def train(cls,
rdd,
k,
convergenceTol=1e-3,
maxIterations=100,
seed=None,
initialModel=None):
"""Train a Gaussian Mixture clustering model."""
initialModelWeights = None
initialModelMu = None
initialModelSigma = None
if initialModel is not None:
if initialModel.k != k:
raise Exception(
"Mismatched cluster count, initialModel.k = %s, however k = %s"
% (initialModel.k, k))
initialModelWeights = initialModel.weights
initialModelMu = [
initialModel.gaussians[i].mu for i in range(initialModel.k)
]
initialModelSigma = [
initialModel.gaussians[i].sigma for i in range(initialModel.k)
]
weight, mu, sigma = callMLlibFunc("trainGaussianMixtureModel",
rdd.map(_convert_to_vector), k,
convergenceTol, maxIterations, seed,
initialModelWeights, initialModelMu,
initialModelSigma)
mvg_obj = [MultivariateGaussian(mu[i], sigma[i]) for i in range(k)]
return GaussianMixtureModel(weight, mvg_obj)
def train(cls, rdd, k, convergenceTol=1e-3, maxIterations=100, seed=None):
"""Train a Gaussian Mixture clustering model."""
weight, mu, sigma = callMLlibFunc("trainGaussianMixture",
rdd.map(_convert_to_vector), k,
convergenceTol, maxIterations, seed)
mvg_obj = [MultivariateGaussian(mu[i], sigma[i]) for i in range(k)]
return GaussianMixtureModel(weight, mvg_obj)
def gaussians(self):
"""
Array of MultivariateGaussian where gaussians[i] represents
the Multivariate Gaussian (Normal) Distribution for Gaussian i.
"""
return [
MultivariateGaussian(gaussian[0], gaussian[1])
for gaussian in self.call("gaussians")]
