NearestNeighbourAlgorithm

class NearestNeighbourAlgorithm(*args)

Nearest neighbour lookup.

Base class to define an algorithm to search for nearest neighbours of a list of points.

Parameters:

sampleSample

Input points.

Methods

getClassName()	Accessor to the object's name.
getId()	Accessor to the object's id.
getImplementation()	Accessor to the underlying implementation.
getName()	Accessor to the object's name.
getSample()	Get the points which have been used to build this nearest neighbour algorithm.
query(*args)	Get the index of the nearest neighbour of the given point.
queryK(x, k[, sorted])	Get the indices of nearest neighbours of the given point.
setName(name)	Accessor to the object's name.
setSample(sample)	Build a NearestNeighbourAlgorithm from these points.

See also

KDTree, NearestNeighbour1D, RegularGridNearestNeighbour, NaiveNearestNeighbour

Notes

Two algorithms can be selected in any dimension:

• NaiveNearestNeighbour loops over all points of the sample to find the closest one.

• KDTree builds a binary tree.

Two algorithms are specific to 1D input dimension, and much more efficient:

• RegularGridNearestNeighbour is the most efficient algorithm when points corresponds to a RegularGrid, query() works in constant time.

• NearestNeighbour1D looks for nearest neighbour by dichotomy in 1D.

It is recommended to use derived classes in order to select the best algorithm according to your data. If you create a generic NearestNeighbourAlgorithm, here is how the derived class is selected:

• If points correspond to a RegularGrid, RegularGridNearestNeighbour algorithm is selected.

• If input dimension is 1, NearestNeighbour1D is selected.

• Otherwise, KDTree is selected.

Examples

>>> import openturns as ot
>>> sample = ot.Normal(2).getSample(10)
>>> finder = ot.NearestNeighbourAlgorithm(sample)
>>> neighbour = sample[finder.query([0.1, 0.2])]

__init__(*args)

getClassName()

Accessor to the object’s name.

Returns:

class_namestr

The object class name (object.__class__.__name__).

getId()

Accessor to the object’s id.

Returns:

idint

Internal unique identifier.

getImplementation()

Accessor to the underlying implementation.

Returns:

implImplementation

A copy of the underlying implementation object.

getName()

Accessor to the object’s name.

Returns:

namestr

The name of the object.

getSample()

Get the points which have been used to build this nearest neighbour algorithm.

Returns:

sampleSample

Input points.

query(*args)

Get the index of the nearest neighbour of the given point.

Available usages:

query(point)

query(sample)

Parameters:

pointsequence of float

Given point.

sample2-d sequence of float

Given points.

Returns:

indexint

Index of the nearest neighbour of the given point.

indicesIndices

Index of the nearest neighbour of the given points.

queryK(x, k, sorted=False)

Get the indices of nearest neighbours of the given point.

Parameters:

xsequence of float

Given point.

kint

Number of indices to return.

sortedbool, optional

Boolean to tell whether returned indices are sorted according to the distance to the given point.

Returns:

indicessequence of int

Indices of the k nearest neighbours of the given point.

setName(name)

Accessor to the object’s name.

Parameters:

namestr

The name of the object.

setSample(sample)

Build a NearestNeighbourAlgorithm from these points.

Parameters:

sampleSample

Input points.