C++ TreeType::NumDescendants方法代码示例

  DualTreeKMeansStatistic(TreeType& node) :
      neighbor::NeighborSearchStat<neighbor::NearestNeighborSort>(),
      upperBound(DBL_MAX),
      lowerBound(DBL_MAX),
      owner(size_t(-1)),
      pruned(size_t(-1)),
      staticPruned(false),
      staticUpperBoundMovement(0.0),
      staticLowerBoundMovement(0.0),
      trueParent(node.Parent())
  {
    // Empirically calculate the centroid.
    centroid.zeros(node.Dataset().n_rows);
    for (size_t i = 0; i < node.NumPoints(); ++i)
    {
      // Correct handling of cover tree: don't double-count the point which
      // appears in the children.
      if (tree::TreeTraits<TreeType>::HasSelfChildren && i == 0 &&
          node.NumChildren() > 0)
        continue;
      centroid += node.Dataset().col(node.Point(i));
    }

    for (size_t i = 0; i < node.NumChildren(); ++i)
      centroid += node.Child(i).NumDescendants() *
          node.Child(i).Stat().Centroid();

    centroid /= node.NumDescendants();

    // Set the true children correctly.
    trueChildren.resize(node.NumChildren());
    for (size_t i = 0; i < node.NumChildren(); ++i)
      trueChildren[i] = &node.Child(i);
  }

inline double KDERules<MetricType, KernelType, TreeType>::
Score(const size_t queryIndex, TreeType& referenceNode)
{
  double score, maxKernel, minKernel, bound;
  const arma::vec& queryPoint = querySet.unsafe_col(queryIndex);
  const double minDistance = referenceNode.MinDistance(queryPoint);
  bool newCalculations = true;

  if (tree::TreeTraits<TreeType>::FirstPointIsCentroid &&
      lastQueryIndex == queryIndex &&
      traversalInfo.LastReferenceNode() != NULL &&
      traversalInfo.LastReferenceNode()->Point(0) == referenceNode.Point(0))
  {
    // Don't duplicate calculations.
    newCalculations = false;
    lastQueryIndex = queryIndex;
    lastReferenceIndex = referenceNode.Point(0);
  }
  else
  {
    // Calculations are new.
    maxKernel = kernel.Evaluate(minDistance);
    minKernel = kernel.Evaluate(referenceNode.MaxDistance(queryPoint));
    bound = maxKernel - minKernel;
  }

  if (newCalculations &&
      bound <= (absError + relError * minKernel) / referenceSet.n_cols)
  {
    // Estimate values.
    double kernelValue;

    // Calculate kernel value based on reference node centroid.
    if (tree::TreeTraits<TreeType>::FirstPointIsCentroid)
    {
      kernelValue = EvaluateKernel(queryIndex, referenceNode.Point(0));
    }
    else
    {
      kde::KDEStat& referenceStat = referenceNode.Stat();
      kernelValue = EvaluateKernel(queryPoint, referenceStat.Centroid());
    }

    densities(queryIndex) += referenceNode.NumDescendants() * kernelValue;

    // Don't explore this tree branch.
    score = DBL_MAX;
  }
  else
  {
    score = minDistance;
  }

  ++scores;
  traversalInfo.LastReferenceNode() = &referenceNode;
  traversalInfo.LastScore() = score;
  return score;
}

    PellegMooreKMeansStatistic(TreeType& node)
    {
        centroid.zeros(node.Dataset().n_rows);

