diff options
Diffstat (limited to 'mllib')
10 files changed, 27 insertions, 17 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/KMeansDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/KMeansDataGenerator.scala index 6eaebaf7db..e6bcff48b0 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/util/KMeansDataGenerator.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/util/KMeansDataGenerator.scala @@ -64,8 +64,10 @@ object KMeansDataGenerator { def main(args: Array[String]) { if (args.length < 6) { + // scalastyle:off println println("Usage: KMeansGenerator " + "<master> <output_dir> <num_points> <k> <d> <r> [<num_partitions>]") + // scalastyle:on println System.exit(1) } diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala index b4e33c98ba..87eeb5db05 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala @@ -153,8 +153,10 @@ object LinearDataGenerator { def main(args: Array[String]) { if (args.length < 2) { + // scalastyle:off println println("Usage: LinearDataGenerator " + "<master> <output_dir> [num_examples] [num_features] [num_partitions]") + // scalastyle:on println System.exit(1) } diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala index 9d802678c4..c09cbe69bb 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala @@ -64,8 +64,10 @@ object LogisticRegressionDataGenerator { def main(args: Array[String]) { if (args.length != 5) { + // scalastyle:off println println("Usage: LogisticRegressionGenerator " + "<master> <output_dir> <num_examples> <num_features> <num_partitions>") + // scalastyle:on println System.exit(1) } diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala index bd73a866c8..16f430599a 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala @@ -55,8 +55,10 @@ import org.apache.spark.rdd.RDD object MFDataGenerator { def main(args: Array[String]) { if (args.length < 2) { + // scalastyle:off println println("Usage: MFDataGenerator " + "<master> <outputDir> [m] [n] [rank] [trainSampFact] [noise] [sigma] [test] [testSampFact]") + // scalastyle:on println System.exit(1) } diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala index a8e30cc9d7..ad20b7694a 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala @@ -37,8 +37,10 @@ object SVMDataGenerator { def main(args: Array[String]) { if (args.length < 2) { + // scalastyle:off println println("Usage: SVMGenerator " + "<master> <output_dir> [num_examples] [num_features] [num_partitions]") + // scalastyle:on println System.exit(1) } diff --git a/mllib/src/test/scala/org/apache/spark/ml/feature/VectorIndexerSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/feature/VectorIndexerSuite.scala index 8c85c96d5c..03120c828c 100644 --- a/mllib/src/test/scala/org/apache/spark/ml/feature/VectorIndexerSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/ml/feature/VectorIndexerSuite.scala @@ -19,7 +19,7 @@ package org.apache.spark.ml.feature import scala.beans.{BeanInfo, BeanProperty} -import org.apache.spark.{SparkException, SparkFunSuite} +import org.apache.spark.{Logging, SparkException, SparkFunSuite} import org.apache.spark.ml.attribute._ import org.apache.spark.ml.param.ParamsSuite import org.apache.spark.mllib.linalg.{SparseVector, Vector, Vectors} @@ -27,7 +27,7 @@ import org.apache.spark.mllib.util.MLlibTestSparkContext import org.apache.spark.rdd.RDD import org.apache.spark.sql.DataFrame -class VectorIndexerSuite extends SparkFunSuite with MLlibTestSparkContext { +class VectorIndexerSuite extends SparkFunSuite with MLlibTestSparkContext with Logging { import VectorIndexerSuite.FeatureData @@ -113,11 +113,11 @@ class VectorIndexerSuite extends SparkFunSuite with MLlibTestSparkContext { model.transform(sparsePoints1) // should work intercept[SparkException] { model.transform(densePoints2).collect() - println("Did not throw error when fit, transform were called on vectors of different lengths") + logInfo("Did not throw error when fit, transform were called on vectors of different lengths") } intercept[SparkException] { vectorIndexer.fit(badPoints) - println("Did not throw error when fitting vectors of different lengths in same RDD.") + logInfo("Did not throw error when fitting vectors of different lengths in same RDD.") } } @@ -196,7 +196,7 @@ class VectorIndexerSuite extends SparkFunSuite with MLlibTestSparkContext { } } catch { case e: org.scalatest.exceptions.TestFailedException => - println(errMsg) + logError(errMsg) throw e } } diff --git a/mllib/src/test/scala/org/apache/spark/mllib/linalg/VectorsSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/linalg/VectorsSuite.scala index c4ae0a16f7..178d95a7b9 100644 --- a/mllib/src/test/scala/org/apache/spark/mllib/linalg/VectorsSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/mllib/linalg/VectorsSuite.scala @@ -21,10 +21,10 @@ import scala.util.Random import breeze.linalg.{DenseMatrix => BDM, squaredDistance => breezeSquaredDistance} -import org.apache.spark.{SparkException, SparkFunSuite} +import org.apache.spark.