/// <summary> Sets the format of output instances. The derived class should use this
/// method once it has determined the outputformat. The
/// output queue is cleared.
///
/// </summary>
/// <param name="outputFormat">the new output format
/// </param>
protected internal virtual void setOutputFormat(Instances outputFormat)
{
if (outputFormat != null)
{
m_OutputFormat = outputFormat.stringFreeStructure();
m_OutputStringAtts = getStringIndices(m_OutputFormat);
// Rename the attribute
System.String relationName = outputFormat.relationName() + "-" + this.GetType().FullName;
// if (this instanceof OptionHandler)
// {
// String [] options = ((OptionHandler)this).getOptions();
// for (int i = 0; i < options.length; i++)
// {
// relationName += options[i].trim();
// }
// }
m_OutputFormat.RelationName = relationName;
}
else
{
m_OutputFormat = null;
}
m_OutputQueue = new Queue();
}
/// <summary> Sets the format of the input instances.
///
/// </summary>
/// <param name="instanceInfo">an Instances object containing the input instance
/// structure (any instances contained in the object are ignored - only the
/// structure is required).
/// </param>
/// <returns> true if the outputFormat may be collected immediately
/// </returns>
/// <exception cref="Exception">if the format couldn't be set successfully
/// </exception>
public override bool setInputFormat(Instances instanceInfo)
{
base.setInputFormat(instanceInfo);
m_SelectCols.Upper = instanceInfo.numAttributes() - 1;
// Create the output buffer
FastVector attributes = new FastVector();
int outputClass = - 1;
m_SelectedAttributes = m_SelectCols.Selection;
int inStrKeepLen = 0;
int[] inStrKeep = new int[m_SelectedAttributes.Length];
for (int i = 0; i < m_SelectedAttributes.Length; i++)
{
int current = m_SelectedAttributes[i];
if (instanceInfo.classIndex() == current)
{
outputClass = attributes.size();
}
Attribute keep = (Attribute) instanceInfo.attribute(current).copy();
if (keep.type() == Attribute.STRING)
{
inStrKeep[inStrKeepLen++] = current;
}
attributes.addElement(keep);
}
m_InputStringIndex = new int[inStrKeepLen];
Array.Copy(inStrKeep, 0, m_InputStringIndex, 0, inStrKeepLen);
Instances outputFormat = new Instances(instanceInfo.relationName(), attributes, 0);
outputFormat.ClassIndex = outputClass;
setOutputFormat(outputFormat);
return true;
}
/// <summary> Calculates the area under the ROC curve. This is normalised so
/// that 0.5 is random, 1.0 is perfect and 0.0 is bizarre.
///
/// </summary>
/// <param name="tcurve">a previously extracted threshold curve Instances.
/// </param>
/// <returns> the ROC area, or Double.NaN if you don't pass in
/// a ThresholdCurve generated Instances.
