Class: KMeansModel

eclairjs/mllib/clustering.KMeansModel

new KMeansModel(clusterCenters)

A Java-friendly constructor that takes an Iterable of Vectors.
Parameters:
Name Type Description
clusterCenters Array.<Vector>
Source:

Methods

(static) load(sc, path) → {module:eclairjs/mllib/clustering.KMeansModel}

Parameters:
Name Type Description
sc module:eclairjs.SparkContext
path string
Source:
Returns:
Type
module:eclairjs/mllib/clustering.KMeansModel

clusterCenters() → {Promise.<Array.<Vector>>}

Source:
Returns:
Type
Promise.<Array.<Vector>>

computeCost(data) → {Promise.<number>}

Return the K-means cost (sum of squared distances of points to their nearest center) for this model on the given data.
Parameters:
Name Type Description
data module:eclairjs/rdd.RDD
Source:
Returns:
Type
Promise.<number>

k() → {Promise.<number>}

Total number of clusters.
Source:
Returns:
Type
Promise.<number>

predict0(point) → {Promise.<number>}

Returns the cluster index that a given point belongs to.
Parameters:
Name Type Description
point module:eclairjs/mllib/linalg.Vector
Source:
Returns:
Type
Promise.<number>

predict1(points) → {module:eclairjs/rdd.RDD}

Maps given points to their cluster indices.
Parameters:
Name Type Description
points module:eclairjs/rdd.RDD
Source:
Returns:
Type
module:eclairjs/rdd.RDD

predict2(points) → {JavaRDD}

Maps given points to their cluster indices.
Parameters:
Name Type Description
points JavaRDD
Source:
Returns:
Type
JavaRDD

save(sc, path) → {Promise.<Void>}

Parameters:
Name Type Description
sc module:eclairjs.SparkContext
path string
Source:
Returns:
A Promise that resolves to nothing.
Type
Promise.<Void>