private void applyClassificationModelToolStripMenuItem_Click(object sender, EventArgs e)
{
return;
Instances ListInstancesTOClassify = GlobalInfo.CurrentScreen.CellBasedClassification.CreateInstancesWithoutClass(dt);
FastVector attVals = new FastVector();
for (int i = 0; i < GlobalInfo.CurrentScreen.CellBasedClassification.NumClasses; i++)
attVals.addElement(i.ToString());
ListInstancesTOClassify.insertAttributeAt(new weka.core.Attribute("Class", attVals), ListInstancesTOClassify.numAttributes());
ListInstancesTOClassify.setClassIndex(ListInstancesTOClassify.numAttributes() - 1);
List<int> ListIdx = new List<int>();
int Max = int.MinValue;
int Min = int.MaxValue;
for (int i = 0; i < ListInstancesTOClassify.numInstances(); i++)
{
Instance InstToProcess = ListInstancesTOClassify.instance(i);
int Value =(int)GlobalInfo.CurrentScreen.CellBasedClassification.J48Model.classifyInstance(InstToProcess);
if (Value > Max) Max = Value;
if (Value < Min) Min = Value;
ListIdx.Add(Value);
}
byte[][] LUT = GlobalInfo.LUT;
for (int j = 0; j < this.chartForPoints.Series[0].Points.Count; j++)
{
int ConvertedValue = (int)(((ListIdx[j] - Min) * (LUT[0].Length - 1)) / (Max - Min));
this.chartForPoints.Series[0].Points[j].MarkerColor = Color.FromArgb(LUT[0][ConvertedValue], LUT[1][ConvertedValue], LUT[2][ConvertedValue]);
}
}
public Identifier(Boolean isAnnotated, WhatWhyTrainer wwt)
{
this.isAnnotated = isAnnotated;
this.wwt = wwt;
listWhoCandidates = new List<Candidate>();
listWhenCandidates = new List<Candidate>();
listWhereCandidates = new List<Candidate>();
listWhatCandidates = new List<List<Token>>();
listWhyCandidates = new List<List<Token>>();
listSecondaryWhatCandidates = new List<Candidate>();
listSecondaryWhyCandidates = new List<Candidate>();
fvPOS = new FastVector(Token.PartOfSpeechTags.Length);
foreach (String POS in Token.PartOfSpeechTags)
{
fvPOS.addElement(POS);
}
whoClassifier = (Classifier)SerializationHelper.read(@"..\..\IdentifierModels\who.model");
whenClassifier = (Classifier)SerializationHelper.read(@"..\..\IdentifierModels\when.model");
whereClassifier = (Classifier)SerializationHelper.read(@"..\..\IdentifierModels\where.model");
//whatClassifier = (Classifier)SerializationHelper.read(@"..\..\IdentifierModels\what.model");
//whyClassifier = (Classifier)SerializationHelper.read(@"..\..\IdentifierModels\why.model");
initializeAnnotations();
}
//@ private invariant -1 <= m_SpecialXmlElement;
//@ private invariant m_SpecialXmlElement < m_Vector.size();
//@ private invariant m_SpecialXmlElement>=0 ==> m_Counter!=m_SpecialXmlElement;
/// <summary> Constructs an enumeration.
///
/// </summary>
/// <param name="vector">the vector which is to be enumerated
/// </param>
public FastVectorEnumeration(FastVector vector)
{
m_Counter = 0;
m_Vector = vector;
m_SpecialXmlElement = -1;
}
/// <summary> Constructs an enumeration with a special element.
/// The special element is skipped during the enumeration.
///
/// </summary>
/// <param name="vector">the vector which is to be enumerated
/// </param>
/// <param name="special">the index of the special element
/// </param>
//@ requires 0 <= special && special < vector.size();
public FastVectorEnumeration(FastVector vector, int special)
{
m_Vector = vector;
m_SpecialXmlElement = special;
if (special == 0)
{
m_Counter = 1;
}
else
{
m_Counter = 0;
}
}
public Instances CreateInstancesWithoutClass(cExtendedTable Input)
{
weka.core.FastVector atts = new FastVector();
int columnNo = 0;
// Descriptors loop
for (int i = 0; i < Input.Count; i++)
{
//if (ParentScreening.ListDescriptors[i].IsActive() == false) continue;
atts.addElement(new weka.core.Attribute(Input[i].Name));
columnNo++;
}
// weka.core.FastVector attVals = new FastVector();
Instances data1 = new Instances("MyRelation", atts, 0);
for (int IdxRow = 0; IdxRow < Input[0].Count; IdxRow++)
{
double[] vals = new double[data1.numAttributes()];
for (int Col = 0; Col < columnNo; Col++)
{
// if (Glo .ListDescriptors[Col].IsActive() == false) continue;
vals[Col] = Input[Col][IdxRow];// double.Parse(dt.Rows[IdxRow][Col].ToString());
}
data1.add(new DenseInstance(1.0, vals));
}
return data1;
}
/// <summary> Constructor creating an empty set of instances. Copies references
/// to the header information from the given set of instances. Sets
/// the capacity of the set of instances to 0 if its negative.
///
/// </summary>
/// <param name="instances">the instances from which the header
/// information is to be taken
/// </param>
/// <param name="capacity">the capacity of the new dataset
/// </param>
public Instances(Instances dataset, int capacity)
{
if (capacity < 0)
{
capacity = 0;
}
// Strings only have to be "shallow" copied because
// they can't be modified.
m_ClassIndex = dataset.m_ClassIndex;
m_RelationName = dataset.m_RelationName;
m_Attributes = dataset.m_Attributes;
m_Instances = new FastVector(capacity);
}
/// <summary>
/// Create a single instance for WEKA
/// </summary>
/// <param name="NClasses">Number of classes</param>
/// <returns>the weka instances</returns>
public Instances CreateInstanceForNClasses(cInfoClass InfoClass)
{
List<double> AverageList = new List<double>();
for (int i = 0; i < Parent.ListDescriptors.Count; i++)
if (Parent.ListDescriptors[i].IsActive()) AverageList.Add(GetAverageValuesList()[i]);
weka.core.FastVector atts = new FastVector();
List<string> NameList = Parent.ListDescriptors.GetListNameActives();
for (int i = 0; i < NameList.Count; i++)
atts.addElement(new weka.core.Attribute(NameList[i]));
weka.core.FastVector attVals = new FastVector();
for (int i = 0; i < InfoClass.NumberOfClass; i++)
attVals.addElement("Class" + i);
atts.addElement(new weka.core.Attribute("Class__", attVals));
Instances data1 = new Instances("SingleInstance", atts, 0);
double[] newTable = new double[AverageList.Count + 1];
Array.Copy(AverageList.ToArray(), 0, newTable, 0, AverageList.Count);
//newTable[AverageList.Count] = 1;
data1.add(new DenseInstance(1.0, newTable));
data1.setClassIndex((data1.numAttributes() - 1));
return data1;
}
/// <summary> Appends all elements of the supplied vector to this vector.
