void TConditionalProbabilityEstimator_ByRows::checkCondition(const TValue &condition) const
{ checkProperty(estimatorList);
if (!estimatorList->size())
raiseError("empty 'estimatorList'");
if (condition.isSpecial())
raiseError("undefined attribute value for condition");
if (condition.varType != TValue::INTVAR)
raiseError("value for condition is not discrete");
if (condition.intV >= estimatorList->size())
raiseError("value for condition out of range");
}
float TProbabilityEstimator_FromDistribution::operator()(const TValue &classVal) const
{ checkProperty(probabilities);
if (classVal.isSpecial())
raiseError("undefined attribute value");
/* This is a harmless shortcut to make things run faster in the most usual case */
if (classVal.varType == TValue::INTVAR) {
const TDiscDistribution *ddist = probabilities.AS(TDiscDistribution);
if (ddist)
return (*ddist)[classVal.intV];
// else, let probabilities->p do something or (more probably) report an error
}
return probabilities->p(classVal);
}
int validateLine(char *Line, int nWords) {
char *token;
int wordCount = 0;
while(wordCount < nWords) {
token = getToken(Line);
if(wordCount < 1) {
addKeyWordToken(token); //!This is a keyword
} else {
if(!checkProperty(token)){ //!This is a property
addValue(token); //! Not a property add a value
}
}
free(token);
token = NULL;
wordCount++;
}
return 0;
}
void TExampleForMissing::resetExample()
{
checkProperty(dataDescription);
DCs.clear();
DKs.clear();
float averageWeight=1;
TVarList::const_iterator vi(domain->attributes->begin()), vie(domain->attributes->end());
TExample::iterator ei(begin()), bei(ei);
vector<float>::const_iterator ai(dataDescription->averages.begin()), aei(dataDescription->averages.end());
for(; vi!=vie; ei++, vi++) {
if ((*ei).isSpecial()) {
if ((*vi)->varType==TValue::FLOATVAR)
*ei=TValue(*ai);
else if (dataDescription->missingWeight && (*ei).isDK()) {
DKs.push_back(ei-bei);
averageWeight/=float((*vi)->noOfValues());
}
else
DCs.push_back(ei-bei);
(*vi)->firstValue(*ei);
}
if (ai!=aei)
ai++;
}
if (dataDescription->missingWeight) {
float weight = dataDescription->originalWeight ? getMeta(dataDescription->originalWeight).floatV : 1;
if (dataDescription->domainDistributions) {
TDomainDistributions::const_iterator di(dataDescription->domainDistributions->begin());
ITERATE(vector<int>, ci, DKs) {
// DKs contain only discrete variables, so it is safe to cast
const TDiscDistribution &dist = CAST_TO_DISCDISTRIBUTION(*(di+*ci));
if (dist.abs)
weight *= dist.front() / dist.abs;
}
}
** LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
** DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
** THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
** (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
** OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE."
**
** $QT_END_LICENSE$
**
****************************************************************************/
//! [0]
QDesignerPropertyEditorInterface *propertyEditor = 0;
propertyEditor = formEditor->propertyEditor();
connect(propertyEditor, SIGNAL(propertyChanged(QString, QVariant)),
this, SLOT(checkProperty(QString, QVariant)));
//! [0]
//! [1]
void checkProperty(QString property, QVariant value) {
QDesignerPropertyEditorInterface *propertyEditor = 0;
propertyEditor = formEditor->propertyEditor();
QObject *object = propertyeditor->object();
MyCustomWidget *widget = qobject_cast<MyCustomWidget>(object);
if (widget && property == aProperty && value != expectedValue)
{
...
