/**
* Build the associator on the filtered data.
*
* @param data the training data
* @throws Exception if the Associator could not be built successfully
*/
public void buildAssociations(Instances data) throws Exception {
if (m_Associator == null) throw new Exception("No base associator has been set!");
// create copy and set class-index
data = new Instances(data);
if (getClassIndex() == 0) {
data.setClassIndex(data.numAttributes() - 1);
} else {
data.setClassIndex(getClassIndex() - 1);
}
if (getClassIndex() != -1) {
// remove instances with missing class
data.deleteWithMissingClass();
}
m_Filter.setInputFormat(data); // filter capabilities are checked here
data = Filter.useFilter(data, m_Filter);
// can associator handle the data?
getAssociator().getCapabilities().testWithFail(data);
m_FilteredInstances = data.stringFreeStructure();
m_Associator.buildAssociations(data);
}
/**
* Method for building this classifier.
*
* @param training the training instances
* @param test the test instances
* @throws Exception if something goes wrong
*/
public void buildClassifier(Instances training, Instances test) throws Exception {
m_ClassifierBuilt = true;
m_Random = new Random(m_Seed);
m_Trainset = training;
m_Testset = test;
// set class index?
if ((m_Trainset.classIndex() == -1) || (m_Testset.classIndex() == -1)) {
m_Trainset.setClassIndex(m_Trainset.numAttributes() - 1);
m_Testset.setClassIndex(m_Trainset.numAttributes() - 1);
}
// are datasets correct?
checkData();
// any other data restrictions not met?
checkRestrictions();
// generate sets
generateSets();
// performs the restarts/iterations
build();
m_Random = null;
}
/**
* 用分类器测试
*
* @param trainFileName
* @param testFileName
*/
public static void classify(String trainFileName, String testFileName) {
try {
File inputFile = new File(fileName + trainFileName); // 训练语料文件
ArffLoader atf = new ArffLoader();
atf.setFile(inputFile);
Instances instancesTrain = atf.getDataSet(); // 读入训练文件
// 设置类标签类
inputFile = new File(fileName + testFileName); // 测试语料文件
atf.setFile(inputFile);
Instances instancesTest = atf.getDataSet(); // 读入测试文件
instancesTest.setClassIndex(instancesTest.numAttributes() - 1);
instancesTrain.setClassIndex(instancesTrain.numAttributes() - 1);
classifier = (Classifier) Class.forName(CLASSIFIERNAME).newInstance();
classifier.buildClassifier(instancesTrain);
Evaluation eval = new Evaluation(instancesTrain);
// 第一个为一个训练过的分类器，第二个参数是在某个数据集上评价的数据集
eval.evaluateModel(classifier, instancesTest);
System.out.println(eval.toClassDetailsString());
System.out.println(eval.toSummaryString());
System.out.println(eval.toMatrixString());
System.out.println("precision is :" + (1 - eval.errorRate()));
} catch (Exception e) {
e.printStackTrace();
}
}
public static void run(String[] args) throws Exception {
/**
* *************************************************
*
* @param args[0]: train arff path
* @param args[1]: test arff path
*/
DataSource source = new DataSource(args[0]);
Instances data = source.getDataSet();
data.setClassIndex(data.numAttributes() - 1);
NaiveBayes model = new NaiveBayes();
model.buildClassifier(data);
// Evaluation:
Evaluation eval = new Evaluation(data);
Instances testData = new DataSource(args[1]).getDataSet();
testData.setClassIndex(testData.numAttributes() - 1);
eval.evaluateModel(model, testData);
System.out.println(model.toString());
System.out.println(eval.toSummaryString("\nResults\n======\n", false));
System.out.println("======\nConfusion Matrix:");
double[][] confusionM = eval.confusionMatrix();