///
/// </summary>
/// <param name="toAppend">the FastVector containing elements to append.
/// </param>
public void appendXmlElements(FastVector toAppend)
{
Capacity = size() + toAppend.size();
Array.Copy(toAppend.m_Objects, 0, m_Objects, size(), toAppend.size());
m_Size = m_Objects.Length;
}
/// <summary> Produces a shallow copy of this vector.
///
/// </summary>
/// <returns> the new vector
/// </returns>
public System.Object copy()
{
FastVector copy = new FastVector(m_Objects.Length);
copy.m_Size = m_Size;
copy.m_CapacityIncrement = m_CapacityIncrement;
copy.m_CapacityMultiplier = m_CapacityMultiplier;
Array.Copy(m_Objects, 0, copy.m_Objects, 0, m_Size);
return copy;
}
/// <summary> Split up a string containing options into an array of strings,
/// one for each option.
///
/// </summary>
/// <param name="optionString">the string containing the options
/// </param>
/// <returns> the array of options
/// </returns>
public static System.String[] splitOptions(System.String quotedOptionString)
{
FastVector optionsVec = new FastVector();
System.String str = new System.Text.StringBuilder(quotedOptionString).ToString();
int i;
while (true)
{
//trimLeft
i = 0;
while ((i < str.Length) && (System.Char.IsWhiteSpace(str[i])))
i++;
str = str.Substring(i);
//stop when str is empty
if (str.Length == 0)
break;
//if str start with a double quote
if (str[0] == '"')
{
//find the first not anti-slached double quote
i = 1;
while (i < str.Length)
{
if (str[i] == str[0])
break;
if (str[i] == '\\')
{
i += 1;
if (i >= str.Length)
throw new System.Exception("String should not finish with \\");
if (str[i] != '\\' && str[i] != '"')
throw new System.Exception("Unknow character \\" + str[i]);
}
i += 1;
}
if (i >= str.Length)
throw new System.Exception("Quote parse error.");
//add the founded string to the option vector (without quotes)
System.String optStr = str.Substring(1, (i) - (1));
optStr = unbackQuoteChars(optStr);
optionsVec.addElement(optStr);
str = str.Substring(i + 1);
}
else
{
//find first whiteSpace
i = 0;
while ((i < str.Length) && (!System.Char.IsWhiteSpace(str[i])))
i++;
//add the founded string to the option vector
System.String optStr = str.Substring(0, (i) - (0));
optionsVec.addElement(optStr);
str = str.Substring(i);
}
}
//convert optionsVec to an array of String
System.String[] options = new System.String[optionsVec.size()];
for (i = 0; i < optionsVec.size(); i++)
{
options[i] = ((System.String) optionsVec.elementAt(i));
}
return options;
}
/// <summary> Removes all instances with missing values for a particular
/// attribute from the dataset.
///
/// </summary>
/// <param name="attIndex">the attribute's index
/// </param>
//@ requires 0 <= attIndex && attIndex < numAttributes();
public virtual void deleteWithMissing(int attIndex)
{
FastVector newInstances = new FastVector(numInstances());
for (int i = 0; i < numInstances(); i++)
{
if (!instance(i).isMissing(attIndex))
{
newInstances.addElement(instance(i));
}
}
m_Instances = newInstances;
}
/// <summary> Removes all instances from the set.</summary>
public virtual void delete()
{
m_Instances = new FastVector();
}
/// <summary> Creates an empty set of instances. Uses the given
/// attribute information. Sets the capacity of the set of
/// instances to 0 if its negative. Given attribute information
/// must not be changed after this constructor has been used.
///
/// </summary>
/// <param name="name">the name of the relation
/// </param>
/// <param name="attInfo">the attribute information
/// </param>
/// <param name="capacity">the capacity of the set
/// </param>
public Instances(System.String name, FastVector attInfo, int capacity)
{
m_RelationName = name;
m_ClassIndex = - 1;
m_Attributes = attInfo;
for (int i = 0; i < numAttributes(); i++)
{
attribute(i).Index = i;
}
m_Instances = new FastVector(capacity);
}
/// <summary> Method for testing this class.
///
/// </summary>
/// <param name="argv">should contain one element: the name of an ARFF file
/// </param>
//@ requires argv != null;
//@ requires argv.length == 1;
//@ requires argv[0] != null;
public static void test(System.String[] argv)
{
Instances instances, secondInstances, train, test, empty;
//Instance instance;
//UPGRADE_TODO: The differences in the expected value of parameters for constructor 'java.util.Random.Random' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
System.Random random = new System.Random((System.Int32) 2);
//UPGRADE_ISSUE: Class hierarchy differences between 'java.io.Reader' and 'System.IO.StreamReader' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1186'"
System.IO.StreamReader reader;
int start, num;
//double newWeight;
FastVector testAtts, testVals;
int i, j;
try
{
if (argv.Length > 1)
{
throw (new System.Exception("Usage: Instances [<filename>]"));
}
// Creating set of instances from scratch
testVals = new FastVector(2);
testVals.addElement("first_value");
testVals.addElement("second_value");
testAtts = new FastVector(2);
testAtts.addElement(new Attribute("nominal_attribute", testVals));
testAtts.addElement(new Attribute("numeric_attribute"));
instances = new Instances("test_set", testAtts, 10);
instances.add(new Instance(instances.numAttributes()));
instances.add(new Instance(instances.numAttributes()));
instances.add(new Instance(instances.numAttributes()));
instances.ClassIndex = 0;
System.Console.Out.WriteLine("\nSet of instances created from scratch:\n");
//UPGRADE_TODO: Method 'java.io.PrintStream.println' was converted to 'System.Console.Out.WriteLine' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javaioPrintStreamprintln_javalangObject'"
System.Console.Out.WriteLine(instances);
if (argv.Length == 1)
{
System.String filename = argv[0];
//UPGRADE_TODO: Constructor 'java.io.FileReader.FileReader' was converted to 'System.IO.StreamReader' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073'"
reader = new System.IO.StreamReader(filename, System.Text.Encoding.Default);
// Read first five instances and print them
System.Console.Out.WriteLine("\nFirst five instances from file:\n");
instances = new Instances(reader, 1);
instances.ClassIndex = instances.numAttributes() - 1;
i = 0;
while ((i < 5) && (instances.readInstance(reader)))
{
i++;
}
//UPGRADE_TODO: Method 'java.io.PrintStream.println' was converted to 'System.Console.Out.WriteLine' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javaioPrintStreamprintln_javalangObject'"
System.Console.Out.WriteLine(instances);
// Read all the instances in the file
//UPGRADE_TODO: Constructor 'java.io.FileReader.FileReader' was converted to 'System.IO.StreamReader' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073'"
reader = new System.IO.StreamReader(filename, System.Text.Encoding.Default);
instances = new Instances(reader);
// Make the last attribute be the class
instances.ClassIndex = instances.numAttributes() - 1;
// Print header and instances.