}
PClassifier TTreeSplitConstructor_Combined::operator()(
PStringList &descriptions, PDiscDistribution &subsetSizes, float &quality, int &spentAttribute,
PExampleGenerator gen, const int &weightID ,
PDomainContingency dcont, PDistribution apriorClass,
const vector<bool> &candidates,
PClassifier nodeClassifier
)
{ checkProperty(discreteSplitConstructor);
checkProperty(continuousSplitConstructor);
vector<bool> discrete, continuous;
bool cse = candidates.size()==0;
vector<bool>::const_iterator ci(candidates.begin()), ce(candidates.end());
TVarList::const_iterator vi(gen->domain->attributes->begin()), ve(gen->domain->attributes->end());
for(; (cse || (ci!=ce)) && (vi!=ve); vi++) {
if (cse || *(ci++))
if ((*vi)->varType == TValue::INTVAR) {
discrete.push_back(true);
continuous.push_back(false);
continue;
}
else if ((*vi)->varType == TValue::FLOATVAR) {
discrete.push_back(false);
continuous.push_back(true);
continue;
}
discrete.push_back(false);
continuous.push_back(false);
}
float discQuality;
PStringList discDescriptions;
PDiscDistribution discSizes;
int discSpent;
PClassifier discSplit = discreteSplitConstructor->call(discDescriptions, discSizes, discQuality, discSpent,
gen, weightID, dcont, apriorClass, discrete, nodeClassifier);
float contQuality;
PStringList contDescriptions;
PDiscDistribution contSizes;
int contSpent;
PClassifier contSplit = continuousSplitConstructor->call(contDescriptions, contSizes, contQuality, contSpent,
gen, weightID, dcont, apriorClass, continuous, nodeClassifier);
int N = gen ? gen->numberOfExamples() : -1;
if (N<0)
N = dcont->classes->cases;
if ( discSplit
&& ( !contSplit
|| (discQuality>contQuality)
|| (discQuality==contQuality) && (N%2>0))) {
quality = discQuality;
descriptions = discDescriptions;
subsetSizes = discSizes;
spentAttribute = discSpent;
return discSplit;
}
else if (contSplit) {
quality = contQuality;
descriptions = contDescriptions;
subsetSizes = contSizes;
spentAttribute = contSpent;
return contSplit;
}
else
return returnNothing(descriptions, subsetSizes, quality, spentAttribute);
}
PClassifier TTreeSplitConstructor_ExhaustiveBinary::operator()(
PStringList &descriptions, PDiscDistribution &subsetSizes, float &quality, int &spentAttribute,
PExampleGenerator gen, const int &weightID ,
PDomainContingency dcont, PDistribution apriorClass,
const vector<bool> &candidates,
PClassifier
)
{
checkProperty(measure);
measure->checkClassTypeExc(gen->domain->classVar->varType);
PIntList bestMapping;
int wins, bestAttr;
PVariable bvar;
if (measure->needs==TMeasureAttribute::Generator) {
bool cse = candidates.size()==0;
bool haveCandidates = false;
vector<bool> myCandidates;
myCandidates.reserve(gen->domain->attributes->size());
vector<bool>::const_iterator ci(candidates.begin()), ce(candidates.end());
TVarList::const_iterator vi, ve(gen->domain->attributes->end());
for(vi = gen->domain->attributes->begin(); vi != ve; vi++) {
bool co = (*vi)->varType == TValue::INTVAR && (!cse || (ci!=ce) && *ci);
myCandidates.push_back(co);
haveCandidates = haveCandidates || co;
}
if (!haveCandidates)
return returnNothing(descriptions, subsetSizes, quality, spentAttribute);
PDistribution thisSubsets;
float thisQuality;
wins = 0;
int thisAttr = 0;
int N = gen->numberOfExamples();
TSimpleRandomGenerator rgen(N);
ci = myCandidates.begin();
for(vi = gen->domain->attributes->begin(); vi != ve; ci++, vi++, thisAttr++) {
if (*ci) {
thisSubsets = NULL;
