public void ProcessDataThroughTree(
DataPointManager dataPointMgr,
GeneticAlgorithmRunResults results,
IEnumerable <DataPoint> dataPoints)
{
//reset traverse counts
//double check on traverse count
//TODO clean this up to determine which one is failing
_nodes.Clear();
Stack <TreeNode> nodes_to_process = new Stack <TreeNode>();
nodes_to_process.Push(_root);
while (nodes_to_process.Count > 0)
{
TreeNode node = nodes_to_process.Pop();
//TODO determine why this line will fail at times... seems to be related to root nodes
_nodes.Add(node);
node._traverseCount = 0;
node.matrix = new ConfusionMatrix(dataPointMgr.classes.Length);
foreach (var subNode in node._subNodes)
{
nodes_to_process.Push(subNode);
}
}
foreach (var dataPoint in dataPoints)
{
results.count_allData++;
TraverseData(dataPoint, results);
}
//at this point, have the results for the run through, need to determine a score
results.ProcessScoresAfterTraverse();
results.tree_nodeCount = _nodes.Count;
results._matrix = this._root.matrix;
//store the results for future use
_currentResults = results;
}
public static TreeTest TreeTestFactory(DataPointManager dataPointMgr, Random rando)
{
//TODO this shoudl take a ga_mgr instead of the parts
//TODO clean up this mess once the DataColumns quit using the TYPE part
TreeTest output;
var col_param = rando.Next(dataPointMgr._columns.Count);
DataColumn column = dataPointMgr._columns[col_param];
switch (column._type)
{
case DataColumn.DataValueTypes.NUMBER:
LessThanEqualTreeTest test = new LessThanEqualTreeTest();
test.param = col_param;
test.valTest = column.GetTestValue(rando);
output = test;
break;
case DataColumn.DataValueTypes.CATEGORY:
var cat_column = column as CategoryDataColumn;
var categories = cat_column._codebook.GetCategories();
var category_count = categories.Count();
//toss a coin to decide on subsetter
EqualTreeTest test_eq = new EqualTreeTest();
test_eq._param = col_param;
test_eq._valTest = column.GetTestValue(rando);
output = test_eq;
break;
default:
throw new ArgumentOutOfRangeException();
}
output._testCol = column;
return(output);
}
public void CreateValues(DataPointManager dp_mgr)
{
foreach (var baseValue in _baseColumn._values)
{
DataValue dv_new = new DataValue();
switch (this._formula)
{
case FormulaOptions.LN:
if (baseValue._value > 0)
{
dv_new._value = Math.Log(baseValue._value);
}
else
{
dv_new._isMissing = true;
this._hasMissingValues = true;
}
break;
case FormulaOptions.TANH:
dv_new._value = Math.Tanh(baseValue._value);
break;
case FormulaOptions.SQRT:
if (baseValue._value > 0)
{
dv_new._value = Math.Sqrt(baseValue._value);
}
else
{
dv_new._isMissing = true;
this._hasMissingValues = true;
}
break;
case FormulaOptions.SQR:
dv_new._value = Math.Pow(baseValue._value, 2);
break;
case FormulaOptions.INV:
if (baseValue._value != 0.0)
{
dv_new._value = 1 / baseValue._value;
}
else
{
dv_new._isMissing = true;
this._hasMissingValues = true;
}
break;
case FormulaOptions.NONE:
dv_new._value = baseValue._value;
break;
default:
throw new ArgumentOutOfRangeException();
}
dv_new._value *= _scaling;
this._values.Add(dv_new);
}
//do a zip with the original DataPoints
var items = dp_mgr._dataPoints.Zip(this._values, (dp, dv) =>
{
dp._data.Add(dv);
return(true);
});
//TODO remove this sloppy bit that forces execution above
foreach (var item in items)
{
}
this.ProcessRanges();
}