/** @param args */
private void Init() {
testIns.setClassIndex(testIns.numAttributes() - 1);
labeledIns.setClassIndex(labeledIns.numAttributes() - 1);
unlabeledIns.setClassIndex(unlabeledIns.numAttributes() - 1);
class_Array[0] = classifier1;
class_Array[1] = classifier2;
class_Array[2] = classifier3;
}
/**
* Parses a given list of options.
*
* <p>
* <!-- options-start -->
* Valid options are:
*
* <p>
*
* <pre> -i <the input file>
* The input file</pre>
*
* <pre> -o <the output file>
* The output file</pre>
*
* <pre> -c <the class index>
* The class index</pre>
*
* <!-- options-end -->
*
* @param options the list of options as an array of strings
* @throws Exception if an option is not supported
*/
public void setOptions(String[] options) throws Exception {
String outputString = Utils.getOption('o', options);
String inputString = Utils.getOption('i', options);
String indexString = Utils.getOption('c', options);
ArffLoader loader = new ArffLoader();
resetOptions();
// parse index
int index = -1;
if (indexString.length() != 0) {
if (indexString.equals("first")) index = 0;
else {
if (indexString.equals("last")) index = -1;
else index = Integer.parseInt(indexString);
}
}
if (inputString.length() != 0) {
try {
File input = new File(inputString);
loader.setFile(input);
Instances inst = loader.getDataSet();
if (index == -1) inst.setClassIndex(inst.numAttributes() - 1);
else inst.setClassIndex(index);
setInstances(inst);
} catch (Exception ex) {
throw new IOException(
"No data set loaded. Data set has to be arff format (Reason: " + ex.toString() + ").");
}
} else throw new IOException("No data set to save.");
if (outputString.length() != 0) {
// add appropriate file extension
if (!outputString.endsWith(getFileExtension())) {
if (outputString.lastIndexOf('.') != -1)
outputString =
(outputString.substring(0, outputString.lastIndexOf('.'))) + getFileExtension();
else outputString = outputString + getFileExtension();
}
try {
File output = new File(outputString);
setFile(output);
} catch (Exception ex) {
throw new IOException("Cannot create output file.");
}
}
if (index == -1) index = getInstances().numAttributes() - 1;
getInstances().setClassIndex(index);
}
/**
* Determines the output format based on the input format and returns this. In case the output
* format cannot be returned immediately, i.e., immediateOutputFormat() returns false, then this
* method will be called from batchFinished().
*
* @param inputFormat the input format to base the output format on
* @return the output format
* @throws Exception in case the determination goes wrong
* @see #hasImmediateOutputFormat()
* @see #batchFinished()
*/
protected Instances determineOutputFormat(Instances inputFormat) throws Exception {
Instances data;
Instances result;
FastVector atts;
FastVector values;
HashSet hash;
int i;
int n;
boolean isDate;
Instance inst;
Vector sorted;
m_Cols.setUpper(inputFormat.numAttributes() - 1);
data = new Instances(inputFormat);
atts = new FastVector();
for (i = 0; i < data.numAttributes(); i++) {
if (!m_Cols.isInRange(i) || !data.attribute(i).isNumeric()) {
atts.addElement(data.attribute(i));
continue;
}
// date attribute?