for (int i = 0; i < confusionM.length; ++i) {
for (int j = 0; j < confusionM[i].length; ++j) {
System.out.format("%10s ", confusionM[i][j]);
}
System.out.print("\n");
}
}
/** @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);
}
/**
* processes the instances using the HAAR algorithm
*
* @param instances the data to process
* @return the modified data
* @throws Exception in case the processing goes wrong
*/
protected Instances processHAAR(Instances instances) throws Exception {
Instances result;
int i;
int n;
int j;
int clsIdx;
double[] oldVal;
double[] newVal;
int level;
int length;
double[] clsVal;
Attribute clsAtt;
clsIdx = instances.classIndex();
clsVal = null;
clsAtt = null;
if (clsIdx > -1) {
clsVal = instances.attributeToDoubleArray(clsIdx);
clsAtt = (Attribute) instances.classAttribute().copy();
instances.setClassIndex(-1);
instances.deleteAttributeAt(clsIdx);
}
result = new Instances(instances, 0);
level = (int) StrictMath.ceil(StrictMath.log(instances.numAttributes()) / StrictMath.log(2.0));
for (i = 0; i < instances.numInstances(); i++) {
oldVal = instances.instance(i).toDoubleArray();
newVal = new double[oldVal.length];
for (n = level; n > 0; n--) {
length = (int) StrictMath.pow(2, n - 1);
for (j = 0; j < length; j++) {
newVal[j] = (oldVal[j * 2] + oldVal[j * 2 + 1]) / StrictMath.sqrt(2);
newVal[j + length] = (oldVal[j * 2] - oldVal[j * 2 + 1]) / StrictMath.sqrt(2);
}
System.arraycopy(newVal, 0, oldVal, 0, newVal.length);
}
// add new transformed instance
result.add(new DenseInstance(1, newVal));
}
// add class again
if (clsIdx > -1) {
result.insertAttributeAt(clsAtt, clsIdx);
result.setClassIndex(clsIdx);
for (i = 0; i < clsVal.length; i++) result.instance(i).setClassValue(clsVal[i]);
}
return result;
}
public static Double runClassify(String trainFile, String testFile) {
double predictOrder = 0.0;
double trueOrder = 0.0;
try {
String trainWekaFileName = trainFile;
String testWekaFileName = testFile;
Instances train = DataSource.read(trainWekaFileName);
Instances test = DataSource.read(testWekaFileName);
train.setClassIndex(0);
test.setClassIndex(0);
train.deleteAttributeAt(8);
test.deleteAttributeAt(8);
train.deleteAttributeAt(6);
test.deleteAttributeAt(6);
train.deleteAttributeAt(5);
test.deleteAttributeAt(5);
train.deleteAttributeAt(4);
test.deleteAttributeAt(4);
// AdditiveRegression classifier = new AdditiveRegression();
// NaiveBayes classifier = new NaiveBayes();
RandomForest classifier = new RandomForest();
// LibSVM classifier = new LibSVM();
classifier.buildClassifier(train);
Evaluation eval = new Evaluation(train);
eval.evaluateModel(classifier, test);
System.out.println(eval.toSummaryString("\nResults\n\n", true));
// System.out.println(eval.toClassDetailsString());
// System.out.println(eval.toMatrixString());
int k = 892;
for (int i = 0; i < test.numInstances(); i++) {
predictOrder = classifier.classifyInstance(test.instance(i));
trueOrder = test.instance(i).classValue();
System.out.println((k++) + "," + (int) predictOrder);
}
} catch (Exception e) {
e.printStackTrace();
}
return predictOrder;
}
/**
* Sets instances that should be stored.
*
* @param instances the instances
*/
@Override
public void setInstances(Instances instances) {
m_ClassIndex.setUpper(instances.numAttributes() - 1);
instances.setClassIndex(m_ClassIndex.getIndex());
super.setInstances(instances);
}
/**
* Set the output format. Takes the current average class values and m_InputFormat and calls
* setOutputFormat(Instances) appropriately.
