[SPARK-7927] [MLLIB] Enforce whitespace for more tokens in style checker

rxin

Author: Xiangrui Meng <meng@databricks.com>

Closes #6481 from mengxr/mllib-scalastyle and squashes the following commits:

3ca4d61 [Xiangrui Meng] revert scalastyle config
30961ba [Xiangrui Meng] adjust spaces in mllib/test
571b5c5 [Xiangrui Meng] fix spaces in mllib

(cherry picked from commit 04616b1a2f5244710b07ecbb404384ded893292c)
Signed-off-by: Reynold Xin <rxin@databricks.com>

15 files changed, 47 insertions, 29 deletions

diff --git a/mllib/src/test/scala/org/apache/spark/ml/feature/Word2VecSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/feature/Word2VecSuite.scala
index 43a09cc418..df446d0c22 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/feature/Word2VecSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/feature/Word2VecSuite.scala
@@ -35,9 +35,9 @@ class Word2VecSuite extends FunSuite with MLlibTestSparkContext {
     val doc = sc.parallelize(Seq(sentence, sentence)).map(line => line.split(" "))
 
     val codes = Map(
-      "a" -> Array(-0.2811822295188904,-0.6356269121170044,-0.3020961284637451),
-      "b" -> Array(1.0309048891067505,-1.29472815990448,0.22276712954044342),
-      "c" -> Array(-0.08456747233867645,0.5137411952018738,0.11731560528278351)
+      "a" -> Array(-0.2811822295188904, -0.6356269121170044, -0.3020961284637451),
+      "b" -> Array(1.0309048891067505, -1.29472815990448, 0.22276712954044342),
+      "c" -> Array(-0.08456747233867645, 0.5137411952018738, 0.11731560528278351)
     )
 
     val expected = doc.map { sentence =>
diff --git a/mllib/src/test/scala/org/apache/spark/ml/tuning/CrossValidatorSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/tuning/CrossValidatorSuite.scala
index 65972ec79b..60d8bfe38f 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/tuning/CrossValidatorSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/tuning/CrossValidatorSuite.scala
@@ -90,14 +90,20 @@ object CrossValidatorSuite {
 
     override def validateParams(): Unit = require($(inputCol).nonEmpty)
 
-    override def fit(dataset: DataFrame): MyModel = ???
+    override def fit(dataset: DataFrame): MyModel = {
+      throw new UnsupportedOperationException
+    }
 
-    override def transformSchema(schema: StructType): StructType = ???
+    override def transformSchema(schema: StructType): StructType = {
+      throw new UnsupportedOperationException
+    }
   }
 
   class MyEvaluator extends Evaluator {
 
-    override def evaluate(dataset: DataFrame): Double = ???
+    override def evaluate(dataset: DataFrame): Double = {
+      throw new UnsupportedOperationException
+    }
 
     override val uid: String = "eval"
   }
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/api/python/PythonMLLibAPISuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/api/python/PythonMLLibAPISuite.scala
index a629dba8a4..3d362b5ee5 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/api/python/PythonMLLibAPISuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/api/python/PythonMLLibAPISuite.scala
@@ -84,7 +84,7 @@ class PythonMLLibAPISuite extends FunSuite {
 
     val smt = new SparseMatrix(
       3, 3, Array(0, 2, 3, 5), Array(0, 2, 1, 0, 2), Array(0.9, 1.2, 3.4, 5.7, 8.9),
-      isTransposed=true)
+      isTransposed = true)
     val nsmt = SerDe.loads(SerDe.dumps(smt)).asInstanceOf[SparseMatrix]
     assert(smt.toArray === nsmt.toArray)
   }
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala
index c111a78a55..ea40b41bbb 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala
@@ -163,7 +163,7 @@ class NaiveBayesSuite extends FunSuite with MLlibTestSparkContext {
     val theta = Array(
       Array(0.50, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.40), // label 0
       Array(0.02, 0.70, 0.10, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02), // label 1
-      Array(0.02, 0.02, 0.60, 0.02,  0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.30)  // label 2
+      Array(0.02, 0.02, 0.60, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.30)  // label 2
     ).map(_.map(math.log))
 
