view release on metacpan or  search on metacpan

xgboost/src/common/quantile.h  view on Meta::CPAN

        wsum += w; i = j;
      }
    }
  };
  /*! \brief data field */
  Entry *data;
  /*! \brief number of elements in the summary */
  size_t size;
  // constructor
  WQSummary(Entry *data, size_t size)
      : data(data), size(size) {}
  /*!
   * \return the maximum error of the Summary
   */
  inline RType MaxError() const {
    RType res = data[0].rmax - data[0].rmin - data[0].wmin;
    for (size_t i = 1; i < size; ++i) {
      res = std::max(data[i].rmax_prev() - data[i - 1].rmin_next(), res);
      res = std::max(data[i].rmax - data[i].rmin - data[i].wmin, res);
    }
    return res;
  }
  /*!
   * \brief query qvalue, start from istart
   * \param qvalue the value we query for
   * \param istart starting position
   */
  inline Entry Query(DType qvalue, size_t &istart) const { // NOLINT(*)
    while (istart < size && qvalue > data[istart].value) {
      ++istart;
    }
    if (istart == size) {
      RType rmax = data[size - 1].rmax;
      return Entry(rmax, rmax, 0.0f, qvalue);
    }
    if (qvalue == data[istart].value) {
      return data[istart];
    } else {
      if (istart == 0) {
        return Entry(0.0f, 0.0f, 0.0f, qvalue);
      } else {
        return Entry(data[istart - 1].rmin_next(),
                     data[istart].rmax_prev(),
                     0.0f, qvalue);
      }
    }
  }
  /*! \return maximum rank in the summary */
  inline RType MaxRank() const {
    return data[size - 1].rmax;
  }
  /*!
   * \brief copy content from src
   * \param src source sketch
   */
  inline void CopyFrom(const WQSummary &src) {
    size = src.size;
    std::memcpy(data, src.data, sizeof(Entry) * size);
  }
  /*!
   * \brief debug function, validate whether the summary
   *  run consistency check to check if it is a valid summary
   * \param eps the tolerate error level, used when RType is floating point and
   *        some inconsistency could occur due to rounding error
   */
  inline void CheckValid(RType eps) const {
    for (size_t i = 0; i < size; ++i) {
      data[i].CheckValid(eps);
      if (i != 0) {
        CHECK(data[i].rmin >= data[i - 1].rmin + data[i - 1].wmin) << "rmin range constraint";
        CHECK(data[i].rmax >= data[i - 1].rmax + data[i].wmin) << "rmax range constraint";
      }
    }
  }
  /*!
   * \brief set current summary to be pruned summary of src
   *        assume data field is already allocated to be at least maxsize
   * \param src source summary
   * \param maxsize size we can afford in the pruned sketch
   */

  inline void SetPrune(const WQSummary &src, size_t maxsize) {
    if (src.size <= maxsize) {
      this->CopyFrom(src); return;
    }
    const RType begin = src.data[0].rmax;
    const RType range = src.data[src.size - 1].rmin - src.data[0].rmax;
    const size_t n = maxsize - 1;
    data[0] = src.data[0];
    this->size = 1;
    // lastidx is used to avoid duplicated records
    size_t i = 1, lastidx = 0;
    for (size_t k = 1; k < n; ++k) {
      RType dx2 =  2 * ((k * range) / n + begin);
      // find first i such that  d < (rmax[i+1] + rmin[i+1]) / 2
      while (i < src.size - 1
             && dx2 >= src.data[i + 1].rmax + src.data[i + 1].rmin) ++i;
      CHECK(i != src.size - 1);
      if (dx2 < src.data[i].rmin_next() + src.data[i + 1].rmax_prev()) {
        if (i != lastidx) {
          data[size++] = src.data[i]; lastidx = i;
        }
      } else {
        if (i + 1 != lastidx) {
          data[size++] = src.data[i + 1]; lastidx = i + 1;
        }
      }
    }
    if (lastidx != src.size - 1) {
      data[size++] = src.data[src.size - 1];
    }
  }
  /*!
   * \brief set current summary to be merged summary of sa and sb
   * \param sa first input summary to be merged
   * \param sb second input summary to be merged
   */
  inline void SetCombine(const WQSummary &sa,
                         const WQSummary &sb) {
    if (sa.size == 0) {
      this->CopyFrom(sb); return;