Github user sethah commented on a diff in the pull request: https://github.com/apache/spark/pull/15413#discussion_r85025434 --- Diff: mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala --- @@ -316,24 +319,129 @@ class GaussianMixture @Since("2.0.0") ( @Since("2.0.0") def setSeed(value: Long): this.type = set(seed, value) + // number of samples per cluster to use when initializing Gaussians + private val nSamples = 5 + @Since("2.0.0") override def fit(dataset: Dataset[_]): GaussianMixtureModel = { transformSchema(dataset.schema, logging = true) - val rdd: RDD[OldVector] = dataset.select(col($(featuresCol))).rdd.map { - case Row(point: Vector) => OldVectors.fromML(point) + + val sc = dataset.sparkSession.sparkContext + val _k = $(k) + + val instances: RDD[Vector] = dataset.select(col($(featuresCol))).rdd.map { + case Row(features: Vector) => features + }.cache() + + // Extract the number of features. + val numFeatures = instances.first().size + + val shouldDistributeGaussians = GaussianMixture.shouldDistributeGaussians(_k, numFeatures) + + // Determine initial weights and corresponding Gaussians. + // We start with uniform weights, a random mean from the data, and + // diagonal covariance matrices using component variances + // derived from the samples. + // TODO: Support users supplied initial GMM. + val samples = instances.takeSample(withReplacement = true, _k * nSamples, $(seed)) + val weights: Array[Double] = Array.fill(_k)(1.0 / _k) + /** + * Since the covariance matrix of multivariate gaussian distribution is symmetric, + * only the upper triangular part of the matrix will be stored as a dense vector + * in order to reduce the shuffled data size. + */ + val gaussians: Array[(DenseVector, DenseVector)] = Array.tabulate(_k) { i => --- End diff -- I think it would be nice to factor this out into an initialization method so we can just call `val gaussians = initRandom(...)` or similar.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org