from pyspark.context import SparkContext

from pyspark.mllib.clustering import KMeans
from pyspark.mllib.random import RandomRDDs


if __name__ == "__main__":
    sc = SparkContext(appName='kmeansMinimalExample')

    # same with 10000 points
    data = RandomRDDs.uniformVectorRDD(sc, 10000000, 64)
    C = KMeans.train(data, 8192,  maxIterations=10)

    sc.stop()