System.Console.Out.WriteLine("\nDataset:\n");
//UPGRADE_TODO: Method 'java.io.PrintStream.println' was converted to 'System.Console.Out.WriteLine' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javaioPrintStreamprintln_javalangObject'"
System.Console.Out.WriteLine(instances);
System.Console.Out.WriteLine("\nClass index: " + instances.classIndex());
}
// Test basic methods based on class index.
System.Console.Out.WriteLine("\nClass name: " + instances.classAttribute().name());
System.Console.Out.WriteLine("\nClass index: " + instances.classIndex());
System.Console.Out.WriteLine("\nClass is nominal: " + instances.classAttribute().Nominal);
System.Console.Out.WriteLine("\nClass is numeric: " + instances.classAttribute().Numeric);
System.Console.Out.WriteLine("\nClasses:\n");
for (i = 0; i < instances.numClasses(); i++)
{
System.Console.Out.WriteLine(instances.classAttribute().value_Renamed(i));
}
System.Console.Out.WriteLine("\nClass values and labels of instances:\n");
for (i = 0; i < instances.numInstances(); i++)
{
Instance inst = instances.instance(i);
System.Console.Out.Write(inst.classValue() + "\t");
System.Console.Out.Write(inst.toString(inst.classIndex()));
if (instances.instance(i).classIsMissing())
{
System.Console.Out.WriteLine("\tis missing");
}
else
{
System.Console.Out.WriteLine();
}
}
// Create random weights.
System.Console.Out.WriteLine("\nCreating random weights for instances.");
for (i = 0; i < instances.numInstances(); i++)
{
instances.instance(i).Weight = random.NextDouble();
}
// Print all instances and their weights (and the sum of weights).
System.Console.Out.WriteLine("\nInstances and their weights:\n");
System.Console.Out.WriteLine(instances.instancesAndWeights());
System.Console.Out.Write("\nSum of weights: ");
System.Console.Out.WriteLine(instances.sumOfWeights());
// Insert an attribute
secondInstances = new Instances(instances);
Attribute testAtt = new Attribute("Inserted");
secondInstances.insertAttributeAt(testAtt, 0);
System.Console.Out.WriteLine("\nSet with inserted attribute:\n");
//UPGRADE_TODO: Method 'java.io.PrintStream.println' was converted to 'System.Console.Out.WriteLine' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javaioPrintStreamprintln_javalangObject'"
System.Console.Out.WriteLine(secondInstances);
System.Console.Out.WriteLine("\nClass name: " + secondInstances.classAttribute().name());
// Delete the attribute
secondInstances.deleteAttributeAt(0);
System.Console.Out.WriteLine("\nSet with attribute deleted:\n");
//UPGRADE_TODO: Method 'java.io.PrintStream.println' was converted to 'System.Console.Out.WriteLine' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javaioPrintStreamprintln_javalangObject'"
System.Console.Out.WriteLine(secondInstances);
System.Console.Out.WriteLine("\nClass name: " + secondInstances.classAttribute().name());
// Test if headers are equal
System.Console.Out.WriteLine("\nHeaders equal: " + instances.equalHeaders(secondInstances) + "\n");
// Print data in internal format.
System.Console.Out.WriteLine("\nData (internal values):\n");
for (i = 0; i < instances.numInstances(); i++)
{
for (j = 0; j < instances.numAttributes(); j++)
{
if (instances.instance(i).isMissing(j))
{
System.Console.Out.Write("? ");
}
else
{
System.Console.Out.Write(instances.instance(i).value_Renamed(j) + " ");
}
}
System.Console.Out.WriteLine();
}
// Just print header
System.Console.Out.WriteLine("\nEmpty dataset:\n");
empty = new Instances(instances, 0);
//UPGRADE_TODO: Method 'java.io.PrintStream.println' was converted to 'System.Console.Out.WriteLine' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javaioPrintStreamprintln_javalangObject'"
System.Console.Out.WriteLine(empty);
System.Console.Out.WriteLine("\nClass name: " + empty.classAttribute().name());
// Create copy and rename an attribute and a value (if possible)
if (empty.classAttribute().Nominal)
{
Instances copy = new Instances(empty, 0);
copy.renameAttribute(copy.classAttribute(), "new_name");
copy.renameAttributeValue(copy.classAttribute(), copy.classAttribute().value_Renamed(0), "new_val_name");
System.Console.Out.WriteLine("\nDataset with names changed:\n" + copy);
System.Console.Out.WriteLine("\nOriginal dataset:\n" + empty);
}
// Create and prints subset of instances.
start = instances.numInstances() / 4;
num = instances.numInstances() / 2;
System.Console.Out.Write("\nSubset of dataset: ");
System.Console.Out.WriteLine(num + " instances from " + (start + 1) + ". instance");
secondInstances = new Instances(instances, start, num);
System.Console.Out.WriteLine("\nClass name: " + secondInstances.classAttribute().name());
// Print all instances and their weights (and the sum of weights).