*/
private void setOutputFormat() {
Instances newData;
FastVector newAtts, newVals;
// Compute new attributes
newAtts = new FastVector(getInputFormat().numAttributes());
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if (!m_AttIndices.isInRange(j) || !att.isString()) {
// We don't have to copy the attribute because the
// attribute index remains unchanged.
newAtts.addElement(att);
} else {
// Compute list of attribute values
newVals = new FastVector(att.numValues());
for (int i = 0; i < att.numValues(); i++) {
newVals.addElement(att.value(i));
}
newAtts.addElement(new Attribute(att.name(), newVals));
}
}
// Construct new header
newData = new Instances(getInputFormat().relationName(), newAtts, 0);
newData.setClassIndex(getInputFormat().classIndex());
setOutputFormat(newData);
}
public static Instances getInstances(String file) throws Exception {
DataSource datasource = new DataSource(file);
Instances data = datasource.getDataSet();
System.out.println("Class index is : " + data.classIndex());
if (data.classIndex() == -1) data.setClassIndex(data.numAttributes() - 1);
return data;
}
public Instances transformInstances(MultiLabelInstances mlData) throws Exception {
labelIndices = mlData.getLabelIndices();
numOfLabels = mlData.getNumLabels();
Instances data = mlData.getDataSet();
Instances transformed = new Instances(mlData.getDataSet(), 0);
// delete all labels
transformed = RemoveAllLabels.transformInstances(transformed, labelIndices);
// add single label attribute
ArrayList<String> classValues = new ArrayList<String>(numOfLabels);
for (int x = 0; x < numOfLabels; x++) {
classValues.add("Class" + (x + 1));
}
Attribute newClass = new Attribute("Class", classValues);
transformed.insertAttributeAt(newClass, transformed.numAttributes());
transformed.setClassIndex(transformed.numAttributes() - 1);
for (int instanceIndex = 0; instanceIndex < data.numInstances(); instanceIndex++) {
// System.out.println(data.instance(instanceIndex).toString());
List<Instance> result = transformInstance(data.instance(instanceIndex));
for (Instance instance : result) {
// System.out.println(instance.toString());
transformed.add(instance);
// System.out.println(transformed.instance(transformed.numInstances()-1));
}
}
return transformed;
}
public static void main(String[] args) throws Exception {
// TODO Auto-generated method stub
// String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/Data/audiology.arff";
// String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/Data/cleveland.arff";
// String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/Data/colic.arff";
// String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/Data/credit.arff";
// String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/Data/dermatology.arff";
// String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/Data/hepatitis.arff";
// String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/Data/labor.arff";
String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/Data/soybean.arff";
// String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/Data/wine.arff";
// String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/Data/wdbc.arff";
Instances m_data = new Instances(new FileReader(fn));
m_data.setClassIndex(m_data.numAttributes() - 1);
// SimilarityStyle sstyle = new SStyle_Abs1lambda_VmaxVmin(4);
SimilarityStyle sstyle = new SStyle_MaxMin();
ImplicatorTnormStyle itstyle = new ITStyle_KleeneDienes();
MStyle_ConditionalEntropy mg = new MStyle_ConditionalEntropy(m_data, sstyle, itstyle);
// mg.getInformation();
// System.out.println(Arrays.toString(mg.getSelectedAtt()));
String str1 = Utils.doubleFormat("0.0000", mg.m_useTime) + "s & ";
String str2 = (mg.m_selectAtt.length - 1) + " & ";
int[] ans = mg.m_selectAtt.clone();
String str = "";
for (int i = 0; i < ans.length - 1; ++i) {
str += (ans[i] + 1) + ",";
}
String str3 = str.substring(0, str.length() - 1) + " \\\\";
System.out.println(str1 + str2 + str3);
}
private void jButton1ActionPerformed(
java.awt.event.ActionEvent evt) { // GEN-FIRST:event_jButton1ActionPerformed
jDOpen openDialog = new jDOpen(this, true);
openDialog.show();
if (openDialog.fileName != "") {
try {
BufferedReader reader = new BufferedReader(new FileReader(openDialog.fileName));
training = new Instances(reader);
training.setClassIndex(training.numAttributes() - 1);