PIntList thisMapping =
/*throughCont ? measure->bestBinarization(thisSubsets, thisQuality, *dci, dcont->classes, apriorClass, minSubset)
: */measure->bestBinarization(thisSubsets, thisQuality, *vi, gen, apriorClass, weightID, minSubset);
if (thisMapping
&& ( (!wins || (thisQuality>quality)) && ((wins=1)==1)
|| (thisQuality==quality) && rgen.randbool(++wins))) {
bestAttr = thisAttr;
quality = thisQuality;
subsetSizes = thisSubsets;
bestMapping = thisMapping;
}
}
/*if (thoughCont)
dci++; */
}
if (!wins)
return returnNothing(descriptions, subsetSizes, quality, spentAttribute);
if (quality<worstAcceptable)
return returnNothing(descriptions, subsetSizes, spentAttribute);
if (subsetSizes && subsetSizes->variable)
bvar = subsetSizes->variable;
else {
TEnumVariable *evar = mlnew TEnumVariable("");
evar->addValue("0");
evar->addValue("1");
bvar = evar;
}
}
else {
bool cse = candidates.size()==0;
if (!cse && noCandidates(candidates))
return returnNothing(descriptions, subsetSizes, quality, spentAttribute);
if (!dcont || dcont->classIsOuter) {
dcont = PDomainContingency(mlnew TDomainContingency(gen, weightID));
// raiseWarningWho("TreeSplitConstructor_ExhaustiveBinary", "this class is not optimized for 'candidates' list and can be very slow");
}
int N = gen ? gen->numberOfExamples() : -1;
if (N<0)
N = dcont->classes->cases;
TSimpleRandomGenerator rgen(N);
PDistribution classDistribution = dcont->classes;
vector<bool>::const_iterator ci(candidates.begin()), ce(candidates.end());
TDiscDistribution *dis0, *dis1;
TContDistribution *con0, *con1;
int thisAttr = 0;
bestAttr = -1;
wins = 0;
quality = 0.0;
float leftExamples, rightExamples;
TDomainContingency::iterator dci(dcont->begin()), dce(dcont->end());
for(; (cse || (ci!=ce)) && (dci!=dce); dci++, thisAttr++) {
// We consider the attribute only if it is a candidate, discrete and has at least two values
if ((cse || *(ci++)) && ((*dci)->outerVariable->varType==TValue::INTVAR) && ((*dci)->discrete->size()>=2)) {
const TDistributionVector &distr = *(*dci)->discrete;
if (distr.size()>16)
raiseError("'%s' has more than 16 values, cannot exhaustively binarize", gen->domain->attributes->at(thisAttr)->get_name().c_str());
// If the attribute is binary, we check subsetSizes and assess the quality if they are OK
if (distr.size()==2) {
if ((distr.front()->abs<minSubset) || (distr.back()->abs<minSubset))
continue; // next attribute
else {
float thisMeas = measure->call(thisAttr, dcont, apriorClass);
if ( ((!wins || (thisMeas>quality)) && ((wins=1)==1))
|| ((thisMeas==quality) && rgen.randbool(++wins))) {
bestAttr = thisAttr;
quality = thisMeas;
leftExamples = distr.front()->abs;
rightExamples = distr.back()->abs;
bestMapping = mlnew TIntList(2, 0);
bestMapping->at(1) = 1;
}
continue;
}
}
vector<int> valueIndices;
int ind = 0;
for(TDistributionVector::const_iterator dvi(distr.begin()), dve(distr.end()); (dvi!=dve); dvi++, ind++)
if ((*dvi)->abs>0)
valueIndices.push_back(ind);
if (valueIndices.size()<2)
continue;
PContingency cont = prepareBinaryCheat(classDistribution, *dci, bvar, dis0, dis1, con0, con1);
// A real job: go through all splits
int binWins = 0;
float binQuality = -1.0;
float binLeftExamples = -1.0, binRightExamples = -1.0;
// Selection: each element correspons to a value of the original attribute and is 1, if the value goes right
// The first value always goes left (and has no corresponding bit in selection.
