jubatus::core::clustering::kmeans_clustering_method Class Reference

#include <kmeans_clustering_method.hpp>

Inheritance diagram for jubatus::core::clustering::kmeans_clustering_method:

Collaboration diagram for jubatus::core::clustering::kmeans_clustering_method:

Public Member Functions
void	batch_update (wplist points)
wplist	get_cluster (size_t cluster_id, const wplist &points) const
std::vector< wplist >	get_clusters (const wplist &points) const
std::vector< common::sfv_t >	get_k_center () const
common::sfv_t	get_nearest_center (const common::sfv_t &point) const
int64_t	get_nearest_center_index (const common::sfv_t &point) const
	kmeans_clustering_method (size_t k)
void	online_update (wplist points)
	~kmeans_clustering_method ()
Public Member Functions inherited from jubatus::core::clustering::clustering_method
virtual	~clustering_method ()

Private Member Functions
void	do_batch_update (wplist &points)
void	initialize_centers (wplist &points)

Private Attributes
size_t	k_
std::vector< common::sfv_t >	kcenters_

Detailed Description

Definition at line 27 of file kmeans_clustering_method.hpp.

Constructor & Destructor Documentation

jubatus::core::clustering::kmeans_clustering_method::kmeans_clustering_method ( size_t  k )

explicit

Definition at line 32 of file kmeans_clustering_method.cpp.

    : k_(k) {
}

jubatus::core::clustering::kmeans_clustering_method::~kmeans_clustering_method

(

)

Definition at line 36 of file kmeans_clustering_method.cpp.

                                                    {
}

Member Function Documentation

void jubatus::core::clustering::kmeans_clustering_method::batch_update ( wplist  points )

virtual

Implements jubatus::core::clustering::clustering_method.

Definition at line 39 of file kmeans_clustering_method.cpp.

References do_batch_update(), initialize_centers(), and kcenters_.

                                                         {
  if (points.empty()) {
    kcenters_.clear();
    return;
  }
  initialize_centers(points);
  do_batch_update(points);
}

Here is the call graph for this function:

void jubatus::core::clustering::kmeans_clustering_method::do_batch_update ( wplist &  points )

private

Definition at line 66 of file kmeans_clustering_method.cpp.

References jubatus::core::clustering::dist(), k_, kcenters_, jubatus::core::clustering::min_dist(), jubatus::core::clustering::scalar_dot(), and jubatus::core::clustering::scalar_mul_and_add().

Referenced by batch_update().

                                                             {
  static jubatus::util::math::random::mtrand r;
  bool terminated = false;
  if (points.size() < k_) {
    return;
  }
  while (!terminated) {
    vector<common::sfv_t> kcenters_new(k_);
    vector<double> center_count(k_, 0);
    for (wplist::iterator it = points.begin(); it != points.end(); ++it) {
      pair<int64_t, double> m = min_dist((*it).data, kcenters_);
      scalar_mul_and_add(it->data, it->weight, kcenters_new[m.first]);
      center_count[m.first] += it->weight;
    }
    terminated = true;
    for (size_t i = 0; i < k_; ++i) {
      if (center_count[i] == 0) {
        kcenters_new[i] = kcenters_[i];
        continue;
      }
      kcenters_new[i] = scalar_dot(kcenters_new[i], 1.0 / center_count[i]);
      double d = dist(kcenters_new[i], kcenters_[i]);
      if (d > 1e-9) {
        terminated = false;
      }
    }
    kcenters_ = kcenters_new;
  }
}

Here is the call graph for this function:

Here is the caller graph for this function:

wplist jubatus::core::clustering::kmeans_clustering_method::get_cluster ( size_t  cluster_id, const wplist &  points  ) const

virtual

Implements jubatus::core::clustering::clustering_method.

Definition at line 113 of file kmeans_clustering_method.cpp.

References get_clusters(), and k_.

