/**
* Returns the Capabilities of this filter, customized based on the data. I.e., if removes all
* class capabilities, in case there's not class attribute present or removes the NO_CLASS
* capability, in case that there's a class present.
*
* @param data the data to use for customization
* @return the capabilities of this object, based on the data
* @see #getCapabilities()
*/
public Capabilities getCapabilities(Instances data) {
Capabilities result;
Capabilities classes;
Iterator iter;
Capability cap;
result = getCapabilities();
// no class? -> remove all class capabilites apart from NO_CLASS
if (data.classIndex() == -1) {
classes = result.getClassCapabilities();
iter = classes.capabilities();
while (iter.hasNext()) {
cap = (Capability) iter.next();
if (cap != Capability.NO_CLASS) {
result.disable(cap);
result.disableDependency(cap);
}
}
}
// class? -> remove NO_CLASS
else {
result.disable(Capability.NO_CLASS);
result.disableDependency(Capability.NO_CLASS);
}
return result;
}
/**
* loads the given dataset and prints the Capabilities necessary to process it.
*
* <p>Valid parameters:
*
* <p>-file filename <br>
* the file to load
*
* <p>-c index the explicit index of the class attribute (default: none)
*
* @param args the commandline arguments
* @throws Exception if something goes wrong
*/
public static void main(String[] args) throws Exception {
String tmpStr;
String filename;
DataSource source;
Instances data;
int classIndex;
Capabilities cap;
Iterator iter;
if (args.length == 0) {
System.out.println(
"\nUsage: " + Capabilities.class.getName() + " -file <dataset> [-c <class index>]\n");
return;
}
// get parameters
tmpStr = Utils.getOption("file", args);
if (tmpStr.length() == 0) throw new Exception("No file provided with option '-file'!");
else filename = tmpStr;
tmpStr = Utils.getOption("c", args);
if (tmpStr.length() != 0) {
if (tmpStr.equals("first")) classIndex = 0;
else if (tmpStr.equals("last")) classIndex = -2; // last
else classIndex = Integer.parseInt(tmpStr) - 1;
} else {
classIndex = -3; // not set
}
// load data
source = new DataSource(filename);
if (classIndex == -3) data = source.getDataSet();
else if (classIndex == -2) data = source.getDataSet(source.getStructure().numAttributes() - 1);
else data = source.getDataSet(classIndex);
// determine and print capabilities
cap = forInstances(data);
System.out.println("File: " + filename);
System.out.println(
"Class index: " + ((data.classIndex() == -1) ? "not set" : "" + (data.classIndex() + 1)));
System.out.println("Capabilities:");
iter = cap.capabilities();
while (iter.hasNext()) System.out.println("- " + iter.next());
}
/**
* Tests a certain range of attributes of the given data, whether it can be processed by the
* handler, given its capabilities. Classifiers implementing the <code>
* MultiInstanceCapabilitiesHandler</code> interface are checked automatically for their
* multi-instance Capabilities (if no bags, then only the bag-structure, otherwise only the first
* bag).
*
* @param data the data to test
* @param fromIndex the range of attributes - start (incl.)
* @param toIndex the range of attributes - end (incl.)
* @return true if all the tests succeeded
* @see MultiInstanceCapabilitiesHandler
* @see #m_InstancesTest
* @see #m_MissingValuesTest
* @see #m_MissingClassValuesTest
* @see #m_MinimumNumberInstancesTest
*/
public boolean test(Instances data, int fromIndex, int toIndex) {
int i;
int n;
int m;
Attribute att;
Instance inst;
boolean testClass;
Capabilities cap;
boolean missing;
Iterator iter;
// shall we test the data?
if (!m_InstancesTest) return true;
// no Capabilities? -> warning
if ((m_Capabilities.size() == 0)
|| ((m_Capabilities.size() == 1) && handles(Capability.NO_CLASS)))
System.err.println(createMessage("No capabilities set!"));
// any attributes?
if (toIndex - fromIndex < 0) {
m_FailReason = new WekaException(createMessage("No attributes!"));
return false;
}
// do wee need to test the class attribute, i.e., is the class attribute
// within the range of attributes?