TBoolCount selection(valueIndices.size()-1), bestSelection(0);
// First for discrete classes
if (dis0) {
do {
*dis0 = CAST_TO_DISCDISTRIBUTION(distr[valueIndices[0]]);
*dis1 *= 0;
vector<int>::const_iterator ii(valueIndices.begin());
ii++;
for(TBoolCount::const_iterator bi(selection.begin()), be(selection.end()); bi!=be; bi++, ii++)
*(*bi ? dis1 : dis0) += distr[*ii];
cont->outerDistribution->setint(0, dis0->abs);
cont->outerDistribution->setint(1, dis1->abs);
if ((dis0->abs < minSubset) || (dis1->abs < minSubset))
continue; // cannot split like that, to few examples in one of the branches
float thisMeas = measure->operator()(cont, classDistribution, apriorClass);
if ( ((!binWins) || (thisMeas>binQuality)) && ((binWins=1) ==1)
|| (thisMeas==binQuality) && rgen.randbool(++binWins)) {
bestSelection = selection;
binQuality = thisMeas;
binLeftExamples = dis0->abs;
binRightExamples = dis1->abs;
}
} while (selection.next());
}
// And then exactly the same for continuous classes
else {
do {
*con0 = CAST_TO_CONTDISTRIBUTION(distr[0]);
*con1 = TContDistribution();
vector<int>::const_iterator ii(valueIndices.begin());
for(TBoolCount::const_iterator bi(selection.begin()), be(selection.end()); bi!=be; bi++, ii++)
*(*bi ? con1 : con0) += distr[*ii];
if ((con0->abs<minSubset) || (con1->abs<minSubset))
continue; // cannot split like that, to few examples in one of the branches
float thisMeas = measure->operator()(cont, classDistribution, apriorClass);
if ( ((!binWins) || (thisMeas>binQuality)) && ((binWins=1) ==1)
|| (thisMeas==binQuality) && rgen.randbool(++binWins)) {
bestSelection = selection;
binQuality = thisMeas;
binLeftExamples = con0->abs;
binRightExamples = con1->abs;
}
} while (selection.next());
}
if ( binWins
&& ( (!wins || (binQuality>quality)) && ((wins=1)==1)
|| (binQuality==quality) && rgen.randbool(++wins))) {
bestAttr = thisAttr;
quality = binQuality;
leftExamples = binLeftExamples;
rightExamples = binRightExamples;
bestMapping = mlnew TIntList(distr.size(), -1);
vector<int>::const_iterator ii = valueIndices.begin();
bestMapping->at(*(ii++)) = 0;
ITERATE(TBoolCount, bi, bestSelection)
bestMapping->at(*(ii++)) = *bi ? 1 : 0;
}
}
}
if (!wins)
return returnNothing(descriptions, subsetSizes, quality, spentAttribute);
subsetSizes = mlnew TDiscDistribution();
subsetSizes->addint(0, leftExamples);
subsetSizes->addint(1, rightExamples);
}
PVariable attribute = gen->domain->attributes->at(bestAttr);
if (attribute->noOfValues() == 2) {
spentAttribute = bestAttr;
descriptions = mlnew TStringList(attribute.AS(TEnumVariable)->values.getReference());
TClassifierFromVarFD *cfv = mlnew TClassifierFromVarFD(attribute, gen->domain, bestAttr, subsetSizes);
cfv->transformUnknowns = false;
return cfv;
}
string s0, s1;
int ns0 = 0, ns1 = 0;
TValue ev;
attribute->firstValue(ev);
PITERATE(TIntList, mi, bestMapping) {
string str;
attribute->val2str(ev, str);
if (*mi==1) {
s1 += string(ns1 ? ", " : "") + str;
ns1++;
}
else if (*mi==0) {
s0 += string(ns0 ? ", " : "") + str;
ns0++;
}
attribute->nextValue(ev);
}
PClassifier TTreeSplitConstructor_Attribute::operator()(
PStringList &descriptions, PDiscDistribution &subsetSizes, float &quality, int &spentAttribute,