     val testData = NaiveBayesSuite.generateNaiveBayesInput(
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/classification/SVMSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/classification/SVMSuite.scala
index 6de098b383..90f9cec685 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/classification/SVMSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/classification/SVMSuite.scala
@@ -46,7 +46,7 @@ object SVMSuite {
     nPoints: Int,
     seed: Int): Seq[LabeledPoint] = {
     val rnd = new Random(seed)
-    val weightsMat = new DoubleMatrix(1, weights.length, weights:_*)
+    val weightsMat = new DoubleMatrix(1, weights.length, weights : _*)
     val x = Array.fill[Array[Double]](nPoints)(
         Array.fill[Double](weights.length)(rnd.nextDouble() * 2.0 - 1.0))
     val y = x.map { xi =>
@@ -91,7 +91,7 @@ class SVMSuite extends FunSuite with MLlibTestSparkContext {
     val model = svm.run(testRDD)
 
     val validationData = SVMSuite.generateSVMInput(A, Array[Double](B, C), nPoints, 17)
-    val validationRDD  = sc.parallelize(validationData, 2)
+    val validationRDD = sc.parallelize(validationData, 2)
 
     // Test prediction on RDD.
 
@@ -117,7 +117,7 @@ class SVMSuite extends FunSuite with MLlibTestSparkContext {
     val B = -1.5
     val C = 1.0
 
-    val testData = SVMSuite.generateSVMInput(A, Array[Double](B,C), nPoints, 42)
+    val testData = SVMSuite.generateSVMInput(A, Array[Double](B, C), nPoints, 42)
 
     val testRDD = sc.parallelize(testData, 2)
     testRDD.cache()
@@ -127,8 +127,8 @@ class SVMSuite extends FunSuite with MLlibTestSparkContext {
 
     val model = svm.run(testRDD)
 
-    val validationData = SVMSuite.generateSVMInput(A, Array[Double](B,C), nPoints, 17)
-    val validationRDD  = sc.parallelize(validationData, 2)
+    val validationData = SVMSuite.generateSVMInput(A, Array[Double](B, C), nPoints, 17)
+    val validationRDD = sc.parallelize(validationData, 2)
 
     // Test prediction on RDD.
     validatePrediction(model.predict(validationRDD.map(_.features)).collect(), validationData)
@@ -145,7 +145,7 @@ class SVMSuite extends FunSuite with MLlibTestSparkContext {
     val B = -1.5
     val C = 1.0
 
-    val testData = SVMSuite.generateSVMInput(A, Array[Double](B,C), nPoints, 42)
+    val testData = SVMSuite.generateSVMInput(A, Array[Double](B, C), nPoints, 42)
 
     val initialB = -1.0
     val initialC = -1.0
@@ -159,8 +159,8 @@ class SVMSuite extends FunSuite with MLlibTestSparkContext {
 
     val model = svm.run(testRDD, initialWeights)
 
-    val validationData = SVMSuite.generateSVMInput(A, Array[Double](B,C), nPoints, 17)
-    val validationRDD  = sc.parallelize(validationData,2)
+    val validationData = SVMSuite.generateSVMInput(A, Array[Double](B, C), nPoints, 17)
+    val validationRDD = sc.parallelize(validationData, 2)
 
     // Test prediction on RDD.
     validatePrediction(model.predict(validationRDD.map(_.features)).collect(), validationData)
@@ -177,7 +177,7 @@ class SVMSuite extends FunSuite with MLlibTestSparkContext {
     val B = -1.5
     val C = 1.0
 
-    val testData = SVMSuite.generateSVMInput(A, Array[Double](B,C), nPoints, 42)
+    val testData = SVMSuite.generateSVMInput(A, Array[Double](B, C), nPoints, 42)
     val testRDD = sc.parallelize(testData, 2)
 
     val testRDDInvalid = testRDD.map { lp =>
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/clustering/KMeansSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/clustering/KMeansSuite.scala
index 0f2b26d462..877e6dc699 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/clustering/KMeansSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/clustering/KMeansSuite.scala
@@ -75,7 +75,7 @@ class KMeansSuite extends FunSuite with MLlibTestSparkContext {
     val center = Vectors.dense(1.0, 2.0, 3.0)
 
     // Make sure code runs.
-    var model = KMeans.train(data, k=2, maxIterations=1)
+    var model = KMeans.train(data, k = 2, maxIterations = 1)
     assert(model.clusterCenters.size === 2)
   }
 
@@ -87,7 +87,7 @@ class KMeansSuite extends FunSuite with MLlibTestSparkContext {
       2)
 
     // Make sure code runs.
-    var model = KMeans.train(data, k=3, maxIterations=1)
+    var model = KMeans.train(data, k = 3, maxIterations = 1)
     assert(model.clusterCenters.size === 3)
   }
 