        // Hope it's a depth-first build procedure.  Also, this won't work right for
        // trees that have self-children or stuff like that.
        for (size_t i = 0; i < node.NumChildren(); ++i)
        {
            centroid += node.Child(i).NumDescendants() *
                        node.Child(i).Stat().Centroid();
        }

        for (size_t i = 0; i < node.NumPoints(); ++i)
        {
            centroid += node.Dataset().col(node.Point(i));
        }

        if (node.NumDescendants() > 0)
            centroid /= node.NumDescendants();
        else
            centroid.fill(DBL_MAX); // Invalid centroid.  What else can we do?
    }

void RangeSearchRules<MetricType, TreeType>::AddResult(const size_t queryIndex,
                                                       TreeType& referenceNode)
{
  // Some types of trees calculate the base case evaluation before Score() is
  // called, so if the base case has already been calculated, then we must avoid
  // adding that point to the results again.
  size_t baseCaseMod = 0;
  if (tree::TreeTraits<TreeType>::FirstPointIsCentroid &&
      (queryIndex == lastQueryIndex) &&
      (referenceNode.Point(0) == lastReferenceIndex))
  {
    baseCaseMod = 1;
  }

  // Resize distances and neighbors vectors appropriately.  We have to use
  // reserve() and not resize(), because we don't know if we will encounter the
  // case where the datasets and points are the same (and we skip in that case).
  const size_t oldSize = neighbors[queryIndex].size();
  neighbors[queryIndex].reserve(oldSize + referenceNode.NumDescendants() -
      baseCaseMod);
  distances[queryIndex].reserve(oldSize + referenceNode.NumDescendants() -
      baseCaseMod);

  for (size_t i = baseCaseMod; i < referenceNode.NumDescendants(); ++i)
  {
    if ((&referenceSet == &querySet) &&
        (queryIndex == referenceNode.Descendant(i)))
      continue;

    const double distance = metric.Evaluate(querySet.unsafe_col(queryIndex),
        referenceNode.Dataset().unsafe_col(referenceNode.Descendant(i)));

    neighbors[queryIndex].push_back(referenceNode.Descendant(i));
    distances[queryIndex].push_back(distance);
  }
}

  DualTreeKMeansStatistic(TreeType& node) :
      closestQueryNode(NULL),
      minQueryNodeDistance(DBL_MAX),
      maxQueryNodeDistance(DBL_MAX),
      clustersPruned(0),
      iteration(size_t() - 1)
  {
    // Empirically calculate the centroid.
    centroid.zeros(node.Dataset().n_rows);
    for (size_t i = 0; i < node.NumPoints(); ++i)
      centroid += node.Dataset().col(node.Point(i));

    for (size_t i = 0; i < node.NumChildren(); ++i)
      centroid += node.Child(i).NumDescendants() *
          node.Child(i).Stat().Centroid();

    centroid /= node.NumDescendants();
  }

void CheckBound(const TreeType& tree)
{
  typedef typename TreeType::ElemType ElemType;
  for (size_t i = 0; i < tree.NumDescendants(); i++)
  {
    arma::Col<ElemType> point = tree.Dataset().col(tree.Descendant(i));

    // Check that the point is contained in the bound.
    BOOST_REQUIRE_EQUAL(true, tree.Bound().Contains(point));

    const arma::Mat<ElemType>& loBound = tree.Bound().LoBound();
    const arma::Mat<ElemType>& hiBound = tree.Bound().HiBound();

    // Ensure that there is a hyperrectangle that contains the point.
    bool success = false;
    for (size_t j = 0; j < tree.Bound().NumBounds(); j++)
    {
      success = true;
      for (size_t k = 0; k < loBound.n_rows; k++)
      {
        if (point[k] < loBound(k, j) - 1e-14 * std::fabs(loBound(k, j)) ||
            point[k] > hiBound(k, j) + 1e-14 * std::fabs(hiBound(k, j)))
        {
          success = false;
          break;
        }
      }
      if (success)
        break;
    }

    BOOST_REQUIRE_EQUAL(success, true);
  }

  if (!tree.IsLeaf())
  {
    CheckBound(*tree.Left());
    CheckBound(*tree.Right());
  }
}

double PellegMooreKMeansRules<MetricType, TreeType>::Score(
    const size_t /* queryIndex */,
    TreeType& referenceNode)
{
  // Obtain the parent's blacklist.  If this is the root node, we'll start with
  // an empty blacklist.  This means that after each iteration, we don't need to
  // reset any statistics.
  if (referenceNode.Parent() == NULL ||
      referenceNode.Parent()->Stat().Blacklist().n_elem == 0)
    referenceNode.Stat().Blacklist().zeros(centroids.n_cols);
  else
    referenceNode.Stat().Blacklist() =
        referenceNode.Parent()->Stat().Blacklist();

