/**
* o(i): Recurrent Neural Network / Part 5
* Neural Network Output: Probability for a possible insurance client to opt for a specific product. A function
* computing an importance measure of each dataset property; as specified from the information gain of each
* specific variable. It constitues an advanced method calculating estimation probabilities for the category of a
* probable insurance client; given the a priori, the a posteriori probabilities; as well. as well values of entrophy
* converted to probabilities through softmax.
*/
public void RNN_Compute_o()
{
o = new MyList <IList <Double> >();
MyList <Double> .InitializeLists(o, dataset.Count, categories);
GetAdditiveGains();
for (int n = 0; n < dataset.Count; n++)
{
TrainSample t = dataset[n];
double sum = 0;
for (int j = 0; j <= categories; j++)
{
o[n][j] += Math.Exp(h[n][collectedPoints.Count - 1] * categoryGains[j]);
sum += o[n][j];
}
for (int j = 0; j <= categories; j++)
{
o[n][j] /= sum;
}
}
for (int n = 0; n < dataset.Count; n++)
{
Console.WriteLine("\nInsured ID: " + dataset[n].getID());
MyList <Double> .NormalizeListValues(o[n], MyList <Double> .FindBoundaries(o[n]));
for (int j = 0; j <= categories; j++)
{
Console.WriteLine("Insurance Program: " + j + " selected with probability: " + o[n][j]);
}
}
}
/**
* A method reading a given train file of a specific format described in comments; contents of which are
* assigned to a parameterized tokens dynamic container if reading was successful; otherwise displays an
* error description.
* @param filename The name of the given text file.
*/
public void ReadTrainFile(String filename)
{
var lines = File.ReadAllLines(filename);
for (var i = 0; i < lines.Length; i += 1)
{
String line = lines[i];
String[] lineTokens = line.Split(' ');
if (lineTokens.Length != 4) throw new FileLoadException("Invalid file format!");
TrainSample trainData = new TrainSample(lineTokens[0], Convert.ToDouble(lineTokens[1]), Convert.ToDouble(lineTokens[2]), Convert.ToInt32(lineTokens[3]));
classificationDecisions[Convert.ToInt32(lineTokens[3])] += 1;
dataset.Add(trainData);
}
}
/**
* Classification scores
*/
public IList<Vec2<String, Double>> Classify()
{
IList<Vec2<String, Double>> classified = new MyList<Vec2<String, Double>>();
for (int n = 0; n < dataset.Count; n++)
{
TrainSample t = dataset[n];
for (int k = 1; k < collectedPoints.Count; k++)
{
classified.Add(new Vec2<String, Double>(t.getID(), Math.Abs(10 * h[n][k])));
}
}
return classified;
}
/**
* h(i): Recurrent Neural Network / Part 4
* Data history computations: A method computing the dataset history; based from the piecewise linear border of
* correlation between the instance variables.
*/
public void RNN_Compute_h()
{
h = new MyList<IList<Double>>();
MyList<Double>.InitializeLists(h, dataset.Count, collectedPoints.Count);
GetCorrelationBorders();
for (int n = 0; n < dataset.Count; n++)
{
TrainSample t = dataset[n];
IList<Double> thisReg = normalizeProperty(0);
h[n][0] = Math.Tanh(propertyGains[0] * thisReg[n]);
for (int k = 1; k < collectedPoints.Count; k++)
{
thisReg = normalizeProperty(k);
h[n][k] = Math.Tanh(correlations[k - 1] * h[n][k - 1] + propertyGains[k] * thisReg[n]);
Console.WriteLine(h[n][k]);
}
}
}