isDate = (data.attribute(i).type() == Attribute.DATE);
// determine all available attribtues in dataset
hash = new HashSet();
for (n = 0; n < data.numInstances(); n++) {
inst = data.instance(n);
if (inst.isMissing(i)) continue;
if (isDate) hash.add(inst.stringValue(i));
else hash.add(new Double(inst.value(i)));
}
// sort values
sorted = new Vector();
for (Object o : hash) sorted.add(o);
Collections.sort(sorted);
// create attribute from sorted values
values = new FastVector();
for (Object o : sorted) {
if (isDate) values.addElement(o.toString());
else values.addElement(Utils.doubleToString(((Double) o).doubleValue(), MAX_DECIMALS));
}
atts.addElement(new Attribute(data.attribute(i).name(), values));
}
result = new Instances(inputFormat.relationName(), atts, 0);
result.setClassIndex(inputFormat.classIndex());
return result;
}
/** Main method for testing this class. */
public static void main(String[] options) {
try {
// Create numeric attributes "length" and "weight"
Attribute length = new Attribute("length");
Attribute weight = new Attribute("weight");
// Create vector to hold nominal values "first", "second", "third"
ArrayList<String> my_nominal_values = new ArrayList<String>(3);
my_nominal_values.add("first");
my_nominal_values.add("second");
my_nominal_values.add("third");
// Create nominal attribute "position"
Attribute position = new Attribute("position", my_nominal_values);
// Create vector of the above attributes
ArrayList<Attribute> attributes = new ArrayList<Attribute>(3);
attributes.add(length);
attributes.add(weight);
attributes.add(position);
// Create the empty dataset "race" with above attributes
Instances race = new Instances("race", attributes, 0);
// Make position the class attribute
race.setClassIndex(position.index());
// Create empty instance with three attribute values
SparseInstance inst = new SparseInstance(3);
// Set instance's values for the attributes "length", "weight", and "position"
inst.setValue(length, 5.3);
inst.setValue(weight, 300);
inst.setValue(position, "first");
// Set instance's dataset to be the dataset "race"
inst.setDataset(race);
// Print the instance
System.out.println("The instance: " + inst);
// Print the first attribute
System.out.println("First attribute: " + inst.attribute(0));
// Print the class attribute
System.out.println("Class attribute: " + inst.classAttribute());
// Print the class index
System.out.println("Class index: " + inst.classIndex());
// Say if class is missing
System.out.println("Class is missing: " + inst.classIsMissing());
// Print the instance's class value in internal format
System.out.println("Class value (internal format): " + inst.classValue());
// Print a shallow copy of this instance
SparseInstance copy = (SparseInstance) inst.copy();
System.out.println("Shallow copy: " + copy);
// Set dataset for shallow copy
copy.setDataset(inst.dataset());
System.out.println("Shallow copy with dataset set: " + copy);
// Print out all values in internal format
System.out.print("All stored values in internal format: ");
for (int i = 0; i < inst.numValues(); i++) {
if (i > 0) {
System.out.print(",");
}
System.out.print(inst.valueSparse(i));
}
System.out.println();
// Set all values to zero
System.out.print("All values set to zero: ");
while (inst.numValues() > 0) {
inst.setValueSparse(0, 0);
}
for (int i = 0; i < inst.numValues(); i++) {
if (i > 0) {
System.out.print(",");
}
System.out.print(inst.valueSparse(i));
}
System.out.println();
// Set all values to one
System.out.print("All values set to one: ");
for (int i = 0; i < inst.numAttributes(); i++) {
inst.setValue(i, 1);
}
for (int i = 0; i < inst.numValues(); i++) {
if (i > 0) {
System.out.print(",");
}
System.out.print(inst.valueSparse(i));
}
System.out.println();
// Unset dataset for copy, delete first attribute, and insert it again
copy.setDataset(null);
copy.deleteAttributeAt(0);
copy.insertAttributeAt(0);
copy.setDataset(inst.dataset());
System.out.println("Copy with first attribute deleted and inserted: " + copy);
// Same for second attribute
copy.setDataset(null);
copy.deleteAttributeAt(1);
copy.insertAttributeAt(1);
copy.setDataset(inst.dataset());
System.out.println("Copy with second attribute deleted and inserted: " + copy);
// Same for last attribute
copy.setDataset(null);
copy.deleteAttributeAt(2);
copy.insertAttributeAt(2);
copy.setDataset(inst.dataset());
System.out.println("Copy with third attribute deleted and inserted: " + copy);
// Enumerate attributes (leaving out the class attribute)
System.out.println("Enumerating attributes (leaving out class):");
Enumeration enu = inst.enumerateAttributes();
while (enu.hasMoreElements()) {
Attribute att = (Attribute) enu.nextElement();
System.out.println(att);
}
// Headers are equivalent?
