private List <Tree> ScoreTreesAndReturnKept(IEnumerable <Tree> trees, int generation)
{
List <Tree> keeps = new List <Tree>();
Logger.WriteLine("point count: " + dataPointMgr._pointsToTest.Count);
foreach (var tree in trees)
{
GeneticAlgorithmRunResults results = null;
//TODO figure out why a NullRefExc came through here
if (tree == null)
{
continue;
}
//quick pass through for trees already processed
if (!tree._isDirty)
{
tree._source = "pass through";
keeps.Add(tree);
continue;
}
results = new GeneticAlgorithmRunResults(this);
tree.ProcessDataThroughTree(dataPointMgr, results, dataPointMgr._pointsToTest);
tree.RemoveZeroCountNodes();
GeneticOperations.PruneTreeOfUselessNodes(tree);
//will add kepeers if there was no previous result or if the score improved or randomly
if (tree._prevResults == null || results.MetricResult > tree._prevResults.MetricResult)
{
//only add the new tree to the results if the score improved
keeps.Add(tree);
}
tree._isDirty = false;
tree._prevResults = results;
//now run a set of values through for the cross validation
//TODO determine when to do the CV step, how many points to use, and what to do with the results
/*TODO uncomment to get CV back, consider impact of node level matrices changing)
* var cv_results = new GeneticAlgorithmRunResults(this);
* tree.ProcessDataThroughTree(dataPointMgr, cv_results, dataPointMgr._pointsNotUsedToTest.TakeEvery(5));
* double loss_ratio = results.AverageLoss / cv_results.AverageLoss;
* Logger.WriteLine(loss_ratio);
*/
}
return(keeps);
}
private List <Tree> CreateRandomPoolOfTrees(int size)
{
var trees = new List <Tree>();
Parallel.For(0, size, index =>
{
var tree = GeneticOperations.CreateRandomTree(this);
lock (trees)
{
trees.Add(tree);
}
});
return(trees);
}