System.Console.Out.WriteLine("\nInstances and their weights:\n");
System.Console.Out.WriteLine(secondInstances.instancesAndWeights());
System.Console.Out.Write("\nSum of weights: ");
System.Console.Out.WriteLine(secondInstances.sumOfWeights());
// Create and print training and test sets for 3-fold
// cross-validation.
System.Console.Out.WriteLine("\nTrain and test folds for 3-fold CV:");
if (instances.classAttribute().Nominal)
{
instances.stratify(3);
}
for (j = 0; j < 3; j++)
{
//UPGRADE_TODO: The differences in the expected value of parameters for constructor 'java.util.Random.Random' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
train = instances.trainCV(3, j, new System.Random((System.Int32) 1));
test = instances.testCV(3, j);
// Print all instances and their weights (and the sum of weights).
System.Console.Out.WriteLine("\nTrain: ");
System.Console.Out.WriteLine("\nInstances and their weights:\n");
System.Console.Out.WriteLine(train.instancesAndWeights());
System.Console.Out.Write("\nSum of weights: ");
System.Console.Out.WriteLine(train.sumOfWeights());
System.Console.Out.WriteLine("\nClass name: " + train.classAttribute().name());
System.Console.Out.WriteLine("\nTest: ");
System.Console.Out.WriteLine("\nInstances and their weights:\n");
System.Console.Out.WriteLine(test.instancesAndWeights());
System.Console.Out.Write("\nSum of weights: ");
System.Console.Out.WriteLine(test.sumOfWeights());
System.Console.Out.WriteLine("\nClass name: " + test.classAttribute().name());
}
// Randomize instances and print them.
System.Console.Out.WriteLine("\nRandomized dataset:");
instances.randomize(random);
// Print all instances and their weights (and the sum of weights).
System.Console.Out.WriteLine("\nInstances and their weights:\n");
System.Console.Out.WriteLine(instances.instancesAndWeights());
System.Console.Out.Write("\nSum of weights: ");
System.Console.Out.WriteLine(instances.sumOfWeights());
// Sort instances according to first attribute and
// print them.
System.Console.Out.Write("\nInstances sorted according to first attribute:\n ");
instances.sort(0);
// Print all instances and their weights (and the sum of weights).
System.Console.Out.WriteLine("\nInstances and their weights:\n");
System.Console.Out.WriteLine(instances.instancesAndWeights());
System.Console.Out.Write("\nSum of weights: ");
System.Console.Out.WriteLine(instances.sumOfWeights());
}
catch (System.Exception)
{
//.WriteStackTrace(e, Console.Error);
}
}
/// <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> Help function needed for stratification of set.
///
/// </summary>
/// <param name="numFolds">the number of folds for the stratification
/// </param>
protected internal virtual void stratStep(int numFolds)
{
FastVector newVec = new FastVector(m_Instances.capacity());
int start = 0, j;
// create stratified batch
while (newVec.size() < numInstances())
{
j = start;
while (j < numInstances())
{
newVec.addElement(instance(j));
j = j + numFolds;
}
start++;
}
m_Instances = newVec;
}
/// <summary> Replaces the attribute information by a clone of
/// itself.
/// </summary>
protected internal virtual void freshAttributeInfo()
{
m_Attributes = (FastVector) m_Attributes.copyXmlElements();
}
public void PerformClassification()
{
FormForSingleCellClassifOptions FFSC = new FormForSingleCellClassifOptions();
//cGUI_ListClasses GLC = new cGUI_ListClasses();
//GLC.ClassType = eClassType.PHENOTYPE;
//GLC.IsCheckBoxes = true;
//GLC.IsSelectAll = true;
//GLC.Run(GlobalInfo);
PanelForClassSelection PhenotypeSelectionPanel = new PanelForClassSelection( true, eClassType.PHENOTYPE);
PhenotypeSelectionPanel.Height = FFSC.panelPhenoToBeClassified.Height;
FFSC.panelPhenoToBeClassified.Controls.Add(PhenotypeSelectionPanel);
PanelForClassSelection WellClassSelectionPanel = new PanelForClassSelection( true, eClassType.WELL);
WellClassSelectionPanel.Height = FFSC.panelWellToBeClassified.Height;
FFSC.panelWellToBeClassified.Controls.Add(WellClassSelectionPanel);
PanelForPlatesSelection PlatesSelectionPanel = new PanelForPlatesSelection( true, null, true);
PlatesSelectionPanel.Height = FFSC.panelWellToBeClassified.Height;
FFSC.tabPagePlates.Controls.Add(PlatesSelectionPanel);
if (FFSC.ShowDialog() != DialogResult.OK) return;
// ----------------------- Classification ------------------------------
int DescrCount = cGlobalInfo.CurrentScreening.ListDescriptors.Count;
this.UpDateNumberOfCluster();
if (NumberOfClusters == 0)
{
System.Windows.Forms.MessageBox.Show("Number of cluster is null", "Error !", MessageBoxButtons.OK, MessageBoxIcon.Hand);
return;
}
//if (FFSC.checkBoxGenerationRatio.Checked)
//{
// // first we update the descriptor
// for (int i = 0; i < this.NumberOfClusters; i++)
// GlobalInfo.CurrentScreening.ListDescriptors.AddNew(new cDescriptorType("Ratio_" + GlobalInfo.ListCellularPhenotypes[i].Name, true, 1, GlobalInfo));
//}
FormForProgress ProgressWindow = new FormForProgress();
ProgressWindow.Show();
int IdxProgress = 0;
int MaxProgress = 0;
#region Confusion Matrix init
cListExtendedTable LT = new cListExtendedTable();
cExtendedTable ConfusionMatrix = new cExtendedTable(cGlobalInfo.ListCellularPhenotypes.Count, cGlobalInfo.ListCellularPhenotypes.Count, 0);
ConfusionMatrix.Name = "Confusion Matrix (global)";
ConfusionMatrix.ListRowNames = new List<string>();
for (int i = 0; i < cGlobalInfo.ListCellularPhenotypes.Count; i++)
{
ConfusionMatrix.ListRowNames.Add(cGlobalInfo.ListCellularPhenotypes[i].Name + "*");
ConfusionMatrix[i].Name = cGlobalInfo.ListCellularPhenotypes[i].Name;
}
LT.Add(ConfusionMatrix);
