Class: TriMap

new TriMap(X, parameters) → {TriMap}

Parameters:

Name Type Description

X

Matrix

the high-dimensional data.

parameters

object

Object containing parameterization of the DR method.

Properties

Name	Type	Attributes	Default	Description
`weight_adj`	number	<optional>	500	scaling factor.
`c`	number	<optional>	5	number of triplets multiplier.
`d`	number	<optional>	2	the dimensionality of the projection.
`tol`	number	<optional>	1e-8
`metric`	function	<optional>	euclidean	the metric which defines the distance between two points.
`seed`	number	<optional>	1212	the seed for the random number generator.

Source: dimred/TriMap.js, line 12
See: https://arxiv.org/pdf/1910.00204v1.pdf
https://github.com/eamid/trimap

Returns:

Type:: TriMap

Extends

Members

projection

Overrides: DR#projection
Source: dimred/DR.js, line 112

Methods

_generate_triplets(n_inliers, n_outliers, n_random)

Generates n_inliers x n_outliers x n_random triplets.

Parameters:

Name	Type	Description
`n_inliers`	number
`n_outliers`	number
`n_random`	number

Source: dimred/TriMap.js, line 65

_grad(Y)

Computes the gradient for updating the embedding.

Parameters:

Name	Type	Description
`Y`	Matrix	The embedding

Source: dimred/TriMap.js, line 265

check_init() → {DR}

If the respective DR method has an init function, call it before transform.

Overrides: DR#check_init
Source: dimred/DR.js, line 101

Returns:

Type:: DR

(generator) generator(max_iteration) → {Matrix|Array.<Array.<number>>}

Parameters:

Name	Type	Default	Description
`max_iteration`	number	800

Overrides: DR#generator
Source: dimred/TriMap.js, line 339

Returns:

Type:: Matrix | Array.<Array.<number>>

Yields:

Type:: Matrix | Array.<Array.<number>>

init(pcaopt, knnopt)

Parameters:

Name	Type	Attributes	Default	Description
`pca`	Matrix	<optional>	null	Initial Embedding (if null then PCA gets used).
`knn`	KNN	<optional>	null	KNN Object (if null then BallTree gets used).

Source: dimred/TriMap.js, line 40

parameter(nameopt, valueopt) → {DR|any|object}

Set and get parameters

Parameters:

Name	Type	Attributes	Default	Description
`name`	string	<optional>	null	Name of the parameter. If not given then returns all parameters as an Object.
`value`	any	<optional>	null	Value of the parameter to set. If `name` is set and `value` is not given, returns the value of the respective parameter.

Overrides: DR#parameter
Source: dimred/DR.js, line 56

Returns:

On setting a parameter, this function returns the DR object. If name is set and value == null then return actual parameter value. If name is not given, then returns all parameters as an Object.

Type:: DR | any | object

Example

'''
const DR = new druid.TSNE(X, {d: 3}); // creates a new DR object, with parameter for <code>d</code> = 3.
DR.parameter("d"); // returns 3,
DR.parameter("d", 2); // sets parameter <code>d</code> to 2 and returns <code>DR</code>.
'''

transform(max_iteration) → {Matrix|Array.<Array.<number>>}

Parameters:

Name	Type	Default	Description
`max_iteration`	number	400

Overrides: DR#transform
Source: dimred/TriMap.js, line 326

Returns:

Type:: Matrix | Array.<Array.<number>>

(async) transform_async(…args) → {Promise.<(Matrix|Array.<Array.<number>>)>}

Computes the projection.

Parameters:

Name	Type	Attributes	Description
`args`	unknown	<repeatable>	Arguments the transform method of the respective DR method takes.

Overrides: DR#transform_async
Source: dimred/DR.js, line 126

Returns:

the dimensionality reduced dataset.

Type:: Promise.<(Matrix|Array.<Array.<number>>)>