PExampleGenerator gen, const int &weightID,
PDomainContingency dcont, PDistribution apriorClass,
const vector<bool> &candidates,
PClassifier nodeClassifier
)
{ checkProperty(measure);
measure->checkClassTypeExc(gen->domain->classVar->varType);
bool cse = candidates.size()==0;
vector<bool>::const_iterator ci(candidates.begin()), ce(candidates.end());
if (!cse) {
if (noCandidates(candidates))
return returnNothing(descriptions, subsetSizes, quality, spentAttribute);
ci = candidates.begin();
}
int N = gen ? gen->numberOfExamples() : -1;
if (N<0)
N = dcont->classes->cases;
TSimpleRandomGenerator rgen(N);
int thisAttr = 0, bestAttr = -1, wins = 0;
quality = 0.0;
if (measure->needs == TMeasureAttribute::Contingency_Class) {
vector<bool> myCandidates;
if (cse) {
myCandidates.reserve(gen->domain->attributes->size());
PITERATE(TVarList, vi, gen->domain->attributes)
myCandidates.push_back((*vi)->varType == TValue::INTVAR);
}
else {
myCandidates.reserve(candidates.size());
TVarList::const_iterator vi(gen->domain->attributes->begin());
for(; ci != ce; ci++, vi++)
myCandidates.push_back(*ci && ((*vi)->varType == TValue::INTVAR));
}
if (!dcont || dcont->classIsOuter)
dcont = PDomainContingency(mlnew TDomainContingency(gen, weightID, myCandidates));
ci = myCandidates.begin();
ce = myCandidates.end();
TDomainContingency::iterator dci(dcont->begin()), dce(dcont->end());
for(; (ci != ce) && (dci!=dce); dci++, ci++, thisAttr++)
if (*ci && checkDistribution((const TDiscDistribution &)((*dci)->outerDistribution.getReference()), minSubset)) {
float thisMeas = measure->call(thisAttr, dcont, apriorClass);
if ( ((!wins || (thisMeas>quality)) && ((wins=1)==1))
|| ((thisMeas==quality) && rgen.randbool(++wins))) {
quality = thisMeas;
subsetSizes = (*dci)->outerDistribution;
bestAttr = thisAttr;
}
}
}
else if (measure->needs == TMeasureAttribute::DomainContingency) {
if (!dcont || dcont->classIsOuter)
dcont = PDomainContingency(mlnew TDomainContingency(gen, weightID));
TDomainContingency::iterator dci(dcont->begin()), dce(dcont->end());
for(; (cse || (ci!=ce)) && (dci!=dce); dci++, thisAttr++)
if ( (cse || *(ci++))
&& ((*dci)->outerVariable->varType==TValue::INTVAR)
&& checkDistribution((const TDiscDistribution &)((*dci)->outerDistribution.getReference()), minSubset)) {
float thisMeas = measure->call(thisAttr, dcont, apriorClass);
if ( ((!wins || (thisMeas>quality)) && ((wins=1)==1))
|| ((thisMeas==quality) && rgen.randbool(++wins))) {
quality = thisMeas;
subsetSizes = (*dci)->outerDistribution;
bestAttr = thisAttr;
}
}
}
else {
TDomainDistributions ddist(gen, weightID);
TDomainDistributions::iterator ddi(ddist.begin()), dde(ddist.end()-1);
for(; (cse || (ci!=ce)) && (ddi!=dde); ddi++, thisAttr++)
if (cse || *(ci++)) {
TDiscDistribution *discdist = (*ddi).AS(TDiscDistribution);
if (discdist && checkDistribution(*discdist, minSubset)) {
float thisMeas = measure->call(thisAttr, gen, apriorClass, weightID);
if ( ((!wins || (thisMeas>quality)) && ((wins=1)==1))
|| ((thisMeas==quality) && rgen.randbool(++wins))) {
quality = thisMeas;
subsetSizes = PDiscDistribution(*ddi); // not discdist - this would be double wrapping!