for (int i = 0; i < cGlobalInfo.ListWellClasses.Count; i++)
{
cExtendedTable ConfusionMatrixTmp = new cExtendedTable(cGlobalInfo.ListCellularPhenotypes.Count, cGlobalInfo.ListCellularPhenotypes.Count, 0);
ConfusionMatrixTmp.Name = "Confusion Matrix - " + cGlobalInfo.ListWellClasses[i].Name;
ConfusionMatrixTmp.ListRowNames = new List<string>();
for (int j = 0; j < cGlobalInfo.ListCellularPhenotypes.Count; j++)
{
ConfusionMatrixTmp.ListRowNames.Add(cGlobalInfo.ListCellularPhenotypes[j].Name + "*");
ConfusionMatrixTmp[j].Name =cGlobalInfo.ListCellularPhenotypes[j].Name;
}
LT.Add(ConfusionMatrixTmp);
}
#endregion
cListPlates LP = PlatesSelectionPanel.GetListSelectedPlates();
foreach (cPlate CurrentPlateToProcess in LP /*GlobalInfo.CurrentScreening.ListPlatesAvailable*/)
MaxProgress += (int)CurrentPlateToProcess.ListActiveWells.Count;
ProgressWindow.progressBar.Maximum = MaxProgress;
FastVector attVals = new FastVector();
for (int i = 0; i < this.NumberOfClusters; i++)
attVals.addElement(i.ToString());
cPlate CurrentDispPlate = cGlobalInfo.CurrentScreening.GetCurrentDisplayPlate();
foreach (cPlate CurrentPlateToProcess in LP/* GlobalInfo.CurrentScreening.ListPlatesAvailable*/)
{
foreach (cWell TmpWell in CurrentPlateToProcess.ListActiveWells)
{
ProgressWindow.progressBar.Value = IdxProgress++;
if (TmpWell.GetCurrentClassIdx() == -1) continue;
if (WellClassSelectionPanel.ListCheckBoxes[TmpWell.GetCurrentClassIdx()].Checked == false) continue;
DataTable FinalDataTable = new DataTable();
TmpWell.AssociatedPlate.DBConnection = new cDBConnection(TmpWell.AssociatedPlate, TmpWell.SQLTableName);
TmpWell.AssociatedPlate.DBConnection.AddWellToDataTable(TmpWell, FinalDataTable, this.GlobalInfo);
cListSingleBiologicalObjects LSBO = TmpWell.AssociatedPlate.DBConnection.GetBiologicalPhenotypes(TmpWell);
//TmpWell.AssociatedPlate.DBConnection.AddWellToDataTable(TmpWell, FinalDataTable, checkBoxIncludeWellClassAsDesc.Checked, GlobalInfo);
Instances ListInstancesTOClassify = this.CreateInstancesWithoutClass(FinalDataTable);
ListInstancesTOClassify.insertAttributeAt(new weka.core.Attribute("Class", attVals), ListInstancesTOClassify.numAttributes());
ListInstancesTOClassify.setClassIndex(ListInstancesTOClassify.numAttributes() - 1);
cExtendedList ListNewClasses = new cExtendedList();
int NumInstances = ListInstancesTOClassify.numInstances();
for (int i = 0; i < NumInstances; i++)
{
// ClassId contains the new class
Instance CurrentInst = ListInstancesTOClassify.instance(i);
double classId = this.CurrentClassifier.classifyInstance(CurrentInst);
double[] ClassConfidence = this.CurrentClassifier.distributionForInstance(CurrentInst);
LSBO[i].ClassificationConfidence = ClassConfidence[(int)classId];
ListNewClasses.Add(classId);
if (CurrentPlateToProcess == CurrentDispPlate)
{
LT[0][LSBO[i].GetAssociatedPhenotype().Idx][(int)classId]++;
if (TmpWell.GetCurrentClassIdx() >= 0)
LT[TmpWell.GetCurrentClassIdx() + 1][LSBO[i].GetAssociatedPhenotype().Idx][(int)classId]++;
}
}
ProgressWindow.richTextBoxForComment.AppendText(TmpWell.GetShortInfo().Remove(TmpWell.GetShortInfo().Length - 2) + " : " + NumInstances + " objects\n");
ProgressWindow.Refresh();
// ------------- update class within the database -----------------------------
TmpWell.AssociatedPlate.DBConnection.ChangePhenotypeClass(TmpWell, ListNewClasses);
//if (FFSC.checkBoxGenerationRatio.Checked)
//{
// List<double[]> Histo = ListNewClasses.CreateHistogram(0, ListInstancesTOClassify.numClasses(), ListInstancesTOClassify.numClasses());
// cListSignature LDesc = new cListSignature();
// for (int IdxHisto = 0; IdxHisto < Histo[1].Length - 1; IdxHisto++)
// {
// Histo[1][IdxHisto] = (100.0 * Histo[1][IdxHisto]) / (double)ListInstancesTOClassify.numInstances();
// cSignature NewDesc = new cSignature(Histo[1][IdxHisto], GlobalInfo.CurrentScreening.ListDescriptors[IdxHisto + DescrCount], GlobalInfo.CurrentScreening);
// LDesc.Add(NewDesc);
// }
// TmpWell.AddSignatures(LDesc);
//}
TmpWell.AssociatedPlate.DBConnection.CloseConnection();
}
}
#region Display Report
cDesignerSplitter DS = new cDesignerSplitter();
DS.Orientation = Orientation.Vertical;
cViewertext VTEXT = new cViewertext();
VTEXT.SetInputData(ProgressWindow.richTextBoxForComment.Text);
VTEXT.Run();
cDesignerTab DT = new cDesignerTab();
DT.IsMultiline = false;
foreach (var item in LT)
{
cViewerTable VT = new cViewerTable();
VT.SetInputData(item);
VT.DigitNumber = 0;
VT.Run();
DT.SetInputData(VT.GetOutPut());
}
DT.Run();
cExtendedControl TextEC = DT.GetOutPut();
TextEC.Width = 0;
TextEC.Height = 0;
TextEC.Anchor = (System.Windows.Forms.AnchorStyles)(System.Windows.Forms.AnchorStyles.Top | System.Windows.Forms.AnchorStyles.Bottom
| System.Windows.Forms.AnchorStyles.Left
| System.Windows.Forms.AnchorStyles.Right);
DS.SetInputData(VTEXT.GetOutPut());
DS.SetInputData(TextEC);
DS.Run();
ProgressWindow.Close();
cDisplayToWindow CDT = new cDisplayToWindow();
CDT.SetInputData(DS.GetOutPut());
CDT.IsModal = true;
CDT.Title = "Phenotypic Classificaton Report";
CDT.Run();
CDT.Display();
#endregion
//if (IsKeepOriginalDesc == System.Windows.Forms.DialogResult.No)
//{
// // int DescNumToRemove = GlobalInfo.CurrentScreen.ListDescriptors.Count -
// for (int IdxDesc = 0; IdxDesc < DescrCount; IdxDesc++)
// GlobalInfo.CurrentScreening.ListDescriptors.RemoveDesc(GlobalInfo.CurrentScreening.ListDescriptors[0], GlobalInfo.CurrentScreening);
//}
cGlobalInfo.CurrentScreening.ListDescriptors.UpDateDisplay();
cGlobalInfo.CurrentScreening.UpDatePlateListWithFullAvailablePlate();
