Learning algorithm for Gaussian Mixtures using the expectation-maximization algorithm.
New in version 1.3.0.
train(rdd, k[, convergenceTol, …])
Train a Gaussian Mixture clustering model.
Training points as an RDD of pyspark.mllib.linalg.Vector
or convertible sequence types.
Number of independent Gaussians in the mixture model.
Maximum change in log-likelihood at which convergence is
considered to have occurred.
Maximum number of iterations allowed.
Random seed for initial Gaussian distribution. Set as None to
generate seed based on system time.
Initial GMM starting point, bypassing the random