private void DetermineFeature()
{
Feature = InformationGains.OrderByDescending(x => x.Value).First().Key;
if (InformationGains.All(x => x.Value == 0))
{
for (int i = 1; i < 67693; i++)
{
if (!FeaturesTaken.Contains(i))
{
Feature = i;
}
}
}
}
private void SetInformationGain()
{
//Counts(True Lable)(Feature Label) 67692
Dictionary <int, double> Counts11 = new Dictionary <int, double>();
Dictionary <int, double> Counts10 = new Dictionary <int, double>();
Dictionary <int, double> Counts01 = new Dictionary <int, double>();
Dictionary <int, double> Counts00 = new Dictionary <int, double>();
double Positive_Labels = 0;
double Negative_Labels = 0;
foreach (var example in TrainingData)
{
if (example.Sign == 1)
{
for (int i = 1; i < 67693; i++)
{
if (example.Vector.ContainsKey(i)) //This means that the feature is +1 and the true label is +1
{
if (Counts11.ContainsKey(i))
{
Counts11[i] = Counts11[i] + 1;
}
else
{
Counts11.Add(i, 1);
}
}
else //This means that the feature is -1 and the true label is +1
{
if (Counts10.ContainsKey(i))
{
Counts10[i] = Counts10[i] + 1;
}
else
{
Counts10.Add(i, 1);
}
}
}
Positive_Labels++;
}
else
{
for (int i = 1; i < 67693; i++)
{
if (example.Vector.ContainsKey(i)) //This means that the feature is +1 and the true label is -1
{
if (Counts01.ContainsKey(i))
{
Counts01[i] = Counts01[i] + 1;
}
else
{
Counts01.Add(i, 1);
}
}
else //This means that the feature is -1 and the true label is -1
{
if (Counts00.ContainsKey(i))
{
Counts00[i] = Counts00[i] + 1;
}
else
{
Counts00.Add(i, 1);
}
}
}
Negative_Labels++;
}
}
if (!Naive_Bayes) //Do Decision tree Stuff
{
for (int i = 1; i < 67693; i++)
{
double PosLabel_PosFeature = Counts11.ContainsKey(i) ? Counts11[i] : 0;
double NegLabel_PosFeature = Counts01.ContainsKey(i) ? Counts01[i] : 0;
double PosLabel_NegFeature = Counts10.ContainsKey(i) ? Counts10[i] : 0;
double NegLabel_NegFeature = Counts00.ContainsKey(i) ? Counts00[i] : 0;
InformationGains.Add(i, CalculateInformationGain(Positive_Labels, Negative_Labels, PosLabel_PosFeature, NegLabel_PosFeature, PosLabel_NegFeature, NegLabel_NegFeature));
}
}
#region Naive Bayes
else // Do Naive Bayes Stuff
{
double Prob_Yes = Positive_Labels / TrainingData.Count;
double Prob_No = Negative_Labels / TrainingData.Count;
//the Si is equal to 2, So i just put 2 there.
double bottom_Pos = Positive_Labels + (2 * Smoothing_Term);
double bottom_Neg = Negative_Labels + (2 * Smoothing_Term);
for (int i = 1; i < 67693; i++)
{
if (Counts11.ContainsKey(i))
{
Counts11[i] = (Counts11[i] + Smoothing_Term) / bottom_Pos;
}
else
{
Counts11.Add(i, Smoothing_Term / bottom_Pos);
}
if (Counts10.ContainsKey(i))
{
Counts10[i] = (Counts10[i] + Smoothing_Term) / bottom_Pos;
}
else
{
Counts10.Add(i, Smoothing_Term / bottom_Pos);
}
if (Counts01.ContainsKey(i))
{
Counts01[i] = (Counts01[i] + Smoothing_Term) / bottom_Neg;
}
else
{
Counts01.Add(i, Smoothing_Term / bottom_Pos);
}
if (Counts00.ContainsKey(i))
{
Counts00[i] = (Counts00[i] + Smoothing_Term) / bottom_Neg;
}
else
{
Counts00.Add(i, Smoothing_Term / bottom_Pos);
}
}
int correct_values = 0;
int poss = 0;
int inff = 0;
foreach (var example in TrainingData)
{
double Pos = Math.Log10(Prob_Yes); // * double.MaxValue * 1.5;
double Neg = Math.Log10(Prob_No); // * double.MaxValue * 1.5;
for (int i = 1; i < 67693; i++)
{
if (example.Vector.ContainsKey(i)) // That means that feature value is 1
{
Pos = Pos + Math.Log10(Counts11[i]); // * 1.022;
}
else //That means the feature value is -1
{
Pos = Pos + Math.Log10(Counts10[i]); // * 1.022;
}
if (example.Vector.ContainsKey(i)) // That means that feature value is 1
{
Neg = Neg + Math.Log10(Counts01[i]); // * 1.022;
}
else //That means the feature value is -1
{
Neg = Neg + Math.Log10(Counts00[i]);// * 1.022;
}
}
int yguess;
if (Pos == 0)
{
poss++;
}
if (Neg == 0)
{
poss++;
}
if (double.IsInfinity(Pos))
{
inff++;
}
if (double.IsInfinity(Neg))
{
inff++;
}
if (Pos >= Neg)
{
yguess = 1;
}
else
{
yguess = -1;
}
Labels.Add(yguess);
if (yguess == example.Sign)
{
correct_values++;
}
}
//Console.WriteLine("0: \t" + poss);
//Console.WriteLine("inf: \t" + inff);
Accuracy = correct_values / Convert.ToDouble(TrainingData.Count);
//Test Data
correct_values = 0;
foreach (var example in TestData)
{
double Pos = Math.Log10(Prob_Yes);
double Neg = Math.Log10(Prob_No);
for (int i = 1; i < 67693; i++)
{
if (example.Vector.ContainsKey(i)) // That means that feature value is 1
{
Pos = Pos + Math.Log10(Counts11[i]);
}
else //That means the feature value is -1
{
Pos = Pos + Math.Log10(Counts10[i]);
}
if (example.Vector.ContainsKey(i)) // That means that feature value is 1
{
Neg = Neg + Math.Log10(Counts01[i]);
}
else //That means the feature value is -1
{
Neg = Neg + Math.Log10(Counts00[i]);
}
}
int yguess;
if (Pos >= Neg)
{
yguess = 1;
}
else
{
yguess = -1;
}
Test_Labels.Add(yguess);
if (yguess == example.Sign)
{
correct_values++;
}
}
Test_Accuracy = correct_values / Convert.ToDouble(TestData.Count);
}
#endregion
}