                                {
  if (cluster_id >= k_) {
    return wplist();
  }
  return get_clusters(points)[cluster_id];
}

Here is the call graph for this function:

vector< wplist > jubatus::core::clustering::kmeans_clustering_method::get_clusters ( const wplist &  points ) const

virtual

Implements jubatus::core::clustering::clustering_method.

Definition at line 122 of file kmeans_clustering_method.cpp.

References k_, kcenters_, and jubatus::core::clustering::min_dist().

Referenced by get_cluster().

                                {
  vector<wplist> ret(k_);
  for (wplist::const_iterator it = points.begin(); it != points.end(); ++it) {
    pair<int64_t, double> m = min_dist(it->data, kcenters_);
    ret[m.first].push_back(*it);
  }
  return ret;
}

Here is the call graph for this function:

Here is the caller graph for this function:

vector< common::sfv_t > jubatus::core::clustering::kmeans_clustering_method::get_k_center ( ) const

virtual

Implements jubatus::core::clustering::clustering_method.

Definition at line 99 of file kmeans_clustering_method.cpp.

References kcenters_.

                                                                 {
  return kcenters_;
}

common::sfv_t jubatus::core::clustering::kmeans_clustering_method::get_nearest_center ( const common::sfv_t &  point ) const

virtual

Implements jubatus::core::clustering::clustering_method.

Definition at line 108 of file kmeans_clustering_method.cpp.

References get_nearest_center_index(), and kcenters_.

                                    {
  return kcenters_[get_nearest_center_index(point)];
}

Here is the call graph for this function:

int64_t jubatus::core::clustering::kmeans_clustering_method::get_nearest_center_index ( const common::sfv_t &  point ) const

virtual

Implements jubatus::core::clustering::clustering_method.

Definition at line 103 of file kmeans_clustering_method.cpp.

References kcenters_, and jubatus::core::clustering::min_dist().

Referenced by get_nearest_center().

                                    {
  return min_dist(point, kcenters_).first;
}

Here is the call graph for this function:

Here is the caller graph for this function:

void jubatus::core::clustering::kmeans_clustering_method::initialize_centers ( wplist &  points )

private

Definition at line 48 of file kmeans_clustering_method.cpp.

References k_, kcenters_, and jubatus::core::clustering::min_dist().

Referenced by batch_update().

                                                                {
  if (points.size() < k_) {
    return;
  }
  kcenters_.clear();
  kcenters_.push_back(points[0].data);
  vector<double> weights;
  while (kcenters_.size() < k_) {
    weights.clear();
    for (wplist::iterator it = points.begin(); it != points.end(); ++it) {
      pair<int64_t, double> m = min_dist((*it).data, kcenters_);
      weights.push_back(m.second * it->weight);
    }
    discrete_distribution d(weights.begin(), weights.end());
    kcenters_.push_back(points[d()].data);
  }
}

Here is the call graph for this function:

Here is the caller graph for this function:

void jubatus::core::clustering::kmeans_clustering_method::online_update ( wplist  points )

virtual

Implements jubatus::core::clustering::clustering_method.

Definition at line 96 of file kmeans_clustering_method.cpp.

                                                          {
}

Member Data Documentation

size_t jubatus::core::clustering::kmeans_clustering_method::k_

private

Definition at line 45 of file kmeans_clustering_method.hpp.

Referenced by do_batch_update(), get_cluster(), get_clusters(), and initialize_centers().

std::vector<common::sfv_t> jubatus::core::clustering::kmeans_clustering_method::kcenters_

private

Definition at line 44 of file kmeans_clustering_method.hpp.

Referenced by batch_update(), do_batch_update(), get_clusters(), get_k_center(), get_nearest_center(), get_nearest_center_index(), and initialize_centers().

---

The documentation for this class was generated from the following files:

• jubatus/core/clustering/kmeans_clustering_method.hpp
• jubatus/core/clustering/kmeans_clustering_method.cpp