Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/15413#discussion_r85186676
--- 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.
--- End diff --
this comment adds no value IMO
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