for (int idxP = 0; idxP < cGlobalInfo.CurrentScreening.ListPlatesActive.Count; idxP++)
cGlobalInfo.CurrentScreening.ListPlatesActive[idxP].UpDataMinMax();
//WindowFormForCellbyCellClassif.Close();
//WindowClusteringInfo.Close();
}
/// <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>
/// Create an instances structure with classes for supervised methods
/// </summary>
/// <param name="NumClass"></param>
/// <returns></returns>
public Instances CreateInstancesWithClasses(cInfoClass InfoClass, int NeutralClass)
{
weka.core.FastVector atts = new FastVector();
int columnNo = 0;
for (int i = 0; i < ParentScreening.ListDescriptors.Count; i++)
{
if (ParentScreening.ListDescriptors[i].IsActive() == false) continue;
atts.addElement(new weka.core.Attribute(ParentScreening.ListDescriptors[i].GetName()));
columnNo++;
}
weka.core.FastVector attVals = new FastVector();
for (int i = 0; i < InfoClass.NumberOfClass; i++)
attVals.addElement("Class__" + (i).ToString());
atts.addElement(new weka.core.Attribute("Class__", attVals));
Instances data1 = new Instances("MyRelation", atts, 0);
int IdxWell = 0;
foreach (cWell CurrentWell in this.ListActiveWells)
{
if (CurrentWell.GetCurrentClassIdx() == NeutralClass) continue;
double[] vals = new double[data1.numAttributes()];
int IdxCol = 0;
for (int Col = 0; Col < ParentScreening.ListDescriptors.Count; Col++)
{
if (ParentScreening.ListDescriptors[Col].IsActive() == false) continue;
vals[IdxCol++] = CurrentWell.ListSignatures[Col].GetValue();
}
vals[columnNo] = InfoClass.CorrespondanceTable[CurrentWell.GetCurrentClassIdx()];
data1.add(new DenseInstance(1.0, vals));
IdxWell++;
}
data1.setClassIndex((data1.numAttributes() - 1));
return data1;
}
/// <summary>
/// Create an instances structure with classes for supervised methods
/// </summary>
/// <param name="NumClass"></param>
/// <returns></returns>
public Instances CreateInstancesWithClasses(List<bool> ListClassSelected)
{
weka.core.FastVector atts = new FastVector();
int columnNo = 0;
for (int i = 0; i < ParentScreening.ListDescriptors.Count; i++)
{
if (ParentScreening.ListDescriptors[i].IsActive() == false) continue;
atts.addElement(new weka.core.Attribute(ParentScreening.ListDescriptors[i].GetName()));
columnNo++;
}
weka.core.FastVector attVals = new FastVector();
foreach (var item in cGlobalInfo.ListWellClasses)
{
attVals.addElement(item.Name);
}
atts.addElement(new weka.core.Attribute("ClassAttribute", attVals));
Instances data1 = new Instances("MyRelation", atts, 0);
int IdxWell = 0;
foreach (cWell CurrentWell in this.ListActiveWells)
{
if (!ListClassSelected[CurrentWell.GetCurrentClassIdx()]) continue;
double[] vals = new double[data1.numAttributes()];
int IdxCol = 0;
for (int Col = 0; Col < ParentScreening.ListDescriptors.Count; Col++)
{
if (ParentScreening.ListDescriptors[Col].IsActive() == false) continue;
vals[IdxCol++] = CurrentWell.ListSignatures[Col].GetValue();
}
vals[columnNo] = CurrentWell.GetCurrentClassIdx();
data1.add(new DenseInstance(1.0, vals));
IdxWell++;
}
data1.setClassIndex((data1.numAttributes() - 1));
return data1;
}
/// <summary>
/// Create an instances structure with classes for supervised methods
/// </summary>
/// <param name="NumClass"></param>
/// <returns></returns>
public Instances CreateInstancesWithClassesWithPlateBasedDescriptor(int NumberOfClass)
{
weka.core.FastVector atts = new FastVector();
int columnNo = 0;
for (int i = 0; i < ParentScreening.ListPlateBaseddescriptorNames.Count; i++)
{
atts.addElement(new weka.core.Attribute(ParentScreening.ListPlateBaseddescriptorNames[i]));
columnNo++;
}
weka.core.FastVector attVals = new FastVector();
for (int i = 0; i < NumberOfClass; i++)
attVals.addElement("Class" + (i).ToString());
atts.addElement(new weka.core.Attribute("Class", attVals));
Instances data1 = new Instances("MyRelation", atts, 0);
int IdxWell = 0;
foreach (cWell CurrentWell in this.ListActiveWells)
{
if (CurrentWell.GetCurrentClassIdx() == -1) continue;
double[] vals = new double[data1.numAttributes()];
int IdxCol = 0;
for (int Col = 0; Col < ParentScreening.ListPlateBaseddescriptorNames.Count; Col++)
{
vals[IdxCol++] = CurrentWell.ListPlateBasedDescriptors[Col].GetValue();
}
vals[columnNo] = CurrentWell.GetCurrentClassIdx();
data1.add(new DenseInstance(1.0, vals));
IdxWell++;
}
data1.setClassIndex((data1.numAttributes() - 1));
return data1;
}
/// <summary> Set the output format if the class is nominal.</summary>
private void setOutputFormat()
{
FastVector newAtts;
int newClassIndex;
System.Text.StringBuilder attributeName;
Instances outputFormat;
FastVector vals;
// Compute new attributes
newClassIndex = getInputFormat().classIndex();
newAtts = new FastVector();
for (int j = 0; j < getInputFormat().numAttributes(); j++)
{
weka.core.Attribute att = getInputFormat().attribute(j);
if (!att.Nominal || (j == getInputFormat().classIndex()) || !m_Columns.isInRange(j))
{
newAtts.addElement(att.copy());
}
else
{
if (att.numValues() <= 2)
{
if (m_Numeric)
{
newAtts.addElement(new weka.core.Attribute(att.name()));
}
else
{
newAtts.addElement(att.copy());
}
}
else
{
if (newClassIndex >= 0 && j < getInputFormat().classIndex())
{
newClassIndex += att.numValues() - 1;
}
// Compute values for new attributes
for (int k = 0; k < att.numValues(); k++)
{
attributeName = new System.Text.StringBuilder(att.name() + "=");
attributeName.Append(att.value_Renamed(k));
if (m_Numeric)
{
newAtts.addElement(new weka.core.Attribute(attributeName.ToString()));
}
else
{
vals = new FastVector(2);
vals.addElement("f"); vals.addElement("t");
newAtts.addElement(new weka.core.Attribute(attributeName.ToString(), vals));
