//TODO add the ability to test against another value in the data, will work against the balance scale data
public override TreeTest Copy()
{
LessThanEqualTreeTest test_copy = new LessThanEqualTreeTest();
test_copy.param = this.param;
test_copy.valTest = this.valTest;
test_copy._testCol = this._testCol;
return(test_copy);
}
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 static bool OptimizeTest(YesNoMissingTreeNode node1_copy, GeneticAlgorithmManager ga_mgr)
{
if (node1_copy.Test is LessThanEqualTreeTest)
{
LessThanEqualTreeTest test = node1_copy.Test as LessThanEqualTreeTest;
if (test == null)
{
return(false);
}
//iterate through all values, make split, test impurity
var values = ga_mgr.dataPointMgr._pointsToTest.Select(c => c._data[test.param]);
var all_uniques = values.Where(c => !c._isMissing).Select(c => c._value).Distinct().OrderBy(c => c).ToArray();
List <double> all_splits = new List <double>();
for (int i = 1; i < all_uniques.Length; i++)
{
all_splits.Add(0.5 * (all_uniques[i] + all_uniques[i - 1]));
}
double best_split = double.NaN;
double best_purity = double.MinValue;
//TODO improve this selection for how many split points to consider
foreach (var split in all_splits.TakeEvery(all_splits.Count / 10 + 1))
{
//change the test value and find the best purity
test.valTest = split;
var results = new GeneticAlgorithmRunResults(ga_mgr);
node1_copy._tree.ProcessDataThroughTree(ga_mgr.dataPointMgr, results, ga_mgr.dataPointMgr._pointsToTest);
//check the result of the split
var gini_d = node1_copy.matrix.GiniImpuritySqrt;
double gini_split = 0.0;
int count = 0;
foreach (var node in node1_copy._subNodes)
{
gini_split += node.matrix._count * node.matrix.GiniImpuritySqrt;
count += node.matrix._count;
}
gini_split /= count;
double gini_gain = gini_d - gini_split;
if (gini_gain > best_purity)
{
best_split = split;
best_purity = gini_gain;
}
}
test.valTest = best_split;
}
else if (node1_copy.Test is EqualTreeTest)
{
EqualTreeTest test = node1_copy.Test as EqualTreeTest;
if (test == null)
{
return(false);
}
//iterate through all values, make split, test impurity
var values = ga_mgr.dataPointMgr._pointsToTest.Select(c => c._data[test._param]);
IEnumerable <double> all_uniques = values.Where(c => !c._isMissing).Select(c => c._value).Distinct().OrderBy(c => c);
var unique_count = all_uniques.Count();
if (unique_count > 10)
{
all_uniques = all_uniques.TakeEvery(unique_count / 10 + 1);
}
double best_split = double.NaN;
double best_purity = double.MinValue;
//TODO improve this selection for how many split points to consider
foreach (var split in all_uniques)
{
//change the test value and find the best purity
test._valTest = split;
var results = new GeneticAlgorithmRunResults(ga_mgr);
node1_copy._tree.ProcessDataThroughTree(ga_mgr.dataPointMgr, results, ga_mgr.dataPointMgr._pointsToTest);
var gini_d = node1_copy.matrix.GiniImpuritySqrt;
double gini_split = 0.0;
int count = 0;
foreach (var node in node1_copy._subNodes)
{
gini_split += node.matrix._count * node.matrix.GiniImpuritySqrt;
count += node.matrix._count;
}
gini_split /= count;
double gini_gain = gini_d - gini_split;
if (gini_gain > best_purity)
{
best_split = split;
best_purity = gini_gain;
}
}
test._valTest = best_split;
}
else
{
return(false);
}
return(true);
}