System.out.println("Header of original and copy equivalent: " + inst.equalHeaders(copy));
// Test for missing values
System.out.println("Length of copy missing: " + copy.isMissing(length));
System.out.println("Weight of copy missing: " + copy.isMissing(weight.index()));
System.out.println("Length of copy missing: " + Utils.isMissingValue(copy.value(length)));
// Prints number of attributes and classes
System.out.println("Number of attributes: " + copy.numAttributes());
System.out.println("Number of classes: " + copy.numClasses());
// Replace missing values
double[] meansAndModes = {2, 3, 0};
copy.replaceMissingValues(meansAndModes);
System.out.println("Copy with missing value replaced: " + copy);
// Setting and getting values and weights
copy.setClassMissing();
System.out.println("Copy with missing class: " + copy);
copy.setClassValue(0);
System.out.println("Copy with class value set to first value: " + copy);
copy.setClassValue("third");
System.out.println("Copy with class value set to \"third\": " + copy);
copy.setMissing(1);
System.out.println("Copy with second attribute set to be missing: " + copy);
copy.setMissing(length);
System.out.println("Copy with length set to be missing: " + copy);
copy.setValue(0, 0);
System.out.println("Copy with first attribute set to 0: " + copy);
copy.setValue(weight, 1);
System.out.println("Copy with weight attribute set to 1: " + copy);
copy.setValue(position, "second");
System.out.println("Copy with position set to \"second\": " + copy);
copy.setValue(2, "first");
System.out.println("Copy with last attribute set to \"first\": " + copy);
System.out.println("Current weight of instance copy: " + copy.weight());
copy.setWeight(2);
System.out.println("Current weight of instance copy (set to 2): " + copy.weight());
System.out.println("Last value of copy: " + copy.toString(2));
System.out.println("Value of position for copy: " + copy.toString(position));
System.out.println("Last value of copy (internal format): " + copy.value(2));
System.out.println("Value of position for copy (internal format): " + copy.value(position));
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* Writes a Batch of instances
*
* @throws IOException throws IOException if saving in batch mode is not possible
*/
public void writeBatch() throws IOException {
Instances instances = getInstances();
if (instances == null) throw new IOException("No instances to save");
if (instances.classIndex() == -1) {
instances.setClassIndex(instances.numAttributes() - 1);
System.err.println("No class specified. Last attribute is used as class attribute.");
}
if (instances.attribute(instances.classIndex()).isNumeric())
throw new IOException("To save in C4.5 format the class attribute cannot be numeric.");
if (getRetrieval() == INCREMENTAL)
throw new IOException("Batch and incremental saving cannot be mixed.");
setRetrieval(BATCH);
if (retrieveFile() == null || getWriter() == null) {
throw new IOException(
"C4.5 format requires two files. Therefore no output to standard out can be generated.\nPlease specifiy output files using the -o option.");
}
setWriteMode(WRITE);
// print names file
setFileExtension(".names");
PrintWriter outW = new PrintWriter(getWriter());
for (int i = 0; i < instances.attribute(instances.classIndex()).numValues(); i++) {
outW.write(instances.attribute(instances.classIndex()).value(i));
if (i < instances.attribute(instances.classIndex()).numValues() - 1) {
outW.write(",");
} else {
outW.write(".\n");
}
}
for (int i = 0; i < instances.numAttributes(); i++) {
if (i != instances.classIndex()) {
outW.write(instances.attribute(i).name() + ": ");
if (instances.attribute(i).isNumeric() || instances.attribute(i).isDate()) {
outW.write("continuous.\n");
} else {
Attribute temp = instances.attribute(i);
for (int j = 0; j < temp.numValues(); j++) {
outW.write(temp.value(j));
if (j < temp.numValues() - 1) {
outW.write(",");
} else {
outW.write(".\n");
}
}
}
}
}
outW.flush();
outW.close();
// print data file
String out = retrieveFile().getAbsolutePath();
setFileExtension(".data");
out = out.substring(0, out.lastIndexOf('.')) + getFileExtension();
File namesFile = new File(out);
try {
setFile(namesFile);
} catch (Exception ex) {
throw new IOException(
"Cannot create data file, only names file created (Reason: " + ex.toString() + ").");
}
if (retrieveFile() == null || getWriter() == null) {
throw new IOException("Cannot create data file, only names file created.");
}
outW = new PrintWriter(getWriter());
// print data file
for (int i = 0; i < instances.numInstances(); i++) {
Instance temp = instances.instance(i);
for (int j = 0; j < temp.numAttributes(); j++) {
if (j != instances.classIndex()) {
if (temp.isMissing(j)) {
outW.write("?,");
} else if (instances.attribute(j).isNominal() || instances.attribute(j).isString()) {
outW.write(instances.attribute(j).value((int) temp.value(j)) + ",");
} else {
outW.write("" + temp.value(j) + ",");
}
}
}
// write the class value
if (temp.isMissing(instances.classIndex())) {
outW.write("?");
} else {
outW.write(
instances
.attribute(instances.classIndex())
.value((int) temp.value(instances.classIndex())));
}
outW.write("\n");
}
outW.flush();
outW.close();
setFileExtension(".names");
setWriteMode(WAIT);
outW = null;
resetWriter();
setWriteMode(CANCEL);
}
/**
* Saves an instances incrementally. Structure has to be set by using the setStructure() method or
* setInstances() method.