  // The query index is a fake index that we won't use, and the reference node
  // holds all of the points in the dataset.  Our goal is to determine whether
  // or not this node is dominated by a single cluster.
  const size_t whitelisted = centroids.n_cols -
      arma::accu(referenceNode.Stat().Blacklist());

  distanceCalculations += whitelisted;

  // Which cluster has minimum distance to the node?
  size_t closestCluster = centroids.n_cols;
  double minMinDistance = DBL_MAX;
  for (size_t i = 0; i < centroids.n_cols; ++i)
  {
    if (referenceNode.Stat().Blacklist()[i] == 0)
    {
      const double minDistance = referenceNode.MinDistance(centroids.col(i));
      if (minDistance < minMinDistance)
      {
        minMinDistance = minDistance;
        closestCluster = i;
      }
    }
  }

  // Now, for every other whitelisted cluster, determine if the closest cluster
  // owns the point.  This calculation is specific to hyperrectangle trees (but,
  // this implementation is specific to kd-trees, so that's okay).  For
  // circular-bound trees, the condition should be simpler and can probably be
  // expressed as a comparison between minimum and maximum distances.
  size_t newBlacklisted = 0;
  for (size_t c = 0; c < centroids.n_cols; ++c)
  {
    if (referenceNode.Stat().Blacklist()[c] == 1 || c == closestCluster)
      continue;

    // This algorithm comes from the proof of Lemma 4 in the extended version
    // of the Pelleg-Moore paper (the CMU tech report, that is).  It has been
    // adapted for speed.
    arma::vec cornerPoint(centroids.n_rows);
    for (size_t d = 0; d < referenceNode.Bound().Dim(); ++d)
    {
      if (centroids(d, c) > centroids(d, closestCluster))
        cornerPoint(d) = referenceNode.Bound()[d].Hi();
      else
        cornerPoint(d) = referenceNode.Bound()[d].Lo();
    }

    const double closestDist = metric.Evaluate(cornerPoint,
        centroids.col(closestCluster));
    const double otherDist = metric.Evaluate(cornerPoint, centroids.col(c));

    distanceCalculations += 3; // One for cornerPoint, then two distances.

    if (closestDist < otherDist)
    {
      // The closest cluster dominates the node with respect to the cluster c.
      // So we can blacklist c.
      referenceNode.Stat().Blacklist()[c] = 1;
      ++newBlacklisted;
    }
  }

  if (whitelisted - newBlacklisted == 1)
  {
    // This node is dominated by the closest cluster.
    counts[closestCluster] += referenceNode.NumDescendants();
    newCentroids.col(closestCluster) += referenceNode.NumDescendants() *
        referenceNode.Stat().Centroid();

    return DBL_MAX;
  }

  // Perform the base case here.
  for (size_t i = 0; i < referenceNode.NumPoints(); ++i)
  {
    size_t bestCluster = centroids.n_cols;
    double bestDistance = DBL_MAX;
    for (size_t c = 0; c < centroids.n_cols; ++c)
    {
      if (referenceNode.Stat().Blacklist()[c] == 1)
        continue;

      ++distanceCalculations;

      // The reference index is the index of the data point.
      const double distance = metric.Evaluate(centroids.col(c),
//.........这里部分代码省略.........

void CheckTrees(TreeType& tree,
                TreeType& xmlTree,
                TreeType& textTree,
                TreeType& binaryTree)
{
  const typename TreeType::Mat* dataset = &tree.Dataset();

