Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/9180#discussion_r43481079
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/regression/LinearRegressionSuite.scala
---
@@ -49,16 +50,29 @@ class LinearRegressionSuite extends SparkFunSuite with
MLlibTestSparkContext {
*/
override def beforeAll(): Unit = {
super.beforeAll()
- dataset = sqlContext.createDataFrame(
+ datasetWithDenseFeature = sqlContext.createDataFrame(
sc.parallelize(LinearDataGenerator.generateLinearInput(
- 6.3, Array(4.7, 7.2), Array(0.9, -1.3), Array(0.7, 1.2), 10000,
seed, 0.1), 2))
+ intercept = 6.3, weights = Array(4.7, 7.2), xMean = Array(0.9,
-1.3),
+ xVariance = Array(0.7, 1.2), nPoints = 10000, seed = seed, eps =
0.1), 2))
/*
datasetWithoutIntercept is not needed for correctness testing but
is useful for illustrating
training model without intercept
*/
- datasetWithoutIntercept = sqlContext.createDataFrame(
+ datasetWithDenseFeatureWithoutIntercept = sqlContext.createDataFrame(
sc.parallelize(LinearDataGenerator.generateLinearInput(
- 0.0, Array(4.7, 7.2), Array(0.9, -1.3), Array(0.7, 1.2), 10000,
seed, 0.1), 2))
+ intercept = 0.0, weights = Array(4.7, 7.2), xMean = Array(0.9,
-1.3),
+ xVariance = Array(0.7, 1.2), nPoints = 10000, seed = seed, eps =
0.1), 2))
+
+ val r = new Random(seed)
+ // When feature size is larger than 4096, normal optimizer is choosed
+ // as the solver of linear regression in the case of "auto" mode.
+ val featureSize = 4100
+ datasetWithSparseFeature = sqlContext.createDataFrame(
+ sc.parallelize(LinearDataGenerator.generateLinearInput(
+ intercept = 0.0, weights =
Seq.fill(featureSize)(r.nextDouble).toArray,
+ xMean = Seq.fill(featureSize)(r.nextDouble).toArray,
+ xVariance = Seq.fill(featureSize)(r.nextDouble).toArray, nPoints =
200,
+ seed = seed, eps = 0.1, sparsity = 0.7), 2))
--- End diff --
seed = seed into seed
---
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]