}
}
}
}
}
outputFormat = new Instances(getInputFormat().relationName(), newAtts, 0);
outputFormat.ClassIndex = newClassIndex;
setOutputFormat(outputFormat);
}
/// <summary>
/// Create an instances structure without classes for unsupervised methods
/// </summary>
/// <returns>a weka Instances object</returns>
public Instances CreateInstancesWithoutClass()
{
weka.core.FastVector atts = new FastVector();
int columnNo = 0;
// Descriptors loop
for (int i = 0; i < ParentScreening.ListDescriptors.Count; i++)
{
if (ParentScreening.ListDescriptors[i].IsActive() == false) continue;
atts.addElement(new weka.core.Attribute(ParentScreening.ListDescriptors[i].GetName()));
columnNo++;
}
weka.core.FastVector attVals = new FastVector();
Instances data1 = new Instances("MyRelation", atts, 0);
foreach (cWell CurrentWell in this.ListActiveWells)
{
double[] vals = new double[data1.numAttributes()];
int IdxRealCol = 0;
for (int Col = 0; Col < ParentScreening.ListDescriptors.Count; Col++)
{
if (ParentScreening.ListDescriptors[Col].IsActive() == false) continue;
vals[IdxRealCol++] = CurrentWell.ListSignatures[Col].GetValue();
}
data1.add(new DenseInstance(1.0, vals));
}
return data1;
}
/// <summary> Clones the vector and shallow copies all its elements.
/// The elements have to implement the Copyable interface.
///
/// </summary>
/// <returns> the new vector
/// </returns>
public System.Object copyXmlElements()
{
FastVector copy = new FastVector(m_Objects.Length);
copy.m_Size = m_Size;
copy.m_CapacityIncrement = m_CapacityIncrement;
copy.m_CapacityMultiplier = m_CapacityMultiplier;
for (int i = 0; i < m_Size; i++)
{
copy.m_Objects[i] = ((Copyable) m_Objects[i]).copy();
}
return copy;
}
/// <summary> Reads the header of an ARFF file from a reader and
/// reserves space for the given number of instances. Lets
/// the class index be undefined (negative).
///
/// </summary>
/// <param name="reader">the reader
/// </param>
/// <param name="capacity">the capacity
/// </param>
/// <exception cref="IllegalArgumentException">if the header is not read successfully
/// or the capacity is negative.
/// </exception>
/// <exception cref="IOException">if there is a problem with the reader.
/// </exception>
//@ requires capacity >= 0;
//@ ensures classIndex() == -1;
//UPGRADE_ISSUE: Class hierarchy differences between 'java.io.Reader' and 'System.IO.StreamReader' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1186'"
public Instances(System.IO.StreamReader reader, int capacity)
{
StreamTokenizer tokenizer;
if (capacity < 0)
{
throw new System.ArgumentException("Capacity has to be positive!");
}
tokenizer = new StreamTokenizer(reader);
initTokenizer(tokenizer);
readHeader(tokenizer);
m_ClassIndex = - 1;
m_Instances = new FastVector(capacity);
}
private static Instances CreateInstanceOnFly(double[] a, double[] b)
{
FastVector atts;
Instances data;
double[] vals;
// 1. set up attributes
atts = new FastVector();
// - numeric
atts.addElement(new Attribute("att1"));
atts.addElement(new Attribute("att2"));
// 2. create Instances object
data = new Instances("MyRelation", atts, 0);
for (int i = 0; i < a.Length; ++i)
{
// 3. fill with data
// first instance
vals = new double[data.numAttributes()];
// - numeric
vals[0] = a[i];
// - nominal
vals[1] = b[i];
data.add(new weka.core.DenseInstance(1.0, vals));
}
return data;
}
///
/// <summary> * Sets the format of output instances. </summary>
///
private void setOutputFormat()
{
// give names to the new attributes
FastVector newAtts = new FastVector();
string foName = null;
for (int i = 0; i < getInputFormat().numAttributes(); i++)
{
string attName = getInputFormat().attribute(i).name();
foName = "'FT " + attName.Replace('\'', ' ').Trim() + " (re)\'";
Attribute newAttribX = new Attribute(foName);
newAtts.addElement(newAttribX);
foName = "'FT " + attName.Replace('\'', ' ').Trim() + " (im)\'";
Attribute newAttribY = new Attribute(foName);
newAtts.addElement(newAttribY);
}
setOutputFormat(new Instances(getInputFormat().relationName(), newAtts, getNumCoeffs()));
}
public cInfoForHierarchical CreateInstancesWithUniqueClasse()
{
cInfoForHierarchical InfoForHierarchical = new cInfoForHierarchical();
weka.core.FastVector atts = new FastVector();
int columnNo = 0;
for (int i = 0; i < this.ParentScreening.ListDescriptors.Count; i++)
{
if (this.ParentScreening.ListDescriptors[i].IsActive() == false) continue;
atts.addElement(new weka.core.Attribute(this.ParentScreening.ListDescriptors[i].GetName()));
columnNo++;
}
weka.core.FastVector attVals = new FastVector();
atts.addElement(new weka.core.Attribute("Class_____", attVals));
InfoForHierarchical.ListInstances = new Instances("MyRelation", atts, 0);
int IdxWell = 0;
foreach (cWell CurrentWell in this.ListActiveWells)
{
if (CurrentWell.GetCurrentClassIdx() == -1) continue;
attVals.addElement("Class_____" + (IdxWell).ToString());
InfoForHierarchical.ListIndexedWells.Add(CurrentWell);
double[] vals = new double[InfoForHierarchical.ListInstances.numAttributes()];
int IdxCol = 0;
for (int Col = 0; Col < this.ParentScreening.ListDescriptors.Count; Col++)
{
if (this.ParentScreening.ListDescriptors[Col].IsActive() == false) continue;
vals[IdxCol++] = CurrentWell.ListSignatures[Col].GetValue();
}
vals[columnNo] = IdxWell;
InfoForHierarchical.ListInstances.add(new DenseInstance(1.0, vals));
IdxWell++;
}
InfoForHierarchical.ListInstances.setClassIndex((InfoForHierarchical.ListInstances.numAttributes() - 1));
return InfoForHierarchical;
}
/// <summary> Reads and stores header of an ARFF file.
