/// <summary>
/// One hot encodes the REBER strings
/// </summary>
/// <param name="strList">A list of REBER sequences</param>
/// <returns>A data table with matrices to represent the sequences of vectors and their corresponding outputs</returns>
public static IDataTable GetOneHot(IEnumerable <string> strList)
{
var strList2 = strList.ToList();
// build the following item table
var following = new Dictionary <string, HashSet <int> >();
foreach (var str in strList2)
{
var sb = new StringBuilder();
string prev = null;
foreach (var ch in str)
{
sb.Append(ch);
var key = sb.ToString();
if (prev != null)
{
if (!following.TryGetValue(prev, out HashSet <int> temp))
{
following.Add(prev, temp = new HashSet <int>());
}
temp.Add(_ch[ch]);
}
prev = key;
}
}
var builder = DataTableBuilder.CreateTwoColumnMatrix();
foreach (var str in strList2)
{
var inputList = new FloatVector[str.Length];
var outputList = new FloatVector[str.Length];
var sb = new StringBuilder();
for (var i = 0; i < str.Length; i++)
{
var ch = str[i];
sb.Append(ch);
var input = new float[_ch.Count];
var output = new float[_ch.Count];
input[_ch[ch]] = 1f;
if (following.TryGetValue(sb.ToString(), out HashSet <int> temp))
{
foreach (var item in temp)
{
output[item] = 1f;
}
}
inputList[i] = new FloatVector {
Data = input
};
outputList[i] = new FloatVector {
Data = output
};
}
builder.Add(FloatMatrix.Create(inputList), FloatMatrix.Create(outputList));
}
return(builder.Build());
}
/// <summary>
/// Creates random integers added together as feature vectors
/// The input feature contains two features, one for each bit at that position
/// The output feature contains a single feature: 1 or 0 if that bit is set in the result
/// </summary>
/// <param name="sampleCount">How many samples to generate</param>
/// <param name="stochastic">True to generate random integers</param>
/// <returns>A list of sequences</returns>
public static IDataTable Addition(int sampleCount, bool stochastic)
{
Random rand = stochastic ? new Random() : new Random(0);
var builder = DataTableBuilder.CreateTwoColumnMatrix();
for (var i = 0; i < sampleCount; i++)
{
// generate some random numbers (sized to prevent overflow)
var a = rand.Next(int.MaxValue / 2);
var b = rand.Next(int.MaxValue / 2);
var a2 = _GetBitArray(a);
var b2 = _GetBitArray(b);
var r2 = _GetBitArray(a + b);
var inputList = new FloatVector[r2.Length];
var outputList = new FloatVector[r2.Length];
for (int j = 0; j < r2.Length; j++)
{
inputList[j] = new FloatVector {
Data = new[] { a2[j], b2[j] }
};
outputList[j] = new FloatVector {
Data = new[] { r2[j] }
};
}
builder.Add(FloatMatrix.Create(inputList), FloatMatrix.Create(outputList));
}
return(builder.Build());
}