Github user holdenk commented on a diff in the pull request: https://github.com/apache/spark/pull/10788#discussion_r49962987 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala --- @@ -374,4 +383,82 @@ 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. + * If using ml implementation, uses ml code to generate initial weights. + */ + override def run(input: RDD[LabeledPoint]): LogisticRegressionModel = { + run(input, generateInitialWeights(input), false) + } + + /** + * 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. + * Uses user provided weights. + */ + override def run(input: RDD[LabeledPoint], initialWeights: Vector): LogisticRegressionModel = { + run(input, initialWeights, true) + } + + private def run(input: RDD[LabeledPoint], initialWeights: Vector, userSuppliedWeights: Boolean): + 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) + if (userSuppliedWeights) { + val initialWeightsWithIntercept = if (addIntercept) { + appendBias(initialWeights) + } else { + initialWeights + } + lr.setInitialWeights(initialWeightsWithIntercept) + } + lr.setFitIntercept(addIntercept) + lr.setMaxIter(optimizer.getNumIterations()) + lr.setTol(optimizer.getConvergenceTol()) + // Convert our input into a DataFrame + val sqlContext = new SQLContext(input.context) + import sqlContext.implicits._ + val df = input.toDF() + // Determine if we should cache the DF + val handlePersistence = input.getStorageLevel == StorageLevel.NONE + if (handlePersistence) { + df.persist(StorageLevel.MEMORY_AND_DISK) + } --- End diff -- So the ML code checks on the DataFrame - which will never be cached. So we check on the user supplied input and if the user supplied input is not persisted we handle our own persistance but if the user supplied input is persisted then we don't.
--- 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