  // Make sure that the data matrices are the same.
  if (tree.Parent() == NULL)
  {
    CheckMatrices(*dataset,
                  xmlTree.Dataset(),
                  textTree.Dataset(),
                  binaryTree.Dataset());

    // Also ensure that the other parents are null too.
    BOOST_REQUIRE_EQUAL(xmlTree.Parent(), (TreeType*) NULL);
    BOOST_REQUIRE_EQUAL(textTree.Parent(), (TreeType*) NULL);
    BOOST_REQUIRE_EQUAL(binaryTree.Parent(), (TreeType*) NULL);
  }

  // Make sure the number of children is the same.
  BOOST_REQUIRE_EQUAL(tree.NumChildren(), xmlTree.NumChildren());
  BOOST_REQUIRE_EQUAL(tree.NumChildren(), textTree.NumChildren());
  BOOST_REQUIRE_EQUAL(tree.NumChildren(), binaryTree.NumChildren());

  // Make sure the number of descendants is the same.
  BOOST_REQUIRE_EQUAL(tree.NumDescendants(), xmlTree.NumDescendants());
  BOOST_REQUIRE_EQUAL(tree.NumDescendants(), textTree.NumDescendants());
  BOOST_REQUIRE_EQUAL(tree.NumDescendants(), binaryTree.NumDescendants());

  // Make sure the number of points is the same.
  BOOST_REQUIRE_EQUAL(tree.NumPoints(), xmlTree.NumPoints());
  BOOST_REQUIRE_EQUAL(tree.NumPoints(), textTree.NumPoints());
  BOOST_REQUIRE_EQUAL(tree.NumPoints(), binaryTree.NumPoints());

  // Check that each point is the same.
  for (size_t i = 0; i < tree.NumPoints(); ++i)
  {
    BOOST_REQUIRE_EQUAL(tree.Point(i), xmlTree.Point(i));
    BOOST_REQUIRE_EQUAL(tree.Point(i), textTree.Point(i));
    BOOST_REQUIRE_EQUAL(tree.Point(i), binaryTree.Point(i));
  }

  // Check that the parent distance is the same.
  BOOST_REQUIRE_CLOSE(tree.ParentDistance(), xmlTree.ParentDistance(), 1e-8);
  BOOST_REQUIRE_CLOSE(tree.ParentDistance(), textTree.ParentDistance(), 1e-8);
  BOOST_REQUIRE_CLOSE(tree.ParentDistance(), binaryTree.ParentDistance(), 1e-8);

  // Check that the furthest descendant distance is the same.
  BOOST_REQUIRE_CLOSE(tree.FurthestDescendantDistance(),
      xmlTree.FurthestDescendantDistance(), 1e-8);
  BOOST_REQUIRE_CLOSE(tree.FurthestDescendantDistance(),
      textTree.FurthestDescendantDistance(), 1e-8);
  BOOST_REQUIRE_CLOSE(tree.FurthestDescendantDistance(),
      binaryTree.FurthestDescendantDistance(), 1e-8);

  // Check that the minimum bound distance is the same.
  BOOST_REQUIRE_CLOSE(tree.MinimumBoundDistance(),
      xmlTree.MinimumBoundDistance(), 1e-8);
  BOOST_REQUIRE_CLOSE(tree.MinimumBoundDistance(),
      textTree.MinimumBoundDistance(), 1e-8);
  BOOST_REQUIRE_CLOSE(tree.MinimumBoundDistance(),
      binaryTree.MinimumBoundDistance(), 1e-8);

  // Recurse into the children.
  for (size_t i = 0; i < tree.NumChildren(); ++i)
  {
    // Check that the child dataset is the same.
    BOOST_REQUIRE_EQUAL(&xmlTree.Dataset(), &xmlTree.Child(i).Dataset());
    BOOST_REQUIRE_EQUAL(&textTree.Dataset(), &textTree.Child(i).Dataset());
    BOOST_REQUIRE_EQUAL(&binaryTree.Dataset(), &binaryTree.Child(i).Dataset());

