public void test_binarisation_in_instances_builder()
{
TestingRow[] rows = new[] {
new TestingRow {
CLASS = 1, ATT_1 = 111, ATT_2 = 222, ATT_3 = 333, ATT_4 = 444, ATT_5 = 555, ATT_6 = 666, ATT_7 = 777, ATT_8 = 888
},
new TestingRow {
CLASS = 0, ATT_1 = 1112, ATT_2 = 2222, ATT_3 = 3332, ATT_4 = 4442, ATT_5 = 5552, ATT_6 = 6662, ATT_7 = 7772, ATT_8 = 8882
}
};
weka.core.Instances instances = new InstancesBuilder <TestingRow>(rows, 0).Build();
Assert.AreEqual(25, instances.numAttributes());
weka.core.Instance i1 = instances.instance(0);
weka.core.Instance i2 = instances.instance(1);
// These are the standard properties
Assert.AreEqual(1.0, i1.value(0)); Assert.AreEqual(1.0, i1.classValue());
Assert.AreEqual(0.0, i2.value(0)); Assert.AreEqual(0.0, i2.classValue());
Assert.AreEqual(0.0, i1.value(1)); Assert.AreEqual("111", i1.stringValue(1));
Assert.AreEqual(1.0, i2.value(1)); Assert.AreEqual("1112", i2.stringValue(1));
Assert.AreEqual(0.0, i1.value(2)); Assert.AreEqual("222", i1.stringValue(2));
Assert.AreEqual(1.0, i2.value(2)); Assert.AreEqual("2222", i2.stringValue(2));
Assert.AreEqual(0.0, i1.value(3)); Assert.AreEqual("333", i1.stringValue(3));
Assert.AreEqual(1.0, i2.value(3)); Assert.AreEqual("3332", i2.stringValue(3));
Assert.AreEqual(0.0, i1.value(4)); Assert.AreEqual("444", i1.stringValue(4));
Assert.AreEqual(1.0, i2.value(4)); Assert.AreEqual("4442", i2.stringValue(4));
Assert.AreEqual(0.0, i1.value(5)); Assert.AreEqual("555", i1.stringValue(5));
Assert.AreEqual(1.0, i2.value(5)); Assert.AreEqual("5552", i2.stringValue(5));
Assert.AreEqual(0.0, i1.value(6)); Assert.AreEqual("666", i1.stringValue(6));
Assert.AreEqual(1.0, i2.value(6)); Assert.AreEqual("6662", i2.stringValue(6));
Assert.AreEqual(0.0, i1.value(7)); Assert.AreEqual("777", i1.stringValue(7));
Assert.AreEqual(1.0, i2.value(7)); Assert.AreEqual("7772", i2.stringValue(7));
Assert.AreEqual(0.0, i1.value(8)); Assert.AreEqual("888", i1.stringValue(8));
Assert.AreEqual(1.0, i2.value(8)); Assert.AreEqual("8882", i2.stringValue(8));
// These are the new binarized
for (int i = 9; i < 25; i += 2)
{
Assert.AreEqual(1.0, i1.value(i)); Assert.AreEqual(0.0, i2.value(i));
Assert.AreEqual(0.0, i1.value(i + 1)); Assert.AreEqual(1.0, i2.value(i + 1));
}
}
public override double classifyInstance(weka.core.Instance instance)
{
if (m_instances.numInstances() == 0)
{
return(2);
}
if (m_instances.numAttributes() != instance.numAttributes())
{
throw new AssertException("different attribute.");
}
int n = (instance.numAttributes() - 1) / 2;
List <Tuple <int, int> > dist = new List <Tuple <int, int> >();
for (int i = 0; i < m_instances.numInstances(); ++i)
{
int d1 = 0, d2 = 0;
weka.core.Instance instanceI = m_instances.instance(i);
for (int j = 0; j < n; ++j)
{
//d += (int)((instanceI.value(j) - instance.value(j)) * (instanceI.value(j) - instance.value(j)));
if (instanceI.value(j) != instance.value(j))
{
if (instance.value(j) == 2 || instanceI.value(j) == 2)
{
d1++;
}
else
{
d1 += 4;
}
}
}
for (int j = n; j < 2 * n; ++j)
{
//d += (int)((instanceI.value(j) - instance.value(j)) * (instanceI.value(j) - instance.value(j)));
if (instanceI.value(j) != instance.value(j))
{
if (instance.value(j) == 2 || instanceI.value(j) == 2)
{
d2++;
}
else
{
d2 += 4;
}
}
}
int c = (int)instanceI.classValue();
//if (c == 0)
//{
// if (d1 < n / 4 && d1 < d2)
// {
// dist.Add(new Tuple<int, int>(d1, c));
// }
//}
//else if (c == 1)
//{
// if (d2 < n / 4 && d2 < d1)
// {
