Github user dbtsai commented on a diff in the pull request: https://github.com/apache/spark/pull/6386#discussion_r31586162 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala --- @@ -363,4 +371,54 @@ class LogisticRegressionWithLBFGS new LogisticRegressionModel(weights, intercept, numFeatures, numOfLinearPredictor + 1) } } + + /** + * Run the algorithm with the configured parameters on an input RDD + * of LabeledPoint entries starting from the initial weights provided. + * If a known updater is used calls the ml implementation, to avoid + * applying a regularization penalty to the intercept, otherwise + * defaults to the mllib implementation. If more than two classes + * or feature scaling is disabled, always uses mllib implementation. + */ + override def run(input: RDD[LabeledPoint], initialWeights: Vector): LogisticRegressionModel = { + // ml's Logisitic regression only supports binary classifcation currently. + if (numOfLinearPredictor == 1 && useFeatureScaling) { + def runWithMlLogisitcRegression(elasticNetParam: Double) = { + // Prepare the ml LogisticRegression based on our settings + val lr = new org.apache.spark.ml.classification.LogisticRegression() + lr.setRegParam(optimizer.getRegParam()) + lr.setElasticNetParam(elasticNetParam) + val initialWeightsWithIntercept = Vectors.dense(0.0, initialWeights.toArray:_*) --- End diff -- Sounds great.
--- 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