jTextField1.setText(openDialog.fileName);
jTextArea1.append("Dataset changed: ");
jTextArea1.append(openDialog.fileName);
jTextArea1.append("\n");
jButton3.setEnabled(true);
} catch (Exception ex) {
jTextField1.setText("");
jTextArea1.append("Fail to load: '");
jTextArea1.append(openDialog.fileName);
jTextArea1.append("' (is it a correct dataset?)\n");
jButton3.setEnabled(false);
}
}
} // GEN-LAST:event_jButton1ActionPerformed
/**
* @param args
* @throws Exception
*/
public static void main(String[] args) throws Exception {
// TODO Auto-generated method stub
oneAlgorithm oneAlg = new oneAlgorithm();
oneAlg.category = xCategory.RSandFCBFalg;
oneAlg.style = xStyle.fuzzySU;
oneAlg.flag = false;
oneAlg.alpha = 2.0;
// String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/Data/wine.arff";
// String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/Data/wdbc.arff";
String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/Data/glass.arff";
// String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/shen/wine-shen.arff";
// String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/fuzzy/fuzzy-ex.arff";
// String fn = "C:/Users/Eric/Desktop/2011秋冬/Code/Xreducer/data/derm.arff";
oneFile onef = new oneFile(new File(fn));
Instances dataset = new Instances(new FileReader(fn));
dataset.setClassIndex(dataset.numAttributes() - 1);
onef.ins = dataset.numInstances();
onef.att = dataset.numAttributes();
onef.cla = dataset.numClasses();
RSandFCBFReduceMethod rs = new RSandFCBFReduceMethod(onef, oneAlg);
boolean[] B = new boolean[rs.NumAttr];
boolean[] rq = rs.getOneReduction(B);
System.out.println(Arrays.toString(Utils.boolean2select(rq)));
}
public weka.core.Instances toWekaInstances() {
// attributes
FastVector wattrs = new FastVector();
Iterator itr = attributes.iterator();
while (itr.hasNext()) {
Attribute attr = (Attribute) itr.next();
wattrs.addElement(attr.toWekaAttribute());
}
// data instances
weka.core.Instances winsts = new weka.core.Instances(name, wattrs, instances.size());
itr = instances.iterator();
while (itr.hasNext()) {
Instance inst = (Instance) itr.next();
Iterator itrval = inst.getValues().iterator();
Iterator itrmis = inst.getMissing().iterator();
double[] vals = new double[wattrs.size()];
for (int i = 0; i < wattrs.size(); i++) {
double val = (Double) itrval.next();
if ((Boolean) itrmis.next()) {
vals[i] = weka.core.Instance.missingValue();
} else {
vals[i] = val;
}
}
weka.core.Instance winst = new weka.core.Instance(1, vals);
winst.setDataset(winsts);
winsts.add(winst);
}
winsts.setClassIndex(this.class_index);
return winsts;
}
/**
* Determines and returns (if possible) the structure (internally the header) of the data set as
* an empty set of instances.
*
* @return the structure of the data set as an empty set of Instances
* @throws IOException if an error occurs
*/
public Instances getStructure() throws IOException {
if (getDirectory() == null) {
throw new IOException("No directory/source has been specified");
}
// determine class labels, i.e., sub-dirs
if (m_structure == null) {
String directoryPath = getDirectory().getAbsolutePath();
ArrayList<Attribute> atts = new ArrayList<Attribute>();
ArrayList<String> classes = new ArrayList<String>();
File dir = new File(directoryPath);
String[] subdirs = dir.list();
for (int i = 0; i < subdirs.length; i++) {
File subdir = new File(directoryPath + File.separator + subdirs[i]);
if (subdir.isDirectory()) classes.add(subdirs[i]);
}
atts.add(new Attribute("text", (ArrayList<String>) null));
if (m_OutputFilename) atts.add(new Attribute("filename", (ArrayList<String>) null));
// make sure that the name of the class attribute is unlikely to
// clash with any attribute created via the StringToWordVector filter
atts.add(new Attribute("@@class@@", classes));
String relName = directoryPath.replaceAll("/", "_");
relName = relName.replaceAll("\\\\", "_").replaceAll(":", "_");
m_structure = new Instances(relName, atts, 0);
m_structure.setClassIndex(m_structure.numAttributes() - 1);
}
return m_structure;
}
public static void main(String args[]) throws MWException, FileNotFoundException, IOException {
ClusterEnsembleJavaclass a = new ClusterEnsembleJavaclass();
String dataname = "half-rings";
// String dataname = "Aggregation";
// String dataname = "Compound";
// String dataname = "twomoons";