testClass =
(data.classIndex() > -1)
&& (data.classIndex() >= fromIndex)
&& (data.classIndex() <= toIndex);
// attributes
for (i = fromIndex; i <= toIndex; i++) {
att = data.attribute(i);
// class is handled separately
if (i == data.classIndex()) continue;
// check attribute types
if (!test(att)) return false;
}
// class
if (!handles(Capability.NO_CLASS) && (data.classIndex() == -1)) {
m_FailReason = new UnassignedClassException(createMessage("Class attribute not set!"));
return false;
}
// special case: no class attribute can be handled
if (handles(Capability.NO_CLASS) && (data.classIndex() > -1)) {
cap = getClassCapabilities();
cap.disable(Capability.NO_CLASS);
iter = cap.capabilities();
if (!iter.hasNext()) {
m_FailReason = new WekaException(createMessage("Cannot handle any class attribute!"));
return false;
}
}
if (testClass && !handles(Capability.NO_CLASS)) {
att = data.classAttribute();
if (!test(att, true)) return false;
// special handling of RELATIONAL class
// TODO: store additional Capabilities for this case
// missing class labels
if (m_MissingClassValuesTest) {
if (!handles(Capability.MISSING_CLASS_VALUES)) {
for (i = 0; i < data.numInstances(); i++) {
if (data.instance(i).classIsMissing()) {
m_FailReason =
new WekaException(createMessage("Cannot handle missing class values!"));
return false;
}
}
} else {
if (m_MinimumNumberInstancesTest) {
int hasClass = 0;
for (i = 0; i < data.numInstances(); i++) {
if (!data.instance(i).classIsMissing()) hasClass++;
}
// not enough instances with class labels?
if (hasClass < getMinimumNumberInstances()) {
m_FailReason =
new WekaException(
createMessage(
"Not enough training instances with class labels (required: "
+ getMinimumNumberInstances()
+ ", provided: "
+ hasClass
+ ")!"));
return false;
}
}
}
}
}
// missing values
if (m_MissingValuesTest) {
if (!handles(Capability.MISSING_VALUES)) {
missing = false;
for (i = 0; i < data.numInstances(); i++) {
inst = data.instance(i);
if (inst instanceof SparseInstance) {
for (m = 0; m < inst.numValues(); m++) {
n = inst.index(m);
// out of scope?
if (n < fromIndex) continue;
if (n > toIndex) break;
// skip class
if (n == inst.classIndex()) continue;
if (inst.isMissing(n)) {
missing = true;
break;
}
}
} else {
for (n = fromIndex; n <= toIndex; n++) {
// skip class
if (n == inst.classIndex()) continue;
if (inst.isMissing(n)) {
missing = true;
break;
}
}
}
if (missing) {
m_FailReason =
new NoSupportForMissingValuesException(
createMessage("Cannot handle missing values!"));
return false;
}
}
}
}
// instances
if (m_MinimumNumberInstancesTest) {
if (data.numInstances() < getMinimumNumberInstances()) {
m_FailReason =
new WekaException(
createMessage(
"Not enough training instances (required: "
+ getMinimumNumberInstances()
+ ", provided: "
+ data.numInstances()
+ ")!"));
return false;
}
}
// Multi-Instance? -> check structure (regardless of attribute range!)
if (handles(Capability.ONLY_MULTIINSTANCE)) {
// number of attributes?
if (data.numAttributes() != 3) {
m_FailReason =
new WekaException(
createMessage("Incorrect Multi-Instance format, must be 'bag-id, bag, class'!"));
return false;
}
// type of attributes and position of class?
if (!data.attribute(0).isNominal()
|| !data.attribute(1).isRelationValued()
|| (data.classIndex() != data.numAttributes() - 1)) {
m_FailReason =
new WekaException(
createMessage(
"Incorrect Multi-Instance format, must be 'NOMINAL att, RELATIONAL att, CLASS att'!"));
return false;
}
// check data immediately
if (getOwner() instanceof MultiInstanceCapabilitiesHandler) {
MultiInstanceCapabilitiesHandler handler = (MultiInstanceCapabilitiesHandler) getOwner();
cap = handler.getMultiInstanceCapabilities();
boolean result;
if (data.numInstances() > 0) result = cap.test(data.attribute(1).relation(0));
else result = cap.test(data.attribute(1).relation());
if (!result) {
m_FailReason = cap.m_FailReason;
return false;
}
}
}
// passed all tests!
return true;
}