/// <summary>
/// This version starts with a SOM, then potentially splits the largest node and/or gathers the smallest nodes into a single
/// </summary>
/// <returns></returns>
public static SOMResult Train(ISOMInput[] inputs, SOMRules rules, bool isDisplay2D)
{
SOMResult result = SelfOrganizingMaps.TrainSOM(inputs, rules, isDisplay2D);
if (result.Nodes.Length == 0)
{
return(result);
}
else if (result.Nodes.Length == 1)
{
#region kmeans single node
if (inputs.Length < 20)
{
return(result);
}
return(SelfOrganizingMaps.TrainKMeans(inputs, 5, true));
#endregion
}
var categorized = GetSOM_SplitMerge_Categorize(result);
List <SOMNode> nodes = new List <SOMNode>();
List <ISOMInput[]> newInputs = new List <ISOMInput[]>();
foreach (NodeCombo set in UtilityCore.Iterate(categorized.kmeans, categorized.keep)) // UtilityCore.Iterate gracefully skips nulls
{
nodes.Add(set.Node);
newInputs.Add(set.Inputs);
}
if (categorized.remaining != null)
{
nodes.Add(new SOMNode()
{
Position = MathND.GetCenter(categorized.remaining.Select(o => o.Node.Position)),
Weights = MathND.GetCenter(categorized.remaining.Select(o => o.Node.Weights)),
});
newInputs.Add(categorized.remaining.
SelectMany(o => o.Inputs).
ToArray());
}
return(new SOMResult(nodes.ToArray(), newInputs.ToArray(), false));
}
/// <summary>
/// This overload does an initial training, then recurses on any node that has too wide of a range of values
/// </summary>
/// <remarks>
/// This method is a bit of a failure. Sometimes it works, but other times it just runs without fixing anything
/// </remarks>
/// <param name="maxSpreadPercent">
/// Spread is an input's distance from the center of all inputs. The percent is a node's max distance divided by all node's max distance.
/// .65 to .75 is a good value to use (smaller values will chop up into more nodes)
/// </param>
public static SOMResult TrainSOM(ISOMInput[] inputs, SOMRules rules, double maxSpreadPercent, bool isDisplay2D, bool returnEmptyNodes = false)
{
const int MININPUTSFORSPLIT = 4;
// Get the initial result
SOMResult result = TrainSOM(inputs, rules, isDisplay2D, returnEmptyNodes);
#region Divide large nodes
double totalSpread = GetTotalSpread(inputs.Select(o => o.Weights));
int infiniteLoop = 0;
while (infiniteLoop < 50) // if it exceeds this, just use whatever is there
{
// Split up nodes that have too much variation (image's distance from average)
var reduced = Enumerable.Range(0, result.Nodes.Length).
AsParallel().
Select(o => SplitNode(o, result, MININPUTSFORSPLIT, maxSpreadPercent, totalSpread, rules)).
ToArray();
if (reduced.All(o => !o.Item1))
{
// No changes were needed this pass
break;
}
SOMNode[] reducedNodes = reduced.
SelectMany(o => o.Item2).
ToArray();
// Rebuild result
ISOMInput[][] imagesByNode = SelfOrganizingMaps.GetInputsByNode(reducedNodes, inputs);
result = new SOMResult(reducedNodes, imagesByNode, false);
result = SelfOrganizingMaps.RemoveZeroNodes(result);
infiniteLoop++;
}
#endregion
// Inject positions into the nodes
InjectNodePositions2D(result.Nodes); //TODO: Look at isDisplay2D
result = ArrangeNodes_LikesAttract(result);
return(result);
}
private static (NodeCombo[] kmeans, NodeCombo[] keep, NodeCombo[] remaining) GetSOM_SplitMerge_Categorize(SOMResult result)
{
NodeCombo[] nodes = Enumerable.Range(0, result.Nodes.Length).
Select(o => new NodeCombo()
{
Node = result.Nodes[o], Inputs = result.InputsByNode[o]
}).
OrderByDescending(o => o.Inputs.Length).
ToArray();
// First node is a potential kmeans split
NodeCombo kmeans = null;
int keepStart = 0;
if (nodes[0].Inputs.Length.ToDouble() / nodes[1].Inputs.Length.ToDouble() > 10)
{
kmeans = nodes[0];
keepStart = 1;
}
NodeCombo[] kmeansSplit = null;
if (kmeans != null)
{
SOMResult result2 = SelfOrganizingMaps.TrainKMeans(kmeans.Inputs, 4, true);
kmeansSplit = Enumerable.Range(0, result2.Nodes.Length).
Select(o => new NodeCombo()
{
Node = result2.Nodes[o], Inputs = result2.InputsByNode[o]
}).
ToArray();
}
// Next nodes are the ones to leave alone
var keep = new List <NodeCombo>();
int?keepStop = null;
keep.Add(nodes[keepStart]);
for (int cntr = keepStart + 1; cntr < nodes.Length; cntr++)
{
if (nodes[keepStart].Inputs.Length.ToDouble() / nodes[cntr].Inputs.Length.ToDouble() > 10)
{
keepStop = cntr;
break;
}
keep.Add(nodes[cntr]);
}
// Everything else gets merged into a single node
NodeCombo[] remaining = null;
if (keepStop != null)
{
remaining = Enumerable.Range(keepStop.Value, result.Nodes.Length - keepStop.Value).
Select(o => nodes[o]).
ToArray();
}
if (remaining == null && keep.Count > 0 && kmeans != null)
{
int sumKeep = keep.Sum(o => o.Inputs.Length);
int smallestKmeans = kmeansSplit.
Select(o => o.Inputs.Length).
OrderBy(o => o).
First();
if (smallestKmeans.ToDouble() / sumKeep.ToDouble() > 10)
{
remaining = keep.ToArray();
keep.Clear();
}
}
return(kmeansSplit, keep.ToArray(), remaining);
}