// String dataname = "Pathbased";
// String dataname = "Spiral";
// String dataname = "D31";
// String dataname = "R15";
// String dataname = "Flame";
String path = "C:\\Users\\Eric\\Desktop\\2012Çﶬ\\NO.4\\data\\" + dataname + ".arff";
Instances data = new Instances(new FileReader(path));
data.setClassIndex(data.numAttributes() - 1);
Object[] rhs = new Object[2];
int n = data.numInstances();
double[][] pData = new double[2][n];
for (int i = 0; i < n; ++i) {
pData[0][i] = data.instance(i).value(0);
pData[1][i] = data.instance(i).value(1);
}
rhs[0] = new MWNumericArray(pData, MWClassID.SINGLE);
rhs[1] = new MWNumericArray(3, MWClassID.SINGLE);
Object[] outRes = new Object[1];
outRes = a.cspa(1, rhs);
MWNumericArray temp = (MWNumericArray) outRes[0];
float[] weights = (float[]) temp.toFloatArray();
System.out.println(Arrays.toString(weights));
}
public static void wekaAlgorithms(Instances data) throws Exception {
classifier = new FilteredClassifier(); // new instance of tree
classifier.setClassifier(new NaiveBayes());
// classifier.setClassifier(new J48());
// classifier.setClassifier(new RandomForest());
// classifier.setClassifier(new ZeroR());
// classifier.setClassifier(new NaiveBayes());
// classifier.setClassifier(new IBk());
data.setClassIndex(data.numAttributes() - 1);
Evaluation eval = new Evaluation(data);
int folds = 10;
eval.crossValidateModel(classifier, data, folds, new Random(1));
System.out.println("===== Evaluating on filtered (training) dataset =====");
System.out.println(eval.toSummaryString());
System.out.println(eval.toClassDetailsString());
double[][] mat = eval.confusionMatrix();
System.out.println("========= Confusion Matrix =========");
for (int i = 0; i < mat.length; i++) {
for (int j = 0; j < mat.length; j++) {
System.out.print(mat[i][j] + " ");
}
System.out.println(" ");
}
}
/** trains the classifier */
@Override
public void train() throws Exception {
if (_train.classIndex() == -1) _train.setClassIndex(_train.numAttributes() - 1);
_cl.buildClassifier(_train);
// evaluate classifier and print some statistics
evaluate();
}
/** tests whether a URL can be loaded (via setURL(URL)). */
public void testURLSourcedLoader() {
Instances data;
if (!(getLoader() instanceof URLSourcedLoader)) {
return;
}
try {
// save
m_Saver.setInstances(m_Instances);
m_Saver.setFile(new File(m_ExportFilename));
m_Saver.writeBatch();
// load
((URLSourcedLoader) m_Loader).setURL(new File(m_ExportFilename).toURI().toURL().toString());
data = m_Loader.getDataSet();
// compare data
try {
if (m_Instances.classIndex() != data.classIndex()) {
data.setClassIndex(m_Instances.classIndex());
}
compareDatasets(m_Instances, data);
} catch (Exception e) {
fail("URL load failed (datasets differ): " + e.toString());
}
} catch (Exception e) {
e.printStackTrace();
fail("URL load failed: " + e.toString());
}
}
/** tests whether data can be loaded via setSource() with a file stream. */
public void testLoaderWithStream() {
Instances data;
try {
// save
m_Saver.setInstances(m_Instances);
m_Saver.setFile(new File(m_ExportFilename));
m_Saver.writeBatch();
// load
m_Loader.setSource(new FileInputStream(new File(m_ExportFilename)));
data = m_Loader.getDataSet();
// compare data
try {
if (m_Instances.classIndex() != data.classIndex()) {
data.setClassIndex(m_Instances.classIndex());
}
compareDatasets(m_Instances, data);
} catch (Exception e) {
fail("File stream loading failed (datasets differ): " + e.toString());
}
} catch (Exception e) {
e.printStackTrace();
fail("File stream loading failed: " + e.toString());
}
}
/** test the batch saving/loading (via setFile(File)). */
public void testBatch() {
Instances data;
try {
// save
m_Saver.setInstances(m_Instances);
m_Saver.setFile(new File(m_ExportFilename));
m_Saver.writeBatch();
// load
((AbstractFileLoader) m_Loader).setFile(new File(m_ExportFilename));
data = m_Loader.getDataSet();
// compare data
try {
if (m_Instances.classIndex() != data.classIndex()) {
data.setClassIndex(m_Instances.classIndex());
}
compareDatasets(m_Instances, data);
} catch (Exception e) {
fail("Incremental load failed (datasets differ): " + e.toString());
}
} catch (Exception e) {
e.printStackTrace();
fail("Batch save/load failed: " + e.toString());
}
}
/**
* Tests the ThresholdCurve generation from the command line. The classifier is currently
* hardcoded. Pipe in an arff file.
