding
// attribute to the distribution for the model, so that
// the complete distribution is stored with the model.
bestModel.distribution().addInstWithUnknown(data, bestModel.attIndex());
// Set the split point analogue to C45 if attribute numeric.
bestModel.SplitPoint = m_allData;
return bestModel;
}
catch (System.Exception e)
{
System.Console.WriteLine(e.StackTrace + " " + e.Message);
}
return null;
}
/// <summary> Generates the classifier.
///
/// </summary>
/// <param name="instances">set of instances serving as training data
/// </param>
/// <exception cref="Exception">if the classifier has not been generated successfully
/// </exception>
public override void buildClassifier(Instances instances)
{
//UPGRADE_TODO: The equivalent in .NET for field 'java.lang.Double.MAX_VALUE' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
double bestVal = System.Double.MaxValue, currVal;
//UPGRADE_TODO: The equivalent in .NET for field 'java.lang.Double.MAX_VALUE' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
double bestPoint = - System.Double.MaxValue, sum;
int bestAtt = - 1, numClasses;
if (instances.checkForStringAttributes())
{
throw new Exception("Can't handle string attributes!");
}
double[][] bestDist = new double[3][];
for (int i = 0; i < 3; i++)
{
bestDist[i] = new double[instances.numClasses()];
}
m_Instances = new Instances(instances);
m_Instances.deleteWithMissingClass();
if (m_Instances.numInstances() == 0)
{
throw new System.ArgumentException("No instances without missing " + "class values in training file!");
}
if (instances.numAttributes() == 1)
{
throw new System.ArgumentException("Attribute missing. Need at least one " + "attribute other than class attribute!");
}
if (m_Instances.classAttribute().Nominal)
{
numClasses = m_Instances.numClasses();
}
else
{
numClasses = 1;
}
// For each attribute
bool first = true;
for (int i = 0; i < m_Instances.numAttributes(); i++)
{
if (i != m_Instances.classIndex())
{
// Reserve space for distribution.
double[][] tmpArray = new double[3][];
for (int i2 = 0; i2 < 3; i2++)
{
tmpArray[i2] = new double[numClasses];
}
m_Distribution = tmpArray;
// Compute value of criterion for best split on attribute
if (m_Instances.attribute(i).Nominal)
{
currVal = findSplitNominal(i);
}
else
{
currVal = findSplitNumeric(i);
}
if ((first) || (currVal < bestVal))
{
bestVal = currVal;
bestAtt = i;
bestPoint = m_SplitPoint;
for (int j = 0; j < 3; j++)
{
Array.Copy(m_Distribution[j], 0, bestDist[j], 0, numClasses);
}
}
// First attribute has been investigated
first = false;
}
}
// Set attribute, split point and distribution.
m_AttIndex = bestAtt;
m_SplitPoint = bestPoint;
m_Distribution = bestDist;
if (m_Instances.classAttribute().Nominal)
{
for (int i = 0; i < m_Distribution.Length; i++)
{
double sumCounts = Utils.sum(m_Distribution[i]);
if (sumCounts == 0)
{
// This means there were only missing attribute values
Array.Copy(m_Distribution[2], 0, m_Distribution[i], 0, m_Distribution[2].Length);
Utils.normalize(m_Distribution[i]);
}
else
{
Utils.normalize(m_Distribution[i], sumCounts);
}
}
}
// Save memory
m_Instances = new Instances(m_Instances, 0);
}
