/// <summary>
/// Calculates the Hamming distance of this instance to a specified instance.
/// </summary>
/// <param name="vector">The instance.</param>
/// <returns>The Hamming distance.</returns>
/// <remarks></remarks>
public int HammingDistance(InstanceS vector)
{
int distance, len;
if (Features.Length != vector.Features.Length)
{
return(int.MaxValue);
}
if (Features.Length < vector.Features.Length)
{
distance = vector.Features.Length - Features.Length;
len = Features.Length;
}
else
{
distance = Features.Length - vector.Features.Length;
len = vector.Features.Length;
}
for (int i = 0; i < len; i++)
{
distance += (Features[i] != vector.Features[i]) ? 1 : 0;
}
return(distance);
}
/// <summary>
/// Calculates the weighted Hamming distance of this instance to a specified instance.
/// </summary>
/// <param name="vector">The instance.</param>
/// <returns>The weighted Hamming distance.</returns>
/// <remarks></remarks>
public float ConfusionWeightedHammingDistance(InstanceS vector)
{
if (Features.Length != vector.Features.Length) return float.MaxValue;
// empirical confusion probabilities
var confusions = new Dictionary<string, float>()
{
{ "F, E", 0.314f },
{ "E, F", 0.147f },
{ "Q, O", 0.125f },
{ "O, Q", 0.125f },
{ "D, O", 0.105f },
{ "O, D", 0.105f },
{ "I, J", 0.105f },
{ "R, K", 0.118f },
{ "N, H", 0.102f },
{ "P, F", 0.094f },
{ "H, N", 0.093f },
{ "L, E", 0.090f },
{ "I, Z", 0.085f },
{ "J, I", 0.080f },
{ "X, Z", 0.074f },
{ "Y, A", 0.073f },
{ "X, I", 0.072f },
{ "A, V", 0.063f },
{ "N, O", 0.057f },
{ "V, A", 0.057f },
{ "W, M", 0.055f },
{ "A, Y", 0.054f },
{ "B, R", 0.053f },
{ "Z, I", 0.052f }
};
float distance = 0;
int errCount = 0;
const float confusionMultiplier = 2.5f;
for (int i = 0; i < Features.Length; i++)
{
if (Features[i] != vector.Features[i])
{
string conf = "" + vector.Features[i] + ", " + Features[i];
if (confusions.ContainsKey(conf))
{
distance += Math.Max(0, 1 - (confusionMultiplier * confusions[conf]));
}
else
{
distance += 1;
}
errCount += 1;
}
}
distance += (1 - Weight) * errCount * 0.5f;
return distance;
}
/// <summary>
/// Calculates the Hamming distance of this instance to a specified instance.
/// </summary>
/// <param name="vector">The instance.</param>
/// <returns>The Hamming distance.</returns>
/// <remarks></remarks>
public int HammingDistance(InstanceS vector)
{
int distance, len;
if (Features.Length != vector.Features.Length)
return int.MaxValue;
if (Features.Length < vector.Features.Length)
{
distance = vector.Features.Length - Features.Length;
len = Features.Length;
}
else
{
distance = Features.Length - vector.Features.Length;
len = vector.Features.Length;
}
for (int i = 0; i < len; i++)
{
distance += (Features[i] != vector.Features[i]) ? 1 : 0;
}
return distance;
}
/// <summary>
/// Finds the K nearest instances to a test instance. String based version.
/// </summary>
/// <param name="test">The test instance.</param>
/// <returns>An array of the k-nearest results.</returns>
/// <remarks></remarks>
public Result[] FindKNearest(InstanceS test)
{
List<Result> results = new List<Result>();
foreach (InstanceS train in TrainingInstances)
{
double dist = double.MaxValue;
switch (Metric)
{
case Metric.HammingDistance: dist = train.HammingDistance(test); break;
case Metric.WeightedHammingDistance: dist = train.ConfusionWeightedHammingDistance(test); break;
default: throw new NotSupportedException();
}
results.Add(new Result(train.Class, dist));
}
int k = (int)Math.Min(K, TrainingInstances.Count);
results.Sort();
Result[] knr = new Result[k];
results.CopyTo(0, knr, 0, k);
return knr;
}
private void setupWordClassifier(string wordsPath, string wordProbPath)
{
Game.ValidWords = new WordDict(wordsPath);
WordClassifier = new KNearestClassifier(1, Metric.WeightedHammingDistance, WeightMode.Modal);
WordClassifier.TrainingInstances = new List<Instance>();
string[] lines = File.ReadAllLines(wordProbPath);
foreach (string line in lines)
{
string[] word = line.Split(' ');
InstanceS x = new InstanceS(word[0]);
x.Weight = float.Parse(word[1]);
WordClassifier.TrainingInstances.Add(x);
}
}
/// <summary>
/// Calculates the weighted Hamming distance of this instance to a specified instance.
/// </summary>
/// <param name="vector">The instance.</param>
/// <returns>The weighted Hamming distance.</returns>
/// <remarks></remarks>
public float ConfusionWeightedHammingDistance(InstanceS vector)
{
if (Features.Length != vector.Features.Length)
{
return(float.MaxValue);
}
// empirical confusion probabilities
var confusions = new Dictionary <string, float>()
{
{ "F, E", 0.314f },
{ "E, F", 0.147f },
{ "Q, O", 0.125f },
{ "O, Q", 0.125f },
{ "D, O", 0.105f },
{ "O, D", 0.105f },
{ "I, J", 0.105f },
{ "R, K", 0.118f },
{ "N, H", 0.102f },
{ "P, F", 0.094f },
{ "H, N", 0.093f },
{ "L, E", 0.090f },
{ "I, Z", 0.085f },
{ "J, I", 0.080f },
{ "X, Z", 0.074f },
{ "Y, A", 0.073f },
{ "X, I", 0.072f },
{ "A, V", 0.063f },
{ "N, O", 0.057f },
{ "V, A", 0.057f },
{ "W, M", 0.055f },
{ "A, Y", 0.054f },
{ "B, R", 0.053f },
{ "Z, I", 0.052f }
};
float distance = 0;
int errCount = 0;
const float confusionMultiplier = 2.5f;
for (int i = 0; i < Features.Length; i++)
{
if (Features[i] != vector.Features[i])
{
string conf = "" + vector.Features[i] + ", " + Features[i];
if (confusions.ContainsKey(conf))
{
distance += Math.Max(0, 1 - (confusionMultiplier * confusions[conf]));
}
else
{
distance += 1;
}
errCount += 1;
}
}
distance += (1 - Weight) * errCount * 0.5f;
return(distance);
}