数以百万计的3D点:如何找到最接近给定点的10个点？

运行:

$ g++ -O3 nearest.cc && (time ./a.out < million_3D_points.txt )

point: (69.0631 2.23409 50.4198)
(69 2 50) 0.235007
(69 2 51) 0.395424
(69 3 50) 0.766819
(69 3 50) 0.766819
(69 3 51) 0.927236
(70 2 50) 1.1088
(70 2 51) 1.26922
(70 2 51) 1.26922
(70 3 51) 1.80103
(69 1 51) 1.86361

real    0m1.174s
user    0m1.180s
sys 0m0.000s

基于线性搜索的方法(时间~1.15秒)

// $ g++ -O3 nearest.cc && (time ./a.out < million_3D_points.txt )
#include            // sort
#include           // binary_function<>
#include 

#include 
#include      // begin(), end()
#include  // get<>, tuple<>, cout <<

#define foreach BOOST_FOREACH

namespace {
  typedef double coord_t;
  typedef std::tr1::tuple point_t;

  // calculate distance (squared) between points `a` & `b`
  coord_t distance_sq(const point_t& a, const point_t& b);

  // read from input stream `in` to the point `point_out`
  std::istream& getpoint(std::istream& in, point_t& point_out);    

  // Adaptable binary predicate that defines whether the first
  // argument is nearer than the second one to given reference point
  class less_distance : public std::binary_function {
    const point_t& point;
  public:
    explicit less_distance(const point_t& reference_point) 
        : point(reference_point) {}
    bool operator () (const point_t& a, const point_t& b) const {
      return distance_sq(a, point) < distance_sq(b, point);
    } 
  };
}

int main() {
  using namespace std;

  // use point value from previous examples
  point_t point(69.06310224, 2.23409409, 50.41979143);
  cout << "point: " << point << endl;
  less_distance nearer(point);

  const size_t nneighbours = 10; // number of nearest neighbours to find
  point_t points[nneighbours];

  // populate `points`
  foreach (point_t& p, points)
    if (! getpoint(cin, p))
      break;

  // Complexity: O(N*m)
  point_t current_point;
  while(cin) {
    getpoint(cin, current_point); //NOTE: `cin` fails after the last
                                  //point, so one can't lift it up to
                                  //the while condition

    // move to the last position the most distant from the
    // `point` point; O(m)
    foreach (point_t& p, points)
      if (nearer(current_point, p)) 
        // found point that is nearer to the `point` 

        //NOTE: could use insert (on sorted sequence) & break instead
        //of swap but in that case it might be better to use
        //heap-based algorithm altogether
        std::swap(current_point, p);
  }

  // print results;  O(m*log(m))
  sort(boost::begin(points), boost::end(points), nearer);
  foreach (point_t p, points)
    cout << p << ' ' << distance_sq(p, point) << '\n';  
}

namespace {
  coord_t distance_sq(const point_t& a, const point_t& b) { 
    // boost::geometry::distance() squared
    using std::tr1::get;
    coord_t x = get<0>(a) - get<0>(b);
    coord_t y = get<1>(a) - get<1>(b);
    coord_t z = get<2>(a) - get<2>(b);
    return x*x + y*y + z*z;
  }

  std::istream& getpoint(std::istream& in, point_t& point_out) {    
    using std::tr1::get;
    return (in >> get<0>(point_out) >> get<1>(point_out) >> get<2>(point_out));
  }
}