    // Make sure the parent link is right.
    BOOST_REQUIRE_EQUAL(xmlTree.Child(i).Parent(), &xmlTree);
    BOOST_REQUIRE_EQUAL(textTree.Child(i).Parent(), &textTree);
    BOOST_REQUIRE_EQUAL(binaryTree.Child(i).Parent(), &binaryTree);

    CheckTrees(tree.Child(i), xmlTree.Child(i), textTree.Child(i),
        binaryTree.Child(i));
  }
}

void CheckDistance(TreeType& tree, TreeType* node = NULL)
{
  typedef typename TreeType::ElemType ElemType;
  if (node == NULL)
  {
    node = &tree;

    while (node->Parent() != NULL)
      node = node->Parent();

    CheckDistance<TreeType, MetricType>(tree, node);

    for (size_t j = 0; j < tree.Dataset().n_cols; j++)
    {
      const arma::Col<ElemType>& point = tree.  Dataset().col(j);
      ElemType maxDist = 0;
      ElemType minDist = std::numeric_limits<ElemType>::max();
      for (size_t i = 0; i < tree.NumDescendants(); i++)
      {
        ElemType dist = MetricType::Evaluate(
            tree.Dataset().col(tree.Descendant(i)),
            tree.Dataset().col(j));

        if (dist > maxDist)
          maxDist = dist;
        if (dist < minDist)
          minDist = dist;
      }

      BOOST_REQUIRE_LE(tree.Bound().MinDistance(point), minDist *
          (1.0 + 10 * std::numeric_limits<ElemType>::epsilon()));
      BOOST_REQUIRE_LE(maxDist, tree.Bound().MaxDistance(point) *
          (1.0 + 10 * std::numeric_limits<ElemType>::epsilon()));

      math::RangeType<ElemType> r = tree.Bound().RangeDistance(point);

      BOOST_REQUIRE_LE(r.Lo(), minDist *
          (1.0 + 10 * std::numeric_limits<ElemType>::epsilon()));
      BOOST_REQUIRE_LE(maxDist, r.Hi() *
          (1.0 + 10 * std::numeric_limits<ElemType>::epsilon()));
    }
      
    if (!tree.IsLeaf())
    {
      CheckDistance<TreeType, MetricType>(*tree.Left());
      CheckDistance<TreeType, MetricType>(*tree.Right());
    }
  }
  else
  {
    if (&tree != node)
    {
      ElemType maxDist = 0;
      ElemType minDist = std::numeric_limits<ElemType>::max();
      for (size_t i = 0; i < tree.NumDescendants(); i++)
        for (size_t j = 0; j < node->NumDescendants(); j++)
        {
          ElemType dist = MetricType::Evaluate(
              tree.Dataset().col(tree.Descendant(i)),
              node->Dataset().col(node->Descendant(j)));

          if (dist > maxDist)
            maxDist = dist;
          if (dist < minDist)
            minDist = dist;
        }

      BOOST_REQUIRE_LE(tree.Bound().MinDistance(node->Bound()), minDist *
          (1.0 + 10 * std::numeric_limits<ElemType>::epsilon()));
      BOOST_REQUIRE_LE(maxDist, tree.Bound().MaxDistance(node->Bound()) *
          (1.0 + 10 * std::numeric_limits<ElemType>::epsilon()));

      math::RangeType<ElemType> r = tree.Bound().RangeDistance(node->Bound());