bestAttr = thisAttr;
}
}
}
}
if (!wins)
return returnNothing(descriptions, subsetSizes, quality, spentAttribute);
if (quality<worstAcceptable)
return returnNothing(descriptions, subsetSizes, spentAttribute);
PVariable attribute = gen->domain->attributes->at(bestAttr);
TEnumVariable *evar = attribute.AS(TEnumVariable);
if (evar)
descriptions = mlnew TStringList(evar->values.getReference());
else
descriptions = mlnew TStringList(subsetSizes->size(), "");
spentAttribute = bestAttr;
TClassifierFromVarFD *cfv = mlnew TClassifierFromVarFD(attribute, gen->domain, bestAttr, subsetSizes);
cfv->transformUnknowns = false;
return cfv;
}
TestResult checkTestable(Testable &&testable, Args &&... args) {
return checkProperty(toProperty(std::forward<Testable>(testable)),
std::forward<Args>(args)...);
}
PDistribution TLogRegClassifier::classDistribution(const TExample &origexam)
{
checkProperty(domain);
TExample cexample(domain, origexam);
TExample *example2;
if (imputer)
example2 = imputer->call(cexample);
else {
if (dataDescription)
for(TExample::const_iterator ei(cexample.begin()), ee(cexample.end()-1); ei!=ee; ei++)
if ((*ei).isSpecial())
return TClassifier::classDistribution(cexample, dataDescription);
example2 = &cexample;
}
TExample *example = continuizedDomain ? mlnew TExample(continuizedDomain, *example2) : example2;
float prob1;
try {
// multiply example with beta
TAttributedFloatList::const_iterator b(beta->begin()), be(beta->end());
// get beta 0
prob1 = *b;
b++;
// multiply beta with example
TVarList::const_iterator vi(example->domain->attributes->begin());
TExample::const_iterator ei(example->begin()), ee(example->end());
for (; (b!=be) && (ei!=ee); ei++, b++, vi++) {
if ((*ei).isSpecial())
raiseError("unknown value in attribute '%s'", (*vi)->get_name().c_str());
prob1 += (*ei).floatV * (*b);
}
prob1 = exp(prob1)/(1+exp(prob1));
}
catch (...) {
if (imputer)
mldelete example2;
if (continuizedDomain)
mldelete example;
throw;
}
if (imputer)
mldelete example2;
if (continuizedDomain)
mldelete example;
if (classVar->varType == TValue::INTVAR) {
TDiscDistribution *dist = mlnew TDiscDistribution(classVar);
PDistribution res = dist;
dist->addint(0, 1-prob1);
dist->addint(1, prob1);
return res;
}
else {
TContDistribution *dist = mlnew TContDistribution(classVar);
PDistribution res = dist;
dist->addfloat(prob1, 1.0);
return res;
}
}
PDistanceMap TDistanceMapConstructor::operator ()(const float &unadjustedSqueeze, float &abslow, float &abshigh)
{
checkProperty(distanceMatrix);
const TSymMatrix &distMat = distanceMatrix.getReference();
abshigh = -1e30f;
abslow = 1e30f;
if (order) {
if (order->size() != distMat.dim)
raiseError("size of 'order' does not match the size of the distance matrix");
if (unadjustedSqueeze < 1.0 - 1e-5) {
int nLines = int(floor(0.5 + order->size() * unadjustedSqueeze));
if (!nLines)
nLines++;
PIntList psqi = new TIntList();
TOrangeVector<int, false> &squeezedIndices = psqi.getReference();
computeSqueezedIndices(distMat.dim, nLines, squeezedIndices);
nLines = squeezedIndices.size() - 1;
PDistanceMap dm = mlnew TDistanceMap(nLines);
dm->elementIndices = psqi;
TIntList::const_iterator row_squeezei(squeezedIndices.begin()), row_squeezen(row_squeezei+1), squeezee(squeezedIndices.end());
for(int row = 0; row_squeezen != squeezee; row_squeezei++, row_squeezen++, row++) {
// this needs to be float (to avoid int division)
float row_elements = *row_squeezen - *row_squeezei;
// to diagonal, exclusive
TIntList::const_iterator col_squeezei(squeezedIndices.begin()), col_squeezen(col_squeezei+1);
for(int column = 0; col_squeezei != row_squeezei; col_squeezei++, col_squeezen++, column++) {
float incell = 0.0;
TIntList::const_iterator row_orderi(order->begin()+*row_squeezei), row_ordere(order->begin()+*row_squeezen);
for(; row_orderi != row_ordere; row_orderi++) {