*
* @param args currently ignored
*/
public static void main(String[] args) {
try {
Instances inst = new Instances(new java.io.InputStreamReader(System.in));
if (false) {
System.out.println(ThresholdCurve.getNPointPrecision(inst, 11));
} else {
inst.setClassIndex(inst.numAttributes() - 1);
ThresholdCurve tc = new ThresholdCurve();
EvaluationUtils eu = new EvaluationUtils();
Classifier classifier = new weka.classifiers.functions.Logistic();
FastVector predictions = new FastVector();
for (int i = 0; i < 2; i++) { // Do two runs.
eu.setSeed(i);
predictions.appendElements(eu.getCVPredictions(classifier, inst, 10));
// System.out.println("\n\n\n");
}
Instances result = tc.getCurve(predictions);
System.out.println(result);
}
} catch (Exception ex) {
ex.printStackTrace();
}
}
/**
* Sets the format of the input instances.
*
* @param instanceInfo an Instances object containing the input instance structure (any instances
* contained in the object are ignored - only the structure is required).
* @return true if the outputFormat may be collected immediately
* @throws UnsupportedAttributeTypeException if selected attributes are not numeric or nominal.
*/
public boolean setInputFormat(Instances instanceInfo) throws Exception {
if ((instanceInfo.classIndex() > 0) && (!getFillWithMissing())) {
throw new IllegalArgumentException(
"TimeSeriesTranslate: Need to fill in missing values "
+ "using appropriate option when class index is set.");
}
super.setInputFormat(instanceInfo);
// Create the output buffer
Instances outputFormat = new Instances(instanceInfo, 0);
for (int i = 0; i < instanceInfo.numAttributes(); i++) {
if (i != instanceInfo.classIndex()) {
if (m_SelectedCols.isInRange(i)) {
if (outputFormat.attribute(i).isNominal() || outputFormat.attribute(i).isNumeric()) {
outputFormat.renameAttribute(
i,
outputFormat.attribute(i).name()
+ (m_InstanceRange < 0 ? '-' : '+')
+ Math.abs(m_InstanceRange));
} else {
throw new UnsupportedAttributeTypeException(
"Only numeric and nominal attributes may be " + " manipulated in time series.");
}
}
}
}
outputFormat.setClassIndex(instanceInfo.classIndex());
setOutputFormat(outputFormat);
return true;
}
/**
* Adds the prediction intervals as additional attributes at the end. Since classifiers can
* returns varying number of intervals per instance, the dataset is filled with missing values for
* non-existing intervals.