      BOOST_REQUIRE_LE(r.Lo(), minDist *
          (1.0 + 10 * std::numeric_limits<ElemType>::epsilon()));
      BOOST_REQUIRE_LE(maxDist, r.Hi() *
          (1.0 + 10 * std::numeric_limits<ElemType>::epsilon()));
    }
    if (!node->IsLeaf())
    {
      CheckDistance<TreeType, MetricType>(tree, node->Left());
      CheckDistance<TreeType, MetricType>(tree, node->Right());
    }
  }
}

double RangeSearchRules<MetricType, TreeType>::Score(TreeType& queryNode,
                                                     TreeType& referenceNode)
{
  math::Range distances;
  if (tree::TreeTraits<TreeType>::FirstPointIsCentroid)
  {
    // It is possible that the base case has already been calculated.
    double baseCase = 0.0;
    bool alreadyDone = false;
    if (tree::TreeTraits<TreeType>::HasSelfChildren)
    {
      TreeType* lastQuery = (TreeType*) referenceNode.Stat().LastDistanceNode();
      TreeType* lastRef = (TreeType*) queryNode.Stat().LastDistanceNode();

      // Did the query node's last combination do the base case?
      if ((lastRef != NULL) && (referenceNode.Point(0) == lastRef->Point(0)))
      {
        baseCase = queryNode.Stat().LastDistance();
        alreadyDone = true;
      }

      // Did the reference node's last combination do the base case?
      if ((lastQuery != NULL) && (queryNode.Point(0) == lastQuery->Point(0)))
      {
        baseCase = referenceNode.Stat().LastDistance();
        alreadyDone = true;
      }

      // If the query node is a self-child, did the query parent's last
      // combination do the base case?
      if ((queryNode.Parent() != NULL) &&
          (queryNode.Point(0) == queryNode.Parent()->Point(0)))
      {
        TreeType* lastParentRef = (TreeType*)
            queryNode.Parent()->Stat().LastDistanceNode();
        if ((lastParentRef != NULL) &&
            (referenceNode.Point(0) == lastParentRef->Point(0)))
        {
          baseCase = queryNode.Parent()->Stat().LastDistance();
          alreadyDone = true;
        }
      }

      // If the reference node is a self-child, did the reference parent's last
      // combination do the base case?
      if ((referenceNode.Parent() != NULL) &&
          (referenceNode.Point(0) == referenceNode.Parent()->Point(0)))
      {
        TreeType* lastQueryRef = (TreeType*)
            referenceNode.Parent()->Stat().LastDistanceNode();
        if ((lastQueryRef != NULL) &&
            (queryNode.Point(0) == lastQueryRef->Point(0)))
        {
          baseCase = referenceNode.Parent()->Stat().LastDistance();
          alreadyDone = true;
        }
      }
    }

    if (!alreadyDone)
    {
      // We must calculate the base case.
      baseCase = BaseCase(queryNode.Point(0), referenceNode.Point(0));
    }
    else
    {
      // Make sure that if BaseCase() is called, we don't duplicate results.
      lastQueryIndex = queryNode.Point(0);
      lastReferenceIndex = referenceNode.Point(0);
    }

    distances.Lo() = baseCase - queryNode.FurthestDescendantDistance()
        - referenceNode.FurthestDescendantDistance();
    distances.Hi() = baseCase + queryNode.FurthestDescendantDistance()
        + referenceNode.FurthestDescendantDistance();

    // Update the last distances performed for the query and reference node.
    queryNode.Stat().LastDistanceNode() = (void*) &referenceNode;
    queryNode.Stat().LastDistance() = baseCase;
    referenceNode.Stat().LastDistanceNode() = (void*) &queryNode;
    referenceNode.Stat().LastDistance() = baseCase;
  }
  else
  {
    // Just perform the calculation.
    distances = referenceNode.RangeDistance(&queryNode);
  }

  // If the ranges do not overlap, prune this node.
  if (!distances.Contains(range))
    return DBL_MAX;

  // In this case, all of the points in the reference node will be part of all
  // the results for each point in the query node.
  if ((distances.Lo() >= range.Lo()) && (distances.Hi() <= range.Hi()))
  {
    for (size_t i = 0; i < queryNode.NumDescendants(); ++i)
      AddResult(queryNode.Descendant(i), referenceNode);
    return DBL_MAX; // We don't need to go any deeper.
  }
//.........这里部分代码省略.........