public CondClassDistribution info_attr(Domain attr_domain) {
Domain target_domain = insts_by_target.getClassDomain();
// flog.debug("What is the attributeToSplit? " + attr_domain);
/* initialize the hashtable */
CondClassDistribution insts_by_attr = new CondClassDistribution(attr_domain, target_domain);
insts_by_attr.setTotal(insts_by_target.getSum());
// flog.debug("Cond distribution for "+ attr_domain + " \n"+ insts_by_attr);
for (int category = 0; category < target_domain.getCategoryCount(); category++) {
Object targetCategory = target_domain.getCategory(category);
for (Instance inst : insts_by_target.getSupportersFor(targetCategory)) {
Object inst_attr_category = inst.getAttrValue(attr_domain.getFReferenceName());
Object inst_class = inst.getAttrValue(target_domain.getFReferenceName());
if (!targetCategory.equals(inst_class)) {
if (flog.error() != null)
flog.error()
.log("How the f**k they are not the same ? " + targetCategory + " " + inst_class);
System.exit(0);
}
insts_by_attr.change(inst_attr_category, targetCategory, inst.getWeight()); // +1
}
}
return insts_by_attr;
}
// public static double info_contattr(InstanceList data, Domain targetDomain, QuantitativeDomain
// splitDomain) {
public CondClassDistribution info_contattr(Categorizer visitor) {
List<Instance> data = visitor.getSortedInstances();
QuantitativeDomain splitDomain = visitor.getSplitDomain();
Domain targetDomain = insts_by_target.getClassDomain();
String targetAttr = targetDomain.getFReferenceName();
CondClassDistribution instances_by_attr = new CondClassDistribution(splitDomain, targetDomain);
instances_by_attr.setTotal(data.size());
int index = 0;
int split_index = 0;
Object attr_key = splitDomain.getCategory(split_index);
for (Instance i : data) {
if (index == splitDomain.getSplit(split_index).getIndex() + 1) {
attr_key = splitDomain.getCategory(split_index + 1);
split_index++;
}
Object targetKey = i.getAttrValue(targetAttr);
instances_by_attr.change(attr_key, targetKey, i.getWeight()); // +1
index++;
}
return instances_by_attr;
// double sum = calc_info_attr(instances_by_attr);
// return sum;
}
/*
* for both
*/
public static double calc_info_attr(CondClassDistribution instances_by_attr) {
// Collection<Object> attributeValues = instances_by_attr.getAttributes();
double data_size = instances_by_attr.getTotal();
double sum = 0.0;
if (data_size > 0)
for (int attr_idx = 0; attr_idx < instances_by_attr.getNumCondClasses(); attr_idx++) {
Object attr_category = instances_by_attr.getCondClass(attr_idx);
double total_num_attr = instances_by_attr.getTotal_AttrCategory(attr_category);
if (total_num_attr > 0) {
double prob = total_num_attr / data_size;
// flog.debug("{("+total_num_attr +"/"+data_size +":"+prob +")* [");
double info = calc_info(instances_by_attr.getDistributionOf(attr_category));
sum += prob * info;
// flog.debug("]} ");
}
}
// flog.debug("\n == "+sum);
return sum;
}