/**
* Constructor for BucketTree. Does the whole initialization; it should be the only method that
* deals with symbolic names for variables.
*/
public BucketTree(Ordering ord, boolean dpc) {
int i, j, markers[];
ProbabilityFunction pf;
ProbabilityVariable pv;
DiscreteVariable aux_pv;
DiscreteFunction ut;
String order[];
do_produce_clusters = dpc;
ordering = ord;
// Collect information from the Ordering object.
bn = ord.bn;
explanation_status = ord.explanation_status;
order = ord.order;
// Indicate the first bucket to process
active_bucket = 0;
// Check the possibility that the query has an observed variable
i = bn.index_of_variable(order[order.length - 1]);
pv = bn.get_probability_variable(i);
if (pv.is_observed() == true) {
pf = transform_to_probability_function(bn, pv);
bucket_tree = new Bucket[1];
bucket_tree[0] = new Bucket(this, pv, do_produce_clusters);
insert(pf);
} else {
// Initialize the bucket objects
bucket_tree = new Bucket[order.length];
for (i = 0; i < order.length; i++) {
j = bn.index_of_variable(order[i]);
bucket_tree[i] = new Bucket(this, bn.get_probability_variable(j), do_produce_clusters);
}
// Insert the probability functions into the bucket_tree;
// first mark all functions that are actually going
// into the bucket_tree.
markers = new int[bn.number_variables()];
for (i = 0; i < order.length; i++) markers[bn.index_of_variable(order[i])] = 1;
// Now insert functions that are marked and non-null.
for (i = 0; i < bn.number_probability_functions(); i++) {
if (markers[bn.get_probability_function(i).get_index(0)] == 1) {
pf = check_evidence(bn.get_probability_function(i));
if (pf != null) {
aux_pv = (bn.get_probability_function(i)).get_variable(0);
insert(pf, !pf.memberOf(aux_pv.get_index()));
}
}
}
// Insert the utility_function.
ut = bn.get_utility_function();
if (ut != null) insert(ut);
}
}
public final DataSet filter(DataSet dataSet) {
// Why does it have to be discrete? Why can't we simply expand
// whatever discrete columns are there and leave the continuous
// ones untouched? jdramsey 7/4/2005
// if (!(dataSet.isDiscrete())) {
// throw new IllegalArgumentException("Data set must be discrete.");
// }
List<Node> variables = new LinkedList<>();
// Add all of the variables to the new data set.
for (int j = 0; j < dataSet.getNumColumns(); j++) {
Node _var = dataSet.getVariable(j);
if (!(_var instanceof DiscreteVariable)) {
variables.add(_var);
continue;
}
DiscreteVariable variable = (DiscreteVariable) _var;
String oldName = variable.getName();
List<String> oldCategories = variable.getCategories();
List<String> newCategories = new LinkedList<>(oldCategories);
String newCategory = "Missing";
int _j = 0;
while (oldCategories.contains(newCategory)) {
newCategory = "Missing" + (++_j);
}
newCategories.add(newCategory);
String newName = oldName + "+";
DiscreteVariable newVariable = new DiscreteVariable(newName, newCategories);
variables.add(newVariable);
}
DataSet newDataSet = new ColtDataSet(dataSet.getNumRows(), variables);
// Copy old values to new data set, replacing missing values with new
// "MissingValue" categories.
for (int j = 0; j < dataSet.getNumColumns(); j++) {
Node _var = dataSet.getVariable(j);
if (_var instanceof ContinuousVariable) {
for (int i = 0; i < dataSet.getNumRows(); i++) {
newDataSet.setDouble(i, j, dataSet.getDouble(i, j));
}
} else if (_var instanceof DiscreteVariable) {
DiscreteVariable variable = (DiscreteVariable) _var;
int numCategories = variable.getNumCategories();
for (int i = 0; i < dataSet.getNumRows(); i++) {
int value = dataSet.getInt(i, j);
if (value == DiscreteVariable.MISSING_VALUE) {
newDataSet.setInt(i, j, numCategories);
} else {
newDataSet.setInt(i, j, value);
}
}
}
}
return newDataSet;
}
