/**
* Parses a given list of options.
*
* <p>
* <!-- options-start -->
* Valid options are:
*
* <p>
*
* <pre> -R <col>
* Sets the range of attribute indices (default last).</pre>
*
* <pre> -V <col>
* Inverts the selection specified by -R.</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 attIndices = Utils.getOption('R', options);
if (attIndices.length() != 0) {
setAttributeRange(attIndices);
} else {
setAttributeRange("last");
}
String invertSelection = Utils.getOption('V', options);
if (invertSelection.length() != 0) {
m_AttIndices.setInvert(true);
} else {
m_AttIndices.setInvert(false);
}
if (getInputFormat() != null) {
setInputFormat(getInputFormat());
}
}
/**
* 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 Exception if the format couldn't be set successfully
*/
public boolean setInputFormat(Instances instanceInfo) throws Exception {
super.setInputFormat(instanceInfo);
m_Insert.setUpper(instanceInfo.numAttributes());
Instances outputFormat = new Instances(instanceInfo, 0);
Attribute newAttribute = null;
switch (m_AttributeType) {
case Attribute.NUMERIC:
newAttribute = new Attribute(m_Name);
break;
case Attribute.NOMINAL:
newAttribute = new Attribute(m_Name, m_Labels);
break;
case Attribute.STRING:
newAttribute = new Attribute(m_Name, (FastVector) null);
break;
case Attribute.DATE:
newAttribute = new Attribute(m_Name, m_DateFormat);
break;
default:
throw new IllegalArgumentException("Unknown attribute type in Add");
}
if ((m_Insert.getIndex() < 0) || (m_Insert.getIndex() > getInputFormat().numAttributes())) {
throw new IllegalArgumentException("Index out of range");
}
outputFormat.insertAttributeAt(newAttribute, m_Insert.getIndex());
setOutputFormat(outputFormat);
// all attributes, except index of added attribute
// (otherwise the length of the input/output indices differ)
Range atts = new Range(m_Insert.getSingleIndex());
atts.setInvert(true);
atts.setUpper(outputFormat.numAttributes() - 1);
initOutputLocators(outputFormat, atts.getSelection());
return true;
}
/**
* Sets whether selected columns should be processed or skipped.
*
* @param value the new invert setting
*/
public void setInvertSelection(boolean value) {
m_AttributeIndices.setInvert(value);
}
/**
* 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 Exception if the format couldn't be set successfully
*/
@Override
public boolean setInputFormat(Instances instanceInfo) throws Exception {
super.setInputFormat(instanceInfo);
int classIndex = instanceInfo.classIndex();
// setup the map
if (m_renameVals != null && m_renameVals.length() > 0) {
String[] vals = m_renameVals.split(",");
for (String val : vals) {
String[] parts = val.split(":");
if (parts.length != 2) {
throw new WekaException("Invalid replacement string: " + val);
}
if (parts[0].length() == 0 || parts[1].length() == 0) {
throw new WekaException("Invalid replacement string: " + val);
}
m_renameMap.put(
m_ignoreCase ? parts[0].toLowerCase().trim() : parts[0].trim(), parts[1].trim());
}
}
// try selected atts as a numeric range first
Range tempRange = new Range();
tempRange.setInvert(m_invert);
if (m_selectedColsString == null) {
m_selectedColsString = "";
}
try {
tempRange.setRanges(m_selectedColsString);
tempRange.setUpper(instanceInfo.numAttributes() - 1);
m_selectedAttributes = tempRange.getSelection();
m_selectedCols = tempRange;
} catch (Exception r) {
// OK, now try as named attributes
StringBuffer indexes = new StringBuffer();
String[] attNames = m_selectedColsString.split(",");
boolean first = true;
for (String n : attNames) {
n = n.trim();
Attribute found = instanceInfo.attribute(n);
if (found == null) {
throw new WekaException(
"Unable to find attribute '" + n + "' in the incoming instances'");
}
if (first) {
indexes.append("" + (found.index() + 1));
first = false;
} else {
indexes.append("," + (found.index() + 1));
}
}
tempRange = new Range();
tempRange.setRanges(indexes.toString());
tempRange.setUpper(instanceInfo.numAttributes() - 1);
m_selectedAttributes = tempRange.getSelection();
m_selectedCols = tempRange;
}
ArrayList<Attribute> attributes = new ArrayList<Attribute>();
for (int i = 0; i < instanceInfo.numAttributes(); i++) {
if (m_selectedCols.isInRange(i)) {
if (instanceInfo.attribute(i).isNominal()) {
List<String> valsForAtt = new ArrayList<String>();
for (int j = 0; j < instanceInfo.attribute(i).numValues(); j++) {
String origV = instanceInfo.attribute(i).value(j);
String replace =
m_ignoreCase ? m_renameMap.get(origV.toLowerCase()) : m_renameMap.get(origV);
if (replace != null && !valsForAtt.contains(replace)) {
valsForAtt.add(replace);
} else {
valsForAtt.add(origV);
}
}
Attribute newAtt = new Attribute(instanceInfo.attribute(i).name(), valsForAtt);
attributes.add(newAtt);
} else {
// ignore any selected attributes that are not nominal
Attribute att = (Attribute) instanceInfo.attribute(i).copy();
attributes.add(att);
}
} else {
Attribute att = (Attribute) instanceInfo.attribute(i).copy();
attributes.add(att);
}
}
Instances outputFormat = new Instances(instanceInfo.relationName(), attributes, 0);
outputFormat.setClassIndex(classIndex);
setOutputFormat(outputFormat);
return true;
}
/**
* Sets whether selected columns should be removed or kept. If true the selected columns are kept
* and unselected columns are deleted. If false selected columns are deleted and unselected
* columns are kept.
*
* @param invert the new invert setting
*/
public void setInvertSelection(boolean invert) {
m_DiscretizeCols.setInvert(invert);
}
/**
* Sets whether selected columns should be worked on or all the others apart from these. If true
* all the other columns are considered for "nominalization".
*
* @param value the new invert setting
*/
public void setInvertSelection(boolean value) {
m_Cols.setInvert(value);
}
/**
* Set whether selected columns should be select or unselect. If true the selected columns are
* modified. If false the selected columns are not modified.
*
* @param invert the new invert setting
*/
public void setInvertSelection(boolean invert) {
m_SelectCols.setInvert(!invert);
}
