@Override
public Instances getDataSet() throws IOException {
if (m_sourceReader == null) {
throw new IOException("No source has been specified");
}
if (getRetrieval() == INCREMENTAL) {
throw new IOException("Cannot mix getting instances in both incremental and batch modes");
}
setRetrieval(BATCH);
if (m_structure == null) {
getStructure();
}
while (readData(true)) {;
}
m_dataDumper.flush();
m_dataDumper.close();
// make final structure
makeStructure();
Reader sr = new BufferedReader(new FileReader(m_tempFile));
ArffReader initialArff = new ArffReader(sr, m_structure, 0, m_fieldSeparatorAndEnclosures);
Instances initialInsts = initialArff.getData();
sr.close();
initialArff = null;
return initialInsts;
}
/**
* Return the full data set. If the structure hasn't yet been determined by a call to getStructure
* then method should do so before processing the rest of the data set.
*
* @return the structure of the data set as an empty set of Instances
* @exception IOException if there is no source or parsing fails
*/
@Override
public Instances getDataSet() throws IOException {
if ((m_sourceFile == null) && (m_sourceReader == null)) {
throw new IOException("No source has been specified");
}
if (m_structure == null) {
getStructure();
}
if (m_st == null) {
m_st = new StreamTokenizer(m_sourceReader);
initTokenizer(m_st);
}
m_st.ordinaryChar(m_FieldSeparator.charAt(0));
m_cumulativeStructure = new ArrayList<Hashtable<Object, Integer>>(m_structure.numAttributes());
for (int i = 0; i < m_structure.numAttributes(); i++) {
m_cumulativeStructure.add(new Hashtable<Object, Integer>());
}
m_cumulativeInstances = new ArrayList<ArrayList<Object>>();
ArrayList<Object> current;
while ((current = getInstance(m_st)) != null) {
m_cumulativeInstances.add(current);
}
ArrayList<Attribute> atts = new ArrayList<Attribute>(m_structure.numAttributes());
for (int i = 0; i < m_structure.numAttributes(); i++) {
String attname = m_structure.attribute(i).name();
Hashtable<Object, Integer> tempHash = m_cumulativeStructure.get(i);
if (tempHash.size() == 0) {
atts.add(new Attribute(attname));
} else {
if (m_StringAttributes.isInRange(i)) {
atts.add(new Attribute(attname, (ArrayList<String>) null));
} else {
ArrayList<String> values = new ArrayList<String>(tempHash.size());
// add dummy objects in order to make the ArrayList's size == capacity
for (int z = 0; z < tempHash.size(); z++) {
values.add("dummy");
}
Enumeration e = tempHash.keys();
while (e.hasMoreElements()) {
Object ob = e.nextElement();
// if (ob instanceof Double) {
int index = ((Integer) tempHash.get(ob)).intValue();
String s = ob.toString();
if (s.startsWith("'") || s.startsWith("\"")) s = s.substring(1, s.length() - 1);
values.set(index, new String(s));
// }
}
atts.add(new Attribute(attname, values));
}
}
}
// make the instances
String relationName;
if (m_sourceFile != null)
relationName = (m_sourceFile.getName()).replaceAll("\\.[cC][sS][vV]$", "");
else relationName = "stream";
Instances dataSet = new Instances(relationName, atts, m_cumulativeInstances.size());
for (int i = 0; i < m_cumulativeInstances.size(); i++) {
current = m_cumulativeInstances.get(i);
double[] vals = new double[dataSet.numAttributes()];
for (int j = 0; j < current.size(); j++) {
Object cval = current.get(j);
if (cval instanceof String) {
if (((String) cval).compareTo(m_MissingValue) == 0) {
vals[j] = Utils.missingValue();
} else {
if (dataSet.attribute(j).isString()) {
vals[j] = dataSet.attribute(j).addStringValue((String) cval);
} else if (dataSet.attribute(j).isNominal()) {
// find correct index
Hashtable<Object, Integer> lookup = m_cumulativeStructure.get(j);
int index = ((Integer) lookup.get(cval)).intValue();
vals[j] = index;
} else {
throw new IllegalStateException(
"Wrong attribute type at position " + (i + 1) + "!!!");
}
}
} else if (dataSet.attribute(j).isNominal()) {
// find correct index
Hashtable<Object, Integer> lookup = m_cumulativeStructure.get(j);
int index = ((Integer) lookup.get(cval)).intValue();
vals[j] = index;
} else if (dataSet.attribute(j).isString()) {
vals[j] = dataSet.attribute(j).addStringValue("" + cval);
} else {
vals[j] = ((Double) cval).doubleValue();
}
}
dataSet.add(new DenseInstance(1.0, vals));
}
m_structure = new Instances(dataSet, 0);
setRetrieval(BATCH);
m_cumulativeStructure = null; // conserve memory
// close the stream
m_sourceReader.close();
return dataSet;
}