getMostFrequentValueForIndex_Generic(
double[][] filteredData,
int index,
Boolean checkMissingValue)
{
Dictionary <double, long> freqs;
freqs = InformationGain.Frequency(
filteredData[index]);
//Do not count missing values
if (checkMissingValue)
{
if (freqs.ContainsKey(_missingValue))
{
freqs.Remove(_missingValue);
}
}
//Aggregate is the LINQ name for the commonly known functional concept Fold
var max = freqs.Aggregate((l, r) => l.Value >
r.Value ? l : r).Key;
return(max);
}
public void Statistics_Frequency()
{
Dictionary <double, long> freqs =
InformationGain.Frequency(ta);
Assert.AreEqual(freqs[2], 5);
Assert.AreEqual(freqs[3], 4);
Assert.AreEqual(freqs[4], 4);
}
public void Statistics_EntropyShannon_ProvideFreq()
{
Dictionary <double, long> freqs =
InformationGain.Frequency(ta);
double value =
InformationGain.EntropyShannon(freqs);
Assert.IsTrue(2.17 <= value && value <= 2.19);
}
splitDataOnUnivariateCriterion(
double[][] data)
{
double entropyS;
double entropySv;
double entropySum;
double infoGain = 0;
double[] filteredTargetData;
Dictionary <double, long> freqs;
SplittedAttributeData ed = new SplittedAttributeData();
ed.SplittingCriteriaValue = double.NegativeInfinity;
entropyS = getEntropyOfTargetAttribute(data);
for (int idxCol = 0; idxCol < data.Count();
idxCol++)
{
entropySum = 0;
if (data[idxCol] != null &&
idxCol != _indexTargetAttribute) //Do not compute when data not present
{
freqs = InformationGain.Frequency(
data[idxCol]);
//key has value
foreach (double key in freqs.Keys)
{
if (key != _missingValue)
{
filteredTargetData =
getFilteredTargetValues(data, idxCol, key);
entropySv = InformationGain.EntropyShannon(filteredTargetData);
entropySum += ((double)filteredTargetData.Length /
(double)data[_indexTargetAttribute].Length)
* entropySv;
}
}
infoGain = entropyS - entropySum;
//Compute InfoGain
if (infoGain > ed.SplittingCriteriaValue)
{
ed.Freqs = freqs;
ed.AttributeIndex = idxCol;
ed.SplittingCriteriaValue = infoGain;
}
} //if condition
} //Main loop
return(ed);
}
