tdidt_split.cpp

orange源码 数据挖掘技术

  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()>10)
          raiseError("'%s' has more than 10 values, cannot exhaustively binarize", gen->domain->attributes->at(thisAttr)->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());
            for(TBoolCount::const_iterator bi(selection.begin()), be(selection.end()); bi!=be; bi++, ii++)
               *(*bi ? dis1 : dis0) += distr[*ii];

            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, selection)
            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());
    return mlnew TClassifierFromVarFD(attribute, gen->domain, bestAttr, subsetSizes);
  }

  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);
  }

  descriptions = mlnew TStringList();
  descriptions->push_back(ns0>1 ? "in ["+s0+"]" : s0);
  descriptions->push_back(ns1>1 ? "in ["+s1+"]" : s1);

  bvar->name = gen->domain->attributes->at(bestAttr)->name;
  spentAttribute = (ns0==1) && (ns1==1) ? bestAttr : -1;
  return mlnew TClassifierFromVarFD(bvar, gen->domain, bestAttr, subsetSizes, mlnew TMapIntValue(bestMapping));
}



TTreeSplitConstructor_Threshold::TTreeSplitConstructor_Threshold(PMeasureAttribute meas, const float &worst, const float &aml)
: TTreeSplitConstructor_Measure(meas, worst, aml)
{}


PClassifier TTreeSplitConstructor_Threshold::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);

  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::FLOATVAR && (!cse || (ci!=ce) && *ci);
    myCandidates.push_back(co);
    haveCandidates = haveCandidates || co;
  }
  if (!haveCandidates)
    return returnNothing(descriptions, subsetSizes, quality, spentAttribute);

  int N = gen ? gen->numberOfExamples() : -1;
  if (N < 0)
    N = dcont->classes->cases;

  TSimpleRandomGenerator rgen(N);


  PDistribution thisSubsets;
  float thisQuality, bestThreshold;
  ci = myCandidates.begin();
  int wins = 0, thisAttr = 0, bestAttr;

  TDomainContingency::iterator dci, dce;
  bool throughCont = (dcont && !dcont->classIsOuter && (measure->needs <= measure->DomainContingency));
  if (throughCont) {
    dci = dcont->begin();
    dce = dcont->end();
  }

  for(vi = gen->domain->attributes->begin(); vi != ve; ci++, vi++, thisAttr++) {
    if (*ci) {
      thisSubsets = NULL;
      const float thisThreshold =
         throughCont ? measure->bestThreshold(thisSubsets, thisQuality, *dci, dcont->classes, apriorClass, minSubset)