/// </returns>
public static double getROCArea(Instances tcurve)
{
//UPGRADE_NOTE: Final was removed from the declaration of 'n '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
int n = tcurve.numInstances();
if (!RELATION_NAME.Equals(tcurve.relationName()) || (n == 0))
{
return System.Double.NaN;
}
//UPGRADE_NOTE: Final was removed from the declaration of 'tpInd '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
int tpInd = tcurve.attribute(TRUE_POS_NAME).index();
//UPGRADE_NOTE: Final was removed from the declaration of 'fpInd '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
int fpInd = tcurve.attribute(FALSE_POS_NAME).index();
//UPGRADE_NOTE: Final was removed from the declaration of 'tpVals '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double[] tpVals = tcurve.attributeToDoubleArray(tpInd);
//UPGRADE_NOTE: Final was removed from the declaration of 'fpVals '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double[] fpVals = tcurve.attributeToDoubleArray(fpInd);
//UPGRADE_NOTE: Final was removed from the declaration of 'tp0 '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double tp0 = tpVals[0];
//UPGRADE_NOTE: Final was removed from the declaration of 'fp0 '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double fp0 = fpVals[0];
double area = 0.0;
//starts at high values and goes down
double xlast = 1.0;
double ylast = 1.0;
for (int i = 1; i < n; i++)
{
//UPGRADE_NOTE: Final was removed from the declaration of 'x '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double x = fpVals[i] / fp0;
//UPGRADE_NOTE: Final was removed from the declaration of 'y '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double y = tpVals[i] / tp0;
//UPGRADE_NOTE: Final was removed from the declaration of 'areaDelta '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double areaDelta = (y + ylast) * (xlast - x) / 2.0;
/*
System.err.println("[" + i + "]"
+ " x=" + x
+ " y'=" + y
+ " xl=" + xlast
+ " yl=" + ylast
+ " a'=" + areaDelta);
*/
area += areaDelta;
xlast = x;
ylast = y;
}
//make sure ends at 0,0
if (xlast > 0.0)
{
//UPGRADE_NOTE: Final was removed from the declaration of 'areaDelta '. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1003'"
double areaDelta = ylast * xlast / 2.0;
//System.err.println(" a'=" + areaDelta);
area += areaDelta;
}
//System.err.println(" area'=" + area);
return area;
}
/// <summary> Gets the index of the instance with the closest threshold value to the
/// desired target
///
/// </summary>
/// <param name="tcurve">a set of instances that have been generated by this class
/// </param>
/// <param name="threshold">the target threshold
/// </param>
/// <returns> the index of the instance that has threshold closest to
/// the target, or -1 if this could not be found (i.e. no data, or
/// bad threshold target)
/// </returns>
public static int getThresholdInstance(Instances tcurve, double threshold)
{
if (!RELATION_NAME.Equals(tcurve.relationName()) || (tcurve.numInstances() == 0) || (threshold < 0) || (threshold > 1.0))
{
return - 1;
}
if (tcurve.numInstances() == 1)
{
return 0;
}
double[] tvals = tcurve.attributeToDoubleArray(tcurve.numAttributes() - 1);
int[] sorted = Utils.sort(tvals);
return binarySearch(sorted, tvals, threshold);
}
/// <summary> Calculates the n point precision result, which is the precision averaged
/// over n evenly spaced (w.r.t recall) samples of the curve.
///
/// </summary>
/// <param name="tcurve">a previously extracted threshold curve Instances.
/// </param>
/// <param name="n">the number of points to average over.
/// </param>
/// <returns> the n-point precision.
/// </returns>
public static double getNPointPrecision(Instances tcurve, int n)
{
if (!RELATION_NAME.Equals(tcurve.relationName()) || (tcurve.numInstances() == 0))
{
return System.Double.NaN;
}
int recallInd = tcurve.attribute(RECALL_NAME).index();
int precisInd = tcurve.attribute(PRECISION_NAME).index();
double[] recallVals = tcurve.attributeToDoubleArray(recallInd);
int[] sorted = Utils.sort(recallVals);
double isize = 1.0 / (n - 1);
double psum = 0;
for (int i = 0; i < n; i++)
{
int pos = binarySearch(sorted, recallVals, i * isize);
double recall = recallVals[sorted[pos]];
double precis = tcurve.instance(sorted[pos]).value_Renamed(precisInd);
/*
System.err.println("Point " + (i + 1) + ": i=" + pos
+ " r=" + (i * isize)
+ " p'=" + precis
+ " r'=" + recall);
*/
// interpolate figures for non-endpoints
while ((pos != 0) && (pos < sorted.Length - 1))
{
pos++;
double recall2 = recallVals[sorted[pos]];
if (recall2 != recall)
{
double precis2 = tcurve.instance(sorted[pos]).value_Renamed(precisInd);
double slope = (precis2 - precis) / (recall2 - recall);
double offset = precis - recall * slope;
precis = isize * i * slope + offset;
/*
System.err.println("Point2 " + (i + 1) + ": i=" + pos
+ " r=" + (i * isize)
+ " p'=" + precis2
+ " r'=" + recall2
+ " p''=" + precis);
*/
break;
}
}
psum += precis;
}
return psum / n;
}