///
/// </summary>
/// <param name="tokenizer">the stream tokenizer
/// </param>
/// <exception cref="IOException">if the information is not read
/// successfully
/// </exception>
protected internal virtual void readHeader(StreamTokenizer tokenizer)
{
System.String attributeName;
FastVector attributeValues;
//int i;
Token token=null;
// Get name of relation.
getFirstToken(tokenizer, out token);
//if (tokenizer.ttype == SupportClass.StreamTokenizerSupport.TT_EOF)
if ((token != null) && (token is EofToken))
{
errms(tokenizer, "premature end of file");
}
if (ARFF_RELATION.ToUpper().Equals(token.StringValue.ToUpper()))
{
getNextToken(tokenizer,out token);
m_RelationName = token.StringValue;
getLastToken(tokenizer,out token, false);
}
else
{
errms(tokenizer, "keyword " + ARFF_RELATION + " expected");
}
// Create vectors to hold information temporarily.
m_Attributes = new FastVector();
// Get attribute declarations.
getFirstToken(tokenizer, out token);
//if (tokenizer.ttype == SupportClass.StreamTokenizerSupport.TT_EOF)
if ((token != null) && (token is EofToken))
{
errms(tokenizer, "premature end of file");
}
while (Attribute.ARFF_ATTRIBUTE.ToUpper().Equals(token.StringValue.ToUpper()))
{
// Get attribute name.
getNextToken(tokenizer,out token);
attributeName = token.StringValue;
getNextToken(tokenizer,out token);
// Check if attribute is nominal.
//if (tokenizer.ttype == SupportClass.StreamTokenizerSupport.TT_WORD)
if ((token != null) && (token is WordToken))
{
// Attribute is real, integer, or string.
if (token.StringValue.ToUpper().Equals(Attribute.ARFF_ATTRIBUTE_REAL.ToUpper()) || token.StringValue.ToUpper().Equals(Attribute.ARFF_ATTRIBUTE_INTEGER.ToUpper()) || token.StringValue.ToUpper().Equals(Attribute.ARFF_ATTRIBUTE_NUMERIC.ToUpper()))
{
m_Attributes.addElement(new Attribute(attributeName, numAttributes()));
readTillEOL(tokenizer);
}
else if (token.StringValue.ToUpper().Equals(Attribute.ARFF_ATTRIBUTE_STRING.ToUpper()))
{
m_Attributes.addElement(new Attribute(attributeName, (FastVector) null, numAttributes()));
readTillEOL(tokenizer);
}
else if (token.StringValue.ToUpper().Equals(Attribute.ARFF_ATTRIBUTE_DATE.ToUpper()))
{
System.String format = null;
tokenizer.NextToken(out token);
//if (tokenizer.NextToken() != SupportClass.StreamTokenizerSupport.TT_EOL)
if ((token != null) && (!(token is EofToken)))
{
//if ((tokenizer.ttype != SupportClass.StreamTokenizerSupport.TT_WORD) && (tokenizer.ttype != '\'') && (tokenizer.ttype != '\"'))
if ((token != null) && (!(token is WordToken)) && (token.StringValue!="'") && (token.StringValue!="\"") )
{
errms(tokenizer, "not a valid date format");
}
format = token.StringValue;
readTillEOL(tokenizer);
}
else
{
tokenizer.PushBack(token);
}
m_Attributes.addElement(new Attribute(attributeName, format, numAttributes()));
}
else
{
errms(tokenizer, "no valid attribute type or invalid " + "enumeration");
}
}
else
{
// Attribute is nominal.
attributeValues = new FastVector();
tokenizer.PushBack(token);
// Get values for nominal attribute.
tokenizer.NextToken(out token);
if ( token.StringValue != "{")
{
errms(tokenizer, "{ expected at beginning of enumeration");
}
tokenizer.NextToken(out token);
while ( token.StringValue != "}")
{
//if (tokenizer.ttype == SupportClass.StreamTokenizerSupport.TT_EOL)
if (token is EolToken)
{
errms(tokenizer, "} expected at end of enumeration");
}
else
{
attributeValues.addElement(token.StringValue);
}
tokenizer.NextToken(out token);
}
if (attributeValues.size() == 0)
{
errms(tokenizer, "no nominal values found");
}
m_Attributes.addElement(new Attribute(attributeName, attributeValues, numAttributes()));
}
getLastToken(tokenizer,out token, false);
getFirstToken(tokenizer,out token);
//if (tokenizer.ttype == SupportClass.StreamTokenizerSupport.TT_EOF)
if (token is EofToken)
errms(tokenizer, "premature end of file");
}
// Check if data part follows. We can't easily check for EOL.
if (!ARFF_DATA.ToUpper().Equals(token.StringValue.ToUpper()))
{
errms(tokenizer, "keyword " + ARFF_DATA + " expected");
}
// Check if any attributes have been declared.
if (m_Attributes.size() == 0)
{
errms(tokenizer, "no attributes declared");
}
// Allocate buffers in case sparse instances have to be read
m_ValueBuffer = new double[numAttributes()];
m_IndicesBuffer = new int[numAttributes()];
}