// dist.Add(new Tuple<int, int>(d2, c));
// }
//}
//else
//{
// throw new AssertException("");
//}
dist.Add(new Tuple <int, int>(d1 + d2, c));
}
if (dist.Count == 0)
{
return(2);
}
dist.Sort(new Comparison <Tuple <int, int> >((x, y) =>
{
return(x.Item1.CompareTo(y.Item1));
}));
int sum = 0, count = 0;
for (int i = 0; i < dist.Count; ++i)
{
if (dist[i].Item1 < n / 4 * 2 * 4)
{
if (dist[i].Item2 != 2 && dist[i].Item2 != 3)
{
sum += dist[i].Item2;
count++;
}
else
{
}
}
else
{
break;
}
}
if (count == 0)
{
return(2);
}
if (count < m_instances.numInstances() / 30)
{
return(2);
}
return((int)Math.Round((double)sum / count));
}
public void Test()
{
weka.core.Instances insts = new weka.core.Instances(new java.io.FileReader("D:\\android_analysis\\attributes.arff"));
insts.setClassIndex(insts.numAttributes() - 1);
weka.classifiers.Classifier cl = new weka.classifiers.trees.J48();
cl.buildClassifier(insts);
weka.filters.Filter myRandom = new weka.filters.unsupervised.instance.Randomize();
myRandom.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myRandom);
int trainSize = (int)(insts.numInstances() * 0.66);
int testSize = insts.numInstances() - trainSize;
weka.core.Instances train = new weka.core.Instances(insts, 0, trainSize);
cl.buildClassifier(train);
for (int i = trainSize; i < insts.numInstances(); i++)
{
weka.core.Instance currentInst = insts.instance(i);
double predictedClass = cl.classifyInstance(currentInst);
double[] distrs = cl.distributionForInstance(currentInst);
string actual = insts.classAttribute().value((int)currentInst.classValue());
string predicted = insts.classAttribute().value((int)predictedClass);
System.Console.WriteLine("ID: " + (i + 1) + ", " + actual + " --> " + predicted);
}
}
public override double classifyInstance(weka.core.Instance instance)
{
if (m_instances.numInstances() == 0)
{
return(2);
}
if (m_instances.numAttributes() != instance.numAttributes())
{
throw new AssertException("different attribute.");
}
int n = instance.numAttributes();
List <Tuple <int, int> > dist = new List <Tuple <int, int> >();
for (int i = 0; i < m_instances.numInstances(); ++i)
{
int d1 = 0, d2 = 0;
weka.core.Instance instanceI = m_instances.instance(i);
for (int j = 0; j < n; ++j)
{
//d += (int)((instanceI.value(j) - instance.value(j)) * (instanceI.value(j) - instance.value(j)));
if (instanceI.value(j) != instance.value(j))
{
d1++;
}
if (instance.value(j) != 0)
{
d2++;
}
}
int c = (int)instanceI.classValue();
dist.Add(new Tuple <int, int>(d1, c));
}
if (dist.Count == 0)
{
return(2);
}
dist.Sort(new Comparison <Tuple <int, int> >((x, y) =>
{
return(x.Item1.CompareTo(y.Item1));
}));
int sum = 0, count = 0;
for (int i = 0; i < dist.Count; ++i)
{
if (dist[i].Item1 < 4)
{
sum += dist[i].Item2;
count++;
}
else
{
break;
}
}
if (count == 0)
{
return(2);
}
if (count < m_instances.numInstances() / 70)
{
return(2);
}
return((int)Math.Round((double)sum / count));
}
protected override string instanceToLibsvm(weka.core.Instance inst)
{
//StringBuffer.__<clinit>();
//StringBuffer buffer = new StringBuffer(new StringBuilder().append("").append(inst.classValue()).toString());
StringBuffer buffer = new StringBuffer(new StringBuilder().append("").append(inst.classValue() - 1).toString());
for (int i = 0; i < inst.numAttributes(); i++)
{
if ((i != inst.classIndex()) && (inst.value(i) != 0f))
{
buffer.append(new StringBuilder().append(" ").append((int)(i + 1)).append(":").append(inst.value(i)).toString());
}
}
return(buffer.toString());
}
