ml::Clustering::KMeans Class Reference

Naive K-means clustering method. More...

#include <KMeans.hpp>

Inheritance diagram for ml::Clustering::KMeans:

Collaboration diagram for ml::Clustering::KMeans:

Public Member Functions
	KMeans (unsigned int number_clusters)
	Constructs a K-means model ready to fit. More...
bool	fit (Eigen::Ref< const Eigen::MatrixXd > data) override
	Fits the model. More...
unsigned int	number_clusters () const override
	Returns the number of clusters. More...
const std::vector< unsigned int > &	labels () const override
	Returns a const reference to resulting cluster labels for each datapoint. Value make sense only if fitting converged successfully.
const Eigen::MatrixXd &	centroids () const override
	Returns a const reference to the matrix of cluster centroids (in columns). More...
void	set_seed (unsigned int seed)
	Sets PRNG seed. More...
void	set_absolute_tolerance (double absolute_tolerance)
	Sets absolute tolerance for convergence test: || old centroids - new centroids ||^2 < absolute tolerance. More...
void	set_maximum_steps (unsigned int maximum_steps)
	Sets maximum number of K-means steps. More...
void	set_number_initialisations (unsigned int number_initialisations)
	Sets number of initialisations to try, to find the clusters with lowest inertia. More...
void	set_centroids_initialiser (std::shared_ptr< const CentroidsInitialiser > centroids_initialiser)
	Sets centroids initialiser. More...
void	set_verbose (bool verbose)
	Switches between verbose and quiet mode. More...
std::pair< unsigned int, double >	assign_label (Eigen::Ref< const Eigen::VectorXd > x) const
	Given a data point x, assign it to its cluster and return the correct label and squared Euclidean distance to the assigned centroid. More...
double	inertia () const
	Sum of squared distances to the nearest centroid. More...
bool	converged () const override
	Reports if the model converged.
Public Member Functions inherited from ml::Clustering::Model
virtual	~Model ()
	Virtual destructor.

Detailed Description

Naive K-means clustering method.

Converges if exactly the same cluster assignments are chosen twice, or if sum of squared differences between new and old centroids is lower than tolerance.

Constructor & Destructor Documentation

KMeans()

ml::Clustering::KMeans::KMeans

(

unsigned int

number_clusters

)

Constructs a K-means model ready to fit.

Parameters

[in]

number_clusters

Number of clusters.

Exceptions

std::invalid_argument

If number_clusters == 0.

Member Function Documentation

fit()

bool ml::Clustering::KMeans::fit ( Eigen::Ref< const Eigen::MatrixXd >  data )

overridevirtual

Fits the model.

Parameters

[in]

data

Matrix (column-major order) with a data point in every column.

Returns

true if fitting converged successfully.

Exceptions

std::invalid_argument

If data has no rows, or if the sample size (number of columns in data) is too low.

Implements ml::Clustering::Model.

number_clusters()

unsigned int ml::Clustering::KMeans::number_clusters ( ) const

inlineoverridevirtual

Returns the number of clusters.

Value make sense only if fitting converged successfully.

Implements ml::Clustering::Model.

centroids()

const Eigen::MatrixXd& ml::Clustering::KMeans::centroids ( ) const

inlineoverridevirtual

Returns a const reference to the matrix of cluster centroids (in columns).

A centroid represent the central location of the cluster. It is e.g. a mean of all points in the cluster. Value make sense only if fitting converged successfully.

Implements ml::Clustering::Model.

set_seed()

void ml::Clustering::KMeans::set_seed

(

unsigned int

seed

)

Sets PRNG seed.

Parameters

[in]

seed

PRNG seed.

set_absolute_tolerance()

void ml::Clustering::KMeans::set_absolute_tolerance

(

double

absolute_tolerance

)

Sets absolute tolerance for convergence test: || old centroids - new centroids ||^2 < absolute tolerance.

Parameters

[in]

absolute_tolerance

Absolute tolerance.

Exceptions

std::domain_error

If absolute_tolerance < 0.

set_maximum_steps()

void ml::Clustering::KMeans::set_maximum_steps

(

unsigned int

maximum_steps

)

Sets maximum number of K-means steps.

Parameters

[in]

maximum_steps

Maximum number of steps.

Exceptions

std::invalid_argument

If maximum_steps < 2.

set_number_initialisations()

void ml::Clustering::KMeans::set_number_initialisations

(

unsigned int

number_initialisations

)

Sets number of initialisations to try, to find the clusters with lowest inertia.

Parameters

number_initialisations

Number of initialisations.

Exceptions

std::invalid_argument

If number_initialisations < 1.

set_centroids_initialiser()

void ml::Clustering::KMeans::set_centroids_initialiser

(

std::shared_ptr< const CentroidsInitialiser >

centroids_initialiser

)

Sets centroids initialiser.

Parameters

[in]

centroids_initialiser

Pointer to CentroidsInitialiser implementation.

Exceptions

std::invalid_argument

If centroids_initialiser is null.

set_verbose()

void ml::Clustering::KMeans::set_verbose ( bool  verbose )

inline

Switches between verbose and quiet mode.

Parameters

[in]

verbose

true if we want verbose output.

assign_label()

std::pair<unsigned int, double> ml::Clustering::KMeans::assign_label

(

Eigen::Ref< const Eigen::VectorXd >

x

)

const

Given a data point x, assign it to its cluster and return the correct label and squared Euclidean distance to the assigned centroid.

Parameters

[in]

x

Data point with correct dimension.

Exceptions

std::invalid_argument

If x.size() != means().rows().

inertia()

double ml::Clustering::KMeans::inertia ( ) const

inline

Sum of squared distances to the nearest centroid.

Returns

Non-negative number;

---

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

• ML/KMeans.hpp