Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/5967#discussion_r29956523
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -44,45 +53,151 @@ private[classification] trait LogisticRegressionParams
extends ProbabilisticClas
@AlphaComponent
class LogisticRegression
extends ProbabilisticClassifier[Vector, LogisticRegression,
LogisticRegressionModel]
- with LogisticRegressionParams {
+ with LogisticRegressionParams with Logging {
- /** @group setParam */
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ * @group setParam
+ */
def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
- /** @group setParam */
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ * @group setParam
+ */
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximal number of iterations.
+ * Default is 100.
+ * @group setParam
+ */
def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is 1E-6.
+ * @group setParam
+ */
+ def setTol(value: Double): this.type = set(tol, value)
+ setDefault(tol -> 1E-6)
/** @group setParam */
def setFitIntercept(value: Boolean): this.type = set(fitIntercept, value)
+ setDefault(fitIntercept -> true)
/** @group setParam */
def setThreshold(value: Double): this.type = set(threshold, value)
+ setDefault(threshold -> 0.5)
override protected def train(dataset: DataFrame):
LogisticRegressionModel = {
// Extract columns from data. If dataset is persisted, do not persist
oldDataset.
- val oldDataset = extractLabeledPoints(dataset)
+ val instances = extractLabeledPoints(dataset).map {
+ case LabeledPoint(label: Double, features: Vector) => (label,
features)
+ }
val handlePersistence = dataset.rdd.getStorageLevel ==
StorageLevel.NONE
- if (handlePersistence) {
- oldDataset.persist(StorageLevel.MEMORY_AND_DISK)
+ if (handlePersistence) instances.persist(StorageLevel.MEMORY_AND_DISK)
+
+ val (summarizer, labelSummarizer) = instances.treeAggregate(
+ (new MultivariateOnlineSummarizer, new MultiClassSummarizer))( {
+ case ((summarizer: MultivariateOnlineSummarizer, labelSummarizer:
MultiClassSummarizer),
--- End diff --
I think we need to update `MultivariateOnline Summarizer`'s constructor to
allow users to set flags to indicate what to compute. Let's do this later:)
---
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]