*/
protected void addPredictionIntervals() {
int maxNum;
int num;
int i;
int n;
FastVector preds;
FastVector atts;
Instances data;
Instance inst;
Instance newInst;
double[] values;
double[][] predInt;
// determine the maximum number of intervals
maxNum = 0;
preds = m_Evaluation.predictions();
for (i = 0; i < preds.size(); i++) {
num = ((NumericPrediction) preds.elementAt(i)).predictionIntervals().length;
if (num > maxNum) maxNum = num;
}
// create new header
atts = new FastVector();
for (i = 0; i < m_PlotInstances.numAttributes(); i++)
atts.addElement(m_PlotInstances.attribute(i));
for (i = 0; i < maxNum; i++) {
atts.addElement(new Attribute("predictionInterval_" + (i + 1) + "-lowerBoundary"));
atts.addElement(new Attribute("predictionInterval_" + (i + 1) + "-upperBoundary"));
atts.addElement(new Attribute("predictionInterval_" + (i + 1) + "-width"));
}
data = new Instances(m_PlotInstances.relationName(), atts, m_PlotInstances.numInstances());
data.setClassIndex(m_PlotInstances.classIndex());
// update data
for (i = 0; i < m_PlotInstances.numInstances(); i++) {
inst = m_PlotInstances.instance(i);
// copy old values
values = new double[data.numAttributes()];
System.arraycopy(inst.toDoubleArray(), 0, values, 0, inst.numAttributes());
// add interval data
predInt = ((NumericPrediction) preds.elementAt(i)).predictionIntervals();
for (n = 0; n < maxNum; n++) {
if (n < predInt.length) {
values[m_PlotInstances.numAttributes() + n * 3 + 0] = predInt[n][0];
values[m_PlotInstances.numAttributes() + n * 3 + 1] = predInt[n][1];
values[m_PlotInstances.numAttributes() + n * 3 + 2] = predInt[n][1] - predInt[n][0];
} else {
values[m_PlotInstances.numAttributes() + n * 3 + 0] = Utils.missingValue();
values[m_PlotInstances.numAttributes() + n * 3 + 1] = Utils.missingValue();
values[m_PlotInstances.numAttributes() + n * 3 + 2] = Utils.missingValue();
}
}
// create new Instance
newInst = new DenseInstance(inst.weight(), values);
data.add(newInst);
}
m_PlotInstances = data;
}
public void run() throws Exception {
BufferedReader datafileclassificationpickup =
readDataFile(Config.outputPath() + "DaysPickUpClassification.txt");
BufferedReader datafileclassificationdropoff =
readDataFile(Config.outputPath() + "DaysDropOffClassification.txt");
BufferedReader datafileregresssionpickup =
readDataFile(Config.outputPath() + "DaysPickUpRegression.txt");
BufferedReader datafileregresssiondropoff =
readDataFile(Config.outputPath() + "DaysDropOffRegression.txt");
dataclassificationpickup = new Instances(datafileclassificationpickup);
dataclassificationpickup.setClassIndex(dataclassificationpickup.numAttributes() - 1);
dataclassificationdropoff = new Instances(datafileclassificationdropoff);
dataclassificationdropoff.setClassIndex(dataclassificationdropoff.numAttributes() - 1);
dataregressionpickup = new Instances(datafileregresssionpickup);
dataregressionpickup.setClassIndex(dataregressionpickup.numAttributes() - 1);
dataregressiondropoff = new Instances(datafileregresssiondropoff);
dataregressiondropoff.setClassIndex(dataregressiondropoff.numAttributes() - 1);
System.out.println("KNN classification model");
ibkclassificationpickup = new IBk(10);
ibkclassificationpickup.buildClassifier(dataclassificationpickup);
ibkclassificationdropoff = new IBk(10);
ibkclassificationdropoff.buildClassifier(dataclassificationdropoff);
System.out.println("Classification Model Ready");
System.out.println("KNN regression model");
ibkregressionpickup = new IBk(10);
ibkregressionpickup.buildClassifier(dataregressionpickup);
ibkregressiondropoff = new IBk(10);
ibkregressiondropoff.buildClassifier(dataregressiondropoff);
System.out.println("Regression Model Ready");
instclassificationpickup = new DenseInstance(9);
instclassificationpickup.setDataset(dataclassificationpickup);
instclassificationdropoff = new DenseInstance(9);
instclassificationdropoff.setDataset(dataclassificationdropoff);
instregressionpickup = new DenseInstance(9);
instregressionpickup.setDataset(dataregressionpickup);
instregressiondropoff = new DenseInstance(9);
instregressiondropoff.setDataset(dataregressiondropoff);
System.out.println("Models ready");
}
/**
* Read the sparse feature vector data from the data file and convert it into the Weka's instance
* format.
