KMeans

class pyspark.mllib.clustering.KMeans[source]

K-means clustering.

New in version 0.9.0.

Methods

train(rdd, k[, maxIterations, …])

Train a k-means clustering model.

Methods Documentation

classmethod train(rdd: pyspark.rdd.RDD[VectorLike], k: int, maxIterations: int = 100, initializationMode: str = 'k-means||', seed: Optional[int] = None, initializationSteps: int = 2, epsilon: float = 0.0001, initialModel: Optional[pyspark.mllib.clustering.KMeansModel] = None, distanceMeasure: str = 'euclidean') → KMeansModel[source]

Train a k-means clustering model.

New in version 0.9.0.

Parameters
rdd:pyspark.RDD

Training points as an RDD of pyspark.mllib.linalg.Vector or convertible sequence types.

kint

Number of clusters to create.

maxIterationsint, optional

Maximum number of iterations allowed. (default: 100)

initializationModestr, optional

The initialization algorithm. This can be either “random” or “k-means||”. (default: “k-means||”)

seedint, optional

Random seed value for cluster initialization. Set as None to generate seed based on system time. (default: None)

initializationSteps :

Number of steps for the k-means|| initialization mode. This is an advanced setting – the default of 2 is almost always enough. (default: 2)

epsilonfloat, optional

Distance threshold within which a center will be considered to have converged. If all centers move less than this Euclidean distance, iterations are stopped. (default: 1e-4)

initialModelKMeansModel, optional

Initial cluster centers can be provided as a KMeansModel object rather than using the random or k-means|| initializationModel. (default: None)

distanceMeasurestr, optional

The distance measure used by the k-means algorithm. (default: “euclidean”)