{Logging, SparkException, SparkFunSuite} import org.apache.spark.mllib.util.TestingUtils._ -class VectorsSuite extends SparkFunSuite { +class VectorsSuite extends SparkFunSuite with Logging { val arr = Array(0.1, 0.0, 0.3, 0.4) val n = 4 @@ -142,7 +142,7 @@ class VectorsSuite extends SparkFunSuite { malformatted.foreach { s => intercept[SparkException] { Vectors.parse(s) - println(s"Didn't detect malformatted string $s.") + logInfo(s"Didn't detect malformatted string $s.") } } } diff --git a/mllib/src/test/scala/org/apache/spark/mllib/stat/CorrelationSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/stat/CorrelationSuite.scala index c292ced75e..c3eeda0125 100644 --- a/mllib/src/test/scala/org/apache/spark/mllib/stat/CorrelationSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/mllib/stat/CorrelationSuite.scala @@ -19,13 +19,13 @@ package org.apache.spark.mllib.stat import breeze.linalg.{DenseMatrix => BDM, Matrix => BM} -import org.apache.spark.SparkFunSuite +import org.apache.spark.{Logging, SparkFunSuite} import org.apache.spark.mllib.linalg.Vectors import org.apache.spark.mllib.stat.correlation.{Correlations, PearsonCorrelation, SpearmanCorrelation} import org.apache.spark.mllib.util.MLlibTestSparkContext -class CorrelationSuite extends SparkFunSuite with MLlibTestSparkContext { +class CorrelationSuite extends SparkFunSuite with MLlibTestSparkContext with Logging { // test input data val xData = Array(1.0, 0.0, -2.0) @@ -146,7 +146,7 @@ class CorrelationSuite extends SparkFunSuite with MLlibTestSparkContext { def matrixApproxEqual(A: BM[Double], B: BM[Double], threshold: Double = 1e-6): Boolean = { for (i <- 0 until A.rows; j <- 0 until A.cols) { if (!approxEqual(A(i, j), B(i, j), threshold)) { - println("i, j = " + i + ", " + j + " actual: " + A(i, j) + " expected:" + B(i, j)) + logInfo("i, j = " + i + ", " + j + " actual: " + A(i, j) + " expected:" + B(i, j)) return false } } diff --git a/mllib/src/test/scala/org/apache/spark/mllib/tree/GradientBoostedTreesSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/tree/GradientBoostedTreesSuite.scala index 84dd3b342d..2521b33421 100644 --- a/mllib/src/test/scala/org/apache/spark/mllib/tree/GradientBoostedTreesSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/mllib/tree/GradientBoostedTreesSuite.scala @@ -17,7 +17,7 @@ package org.apache.spark.mllib.tree -import org.apache.spark.SparkFunSuite +import org.apache.spark.{Logging, SparkFunSuite} import org.apache.spark.mllib.regression.LabeledPoint import org.apache.spark.mllib.tree.configuration.Algo._ import org.apache.spark.mllib.tree.configuration.{BoostingStrategy, Strategy} @@ -31,7 +31,7 @@ import org.apache.spark.util.Utils /** * Test suite for [[GradientBoostedTrees]]. */ -class GradientBoostedTreesSuite extends SparkFunSuite with MLlibTestSparkContext { +class GradientBoostedTreesSuite extends SparkFunSuite with MLlibTestSparkContext with Logging { test("Regression with continuous features: SquaredError") { GradientBoostedTreesSuite.testCombinations.foreach { @@ -50,7 +50,7 @@ class GradientBoostedTreesSuite extends SparkFunSuite with MLlibTestSparkContext EnsembleTestHelper.validateRegressor(gbt, GradientBoostedTreesSuite.data, 0.06) } catch { case e: java.lang.AssertionError => - println(s"FAILED for numIterations=$numIterations, learningRate=$learningRate," + + logError(s"FAILED for numIterations=$numIterations, learningRate=$learningRate," + s" subsamplingRate=$subsamplingRate") throw e } @@ -80,7 +80,7 @@ class GradientBoostedTreesSuite extends SparkFunSuite with MLlibTestSparkContext EnsembleTestHelper.validateRegressor(gbt, GradientBoostedTreesSuite.data, 0.85, "mae") } catch { case e: java.lang.AssertionError => - println(s"FAILED for numIterations=$numIterations, learningRate=$learningRate," + + logError(s"FAILED for numIterations=$numIterations, learningRate=$learningRate," + s" subsamplingRate=$subsamplingRate") throw e } @@ -111,7 +111,7 @@ class GradientBoostedTreesSuite extends SparkFunSuite with MLlibTestSparkContext EnsembleTestHelper.validateClassifier(gbt, GradientBoostedTreesSuite.data, 0.9) } catch { case e: java.lang.AssertionError => - println(s"FAILED for numIterations=$numIterations, learningRate=$learningRate," + + logError(s"FAILED for numIterations=$numIterations, learningRate=$learningRate," + s" subsamplingRate=$subsamplingRate") throw e } diff --git a/mllib/src/test/scala/org/apache/spark/mllib/util/NumericParserSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/util/NumericParserSuite.scala index fa4f74d71b..16d7c3ab39 100644 --- a/mllib/src/test/scala/org/apache/spark/mllib/util/NumericParserSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/mllib/util/NumericParserSuite.scala @@ -33,7 +33,7 @@ class NumericParserSuite extends SparkFunSuite { malformatted.foreach { s => intercept[SparkException] { NumericParser.parse(s) - println(s"Didn't detect malformatted string $s.") + throw new RuntimeException(s"Didn't detect malformatted string $s.") } } } |