*
* @param inst the instance to save
* @throws IOException throws IOEXception if an instance cannot be saved incrementally.
*/
public void writeIncremental(Instance inst) throws IOException {
int writeMode = getWriteMode();
Instances structure = getInstances();
PrintWriter outW = null;
if (structure != null) {
if (structure.classIndex() == -1) {
structure.setClassIndex(structure.numAttributes() - 1);
System.err.println("No class specified. Last attribute is used as class attribute.");
}
if (structure.attribute(structure.classIndex()).isNumeric())
throw new IOException("To save in C4.5 format the class attribute cannot be numeric.");
}
if (getRetrieval() == BATCH || getRetrieval() == NONE)
throw new IOException("Batch and incremental saving cannot be mixed.");
if (retrieveFile() == null || getWriter() == null) {
throw new IOException(
"C4.5 format requires two files. Therefore no output to standard out can be generated.\nPlease specifiy output files using the -o option.");
}
outW = new PrintWriter(getWriter());
if (writeMode == WAIT) {
if (structure == null) {
setWriteMode(CANCEL);
if (inst != null)
System.err.println("Structure(Header Information) has to be set in advance");
} else setWriteMode(STRUCTURE_READY);
writeMode = getWriteMode();
}
if (writeMode == CANCEL) {
if (outW != null) outW.close();
cancel();
}
if (writeMode == STRUCTURE_READY) {
setWriteMode(WRITE);
// write header: here names file
for (int i = 0; i < structure.attribute(structure.classIndex()).numValues(); i++) {
outW.write(structure.attribute(structure.classIndex()).value(i));
if (i < structure.attribute(structure.classIndex()).numValues() - 1) {
outW.write(",");
} else {
outW.write(".\n");
}
}
for (int i = 0; i < structure.numAttributes(); i++) {
if (i != structure.classIndex()) {
outW.write(structure.attribute(i).name() + ": ");
if (structure.attribute(i).isNumeric() || structure.attribute(i).isDate()) {
outW.write("continuous.\n");
} else {
Attribute temp = structure.attribute(i);
for (int j = 0; j < temp.numValues(); j++) {
outW.write(temp.value(j));
if (j < temp.numValues() - 1) {
outW.write(",");
} else {
outW.write(".\n");
}
}
}
}
}
outW.flush();
outW.close();
writeMode = getWriteMode();
String out = retrieveFile().getAbsolutePath();
setFileExtension(".data");
out = out.substring(0, out.lastIndexOf('.')) + getFileExtension();
File namesFile = new File(out);
try {
setFile(namesFile);
} catch (Exception ex) {
throw new IOException("Cannot create data file, only names file created.");
}
if (retrieveFile() == null || getWriter() == null) {
throw new IOException("Cannot create data file, only names file created.");
}
outW = new PrintWriter(getWriter());
}
if (writeMode == WRITE) {
if (structure == null) throw new IOException("No instances information available.");
if (inst != null) {
// write instance: here data file
for (int j = 0; j < inst.numAttributes(); j++) {
if (j != structure.classIndex()) {
if (inst.isMissing(j)) {
outW.write("?,");
} else if (structure.attribute(j).isNominal() || structure.attribute(j).isString()) {
outW.write(structure.attribute(j).value((int) inst.value(j)) + ",");
} else {
outW.write("" + inst.value(j) + ",");
}
}
}
// write the class value
if (inst.isMissing(structure.classIndex())) {
outW.write("?");
} else {
outW.write(
structure
.attribute(structure.classIndex())
.value((int) inst.value(structure.classIndex())));
}
outW.write("\n");
// flushes every 100 instances
m_incrementalCounter++;
if (m_incrementalCounter > 100) {
m_incrementalCounter = 0;
outW.flush();
}
} else {
// close
if (outW != null) {
outW.flush();
outW.close();
}
setFileExtension(".names");
m_incrementalCounter = 0;
resetStructure();
outW = null;
resetWriter();
}
}
}