*/
public void readSparseFVsFromFile(
File dataFile, int numDocs, boolean trainingMode, int numLabels, boolean surroundMode) {
int numFeats = 0;
int numClasses = 0;
labelsFVDoc = new LabelsOfFeatureVectorDoc[numDocs];
// Read the sparse FVs by using the method in MultiClassLearning class
MultiClassLearning multiClassL = new MultiClassLearning();
boolean isUsingDataFile = false;
File tempFVDataFile = null;
multiClassL.getDataFromFile(numDocs, dataFile, isUsingDataFile, tempFVDataFile);
// Create the attributes.
numFeats = multiClassL.dataFVinDoc.getTotalNumFeatures();
FastVector attributes = new FastVector(numFeats + 1);
for (int i = 0; i < numFeats; ++i)
attributes.addElement(new Attribute(new Integer(i + 1).toString()));
// Add class attribute.
if (surroundMode) numClasses = 2 * numLabels + 1; // count the null too, as value -1.
else numClasses = numLabels + 1;
FastVector classValues = new FastVector(numClasses);
classValues.addElement("-1"); // The first class for null class
for (int i = 1; i < numClasses; ++i) classValues.addElement(new Integer(i).toString());
attributes.addElement(new Attribute("Class", classValues));
// Create the dataset with capacity of all FVs (but actuall number of FVs
// mabe be larger than the pre-specified, because possible multi-label) and
// set index of class
instancesData =
new Instances("SparseFVsData", attributes, multiClassL.dataFVinDoc.getNumTraining());
instancesData.setClassIndex(instancesData.numAttributes() - 1);
// Copy the data into the instance;
for (int iDoc = 0; iDoc < multiClassL.dataFVinDoc.getNumTrainingDocs(); ++iDoc) {
SparseFeatureVector[] fvs = multiClassL.dataFVinDoc.trainingFVinDoc[iDoc].getFvs();
labelsFVDoc[iDoc] = new LabelsOfFeatureVectorDoc();
labelsFVDoc[iDoc].multiLabels = multiClassL.dataFVinDoc.labelsFVDoc[iDoc].multiLabels;
for (int i = 0; i < fvs.length; ++i) {
// Object valueO = fvs[i].getValues();
double[] values = new double[fvs[i].getLen()];
int[] indexes = new int[fvs[i].getLen()];
for (int j = 0; j < fvs[i].getLen(); ++j) {
// values[j] = (double)fvs[i].values[j];
values[j] = fvs[i].nodes[j].value;
indexes[j] = fvs[i].nodes[j].index;
}
SparseInstance inst = new SparseInstance(1.0, values, indexes, 50000);
inst.setDataset(instancesData);
if (trainingMode && labelsFVDoc[iDoc].multiLabels[i].num > 0)
for (int j1 = 0; j1 < labelsFVDoc[iDoc].multiLabels[i].num; ++j1) {
inst.setClassValue((labelsFVDoc[iDoc].multiLabels[i].labels[j1])); // label
// >0
instancesData.add(inst);
}
else {
inst.setClassValue("-1"); // set label as -1 for null
instancesData.add(inst);
}
}
}
return;
}
/** evaluates the classifier */
@Override
public void evaluate() throws Exception {
// evaluate classifier and print some statistics
if (_test.classIndex() == -1) _test.setClassIndex(_test.numAttributes() - 1);
Evaluation eval = new Evaluation(_train);
eval.evaluateModel(_cl, _test);
System.out.println(eval.toSummaryString("\nResults\n======\n", false));
System.out.println(eval.toMatrixString());
}
public static void main(String[] args) throws Exception {
BufferedReader reader = new BufferedReader(new FileReader("PCAin.arff"));
Instances data = new Instances(reader);
reader.close();
if (data.classIndex() == -1) {
data.setClassIndex(data.numAttributes() - 1);
}
pca(data);
}