TIntList::const_iterator col_orderi(order->begin()+*col_squeezei), col_ordere(order->begin()+*col_squeezen);
for(; col_orderi != col_ordere; col_orderi++)
incell += distMat.getitem(*row_orderi, *col_orderi);
}
incell /= row_elements * (*col_squeezen - *col_squeezei);
dm->cells[row*nLines+column] = dm->cells[column*nLines+row] = incell;
UPDATE_LOW_HIGH;
}
// diagonal
{
float incell = 0.0;
TIntList::const_iterator row_orderi(order->begin()+*row_squeezei), row_ordere(order->begin()+*row_squeezen);
for(; row_orderi != row_ordere; row_orderi++) {
TIntList::const_iterator col_orderi(order->begin()+*row_squeezei);
for(; col_orderi != row_orderi; col_orderi++)
incell += distMat.getitem(*row_orderi, *col_orderi);
incell += distMat.getitem(*row_orderi, *row_orderi);
}
incell /= row_elements * (row_elements+1) / 2.0;
dm->cells[row*(nLines+1)] = incell;
UPDATE_LOW_HIGH;
}
}
return dm;
}
else { // order && no squeeze
const int &dim = distMat.dim;
PDistanceMap dm = mlnew TDistanceMap(dim);
TIntList::const_iterator row_orderi(order->begin()), row_ordere(order->end());
for(int row = 0; row_orderi != row_ordere; row_orderi++, row++) {
TIntList::const_iterator col_orderi(order->begin());
for(int column = 0; col_orderi != row_orderi; col_orderi++, column++) {
const float &incell = distMat.getref(*row_orderi, *col_orderi);
dm->cells[row*dim+column] = dm->cells[column*dim+row] = incell;
UPDATE_LOW_HIGH;
}
const float &incell = distMat.getref(*row_orderi, *row_orderi);
dm->cells[row*(dim+1)] = incell;
UPDATE_LOW_HIGH;
}
return dm;
}
}
else { // no order
if (unadjustedSqueeze < 1 - 1e-5) {
int nLines = int(floor(0.5 + distMat.dim * unadjustedSqueeze));
if (!nLines)
nLines++;
PIntList psqi = new TIntList();
TOrangeVector<int, false> &squeezedIndices = psqi.getReference();
computeSqueezedIndices(distMat.dim, nLines, squeezedIndices);
nLines = squeezedIndices.size() - 1;
PDistanceMap dm = mlnew TDistanceMap(nLines);
dm->elementIndices = psqi;
TIntList::const_iterator row_squeezei(squeezedIndices.begin()), row_squeezen(row_squeezei+1), squeezee(squeezedIndices.end());
for(int row = 0; row_squeezen != squeezee; row_squeezei++, row_squeezen++, row++) {
// this needs to be float (to avoid int division)
float row_elements = *row_squeezen - *row_squeezei;
// to diagonal, exclusive
TIntList::const_iterator col_squeezei(squeezedIndices.begin()), col_squeezen(col_squeezei+1);
for(int column = 0; col_squeezei != row_squeezei; col_squeezei++, col_squeezen++, column++) {
int col_elements = *col_squeezen - *col_squeezei;
float incell = 0.0;
int origrow = *row_squeezei, origrowe = *row_squeezen;
for(; origrow != origrowe; origrow++) {
const float *origval = &distMat.getref(origrow, *col_squeezei);
for(int ce = col_elements; ce--; incell += *(origval++));
}
incell /= row_elements * col_elements;
dm->cells[row*nLines+column] = dm->cells[column*nLines+row] = incell;
UPDATE_LOW_HIGH;
}
// diagonal
{
float incell = 0.0;
int origrow = *row_squeezei, origrowe = *row_squeezen;
for(; origrow != origrowe; origrow++) {
const float *origval = &distMat.getref(origrow, *col_squeezei);
for(int ce = origrow - *row_squeezei+1; ce--; incell += *(origval++));
}
incell /= row_elements * (row_elements+1) / 2.0;
dm->cells[row*(nLines+1)] = incell;
UPDATE_LOW_HIGH;
}
}
return dm;
}
else {// no order && no squeeze
const int &dim = distMat.dim;
PDistanceMap dm = mlnew TDistanceMap(dim);
dm->elementIndices = new TIntList();
TOrangeVector<int, false> &squeezedIndices = dm->elementIndices.getReference();
for(int row = 0; row < dim; row++) {
squeezedIndices.push_back(row);
for(int column = 0; column < row; column++) {
const float &incell = distMat.getref(row, column);
dm->cells[row*dim+column] = dm->cells[column*dim+row] = incell;
UPDATE_LOW_HIGH;
}
const float &incell = distMat.getref(row, row);
dm->cells[row*(dim+1)] = incell;
UPDATE_LOW_HIGH;
}
squeezedIndices.push_back(dim);
return dm;
}
}
}