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/clustering/PowerIterationClusteringSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/clustering/PowerIterationClusteringSuite.scala
index 6d6fe6fe46..556842f312 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/clustering/PowerIterationClusteringSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/clustering/PowerIterationClusteringSuite.scala
@@ -94,11 +94,13 @@ class PowerIterationClusteringSuite extends FunSuite with MLlibTestSparkContext
      */
     val similarities = Seq[(Long, Long, Double)](
       (0, 1, 1.0), (0, 2, 1.0), (0, 3, 1.0), (1, 2, 1.0), (2, 3, 1.0))
+    // scalastyle:off
     val expected = Array(
       Array(0.0,     1.0/3.0, 1.0/3.0, 1.0/3.0),
       Array(1.0/2.0,     0.0, 1.0/2.0,     0.0),
       Array(1.0/3.0, 1.0/3.0,     0.0, 1.0/3.0),
       Array(1.0/2.0,     0.0, 1.0/2.0,     0.0))
+    // scalastyle:on
     val w = normalize(sc.parallelize(similarities, 2))
     w.edges.collect().foreach { case Edge(i, j, x) =>
       assert(x ~== expected(i.toInt)(j.toInt) absTol 1e-14)
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/evaluation/RegressionMetricsSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/evaluation/RegressionMetricsSuite.scala
index 670b4c34e6..3aa732474e 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/evaluation/RegressionMetricsSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/evaluation/RegressionMetricsSuite.scala
@@ -26,7 +26,7 @@ class RegressionMetricsSuite extends FunSuite with MLlibTestSparkContext {
 
   test("regression metrics") {
     val predictionAndObservations = sc.parallelize(
-      Seq((2.5,3.0),(0.0,-0.5),(2.0,2.0),(8.0,7.0)), 2)
+      Seq((2.5, 3.0), (0.0, -0.5), (2.0, 2.0), (8.0, 7.0)), 2)
     val metrics = new RegressionMetrics(predictionAndObservations)
     assert(metrics.explainedVariance ~== 0.95717 absTol 1E-5,
       "explained variance regression score mismatch")
@@ -39,7 +39,7 @@ class RegressionMetricsSuite extends FunSuite with MLlibTestSparkContext {
 
   test("regression metrics with complete fitting") {
     val predictionAndObservations = sc.parallelize(
-      Seq((3.0,3.0),(0.0,0.0),(2.0,2.0),(8.0,8.0)), 2)
+      Seq((3.0, 3.0), (0.0, 0.0), (2.0, 2.0), (8.0, 8.0)), 2)
     val metrics = new RegressionMetrics(predictionAndObservations)
     assert(metrics.explainedVariance ~== 1.0 absTol 1E-5,
       "explained variance regression score mismatch")
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/feature/StandardScalerSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/feature/StandardScalerSuite.scala
index 7f94564b2a..1eb991869d 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/feature/StandardScalerSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/feature/StandardScalerSuite.scala
@@ -360,7 +360,7 @@ class StandardScalerSuite extends FunSuite with MLlibTestSparkContext {
     }
     withClue("model needs std and mean vectors to be equal size when both are provided") {
       intercept[IllegalArgumentException] {
-        val model = new StandardScalerModel(Vectors.dense(0.0), Vectors.dense(0.0,1.0))
+        val model = new StandardScalerModel(Vectors.dense(0.0), Vectors.dense(0.0, 1.0))
       }
     }
   }
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrixSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrixSuite.scala
index 949d1c9939..a583361758 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrixSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrixSuite.scala
@@ -57,11 +57,13 @@ class BlockMatrixSuite extends FunSuite with MLlibTestSparkContext {
     val random = new ju.Random()
     // This should generate a 4x4 grid of 1x2 blocks.
     val part0 = GridPartitioner(4, 7, suggestedNumPartitions = 12)
+    // scalastyle:off
     val expected0 = Array(
       Array(0, 0, 4, 4,  8,  8, 12),
       Array(1, 1, 5, 5,  9,  9, 13),
       Array(2, 2, 6, 6, 10, 10, 14),
       Array(3, 3, 7, 7, 11, 11, 15))
+    // scalastyle:on
     for (i <- 0 until 4; j <- 0 until 7) {
       assert(part0.getPartition((i, j)) === expected0(i)(j))
       assert(part0.getPartition((i, j, random.nextInt())) === expected0(i)(j))
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/optimization/GradientDescentSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/optimization/GradientDescentSuite.scala
index 86481c6e66..e110506d57 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/optimization/GradientDescentSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/optimization/GradientDescentSuite.scala
@@ -42,7 +42,7 @@ object GradientDescentSuite {
       offset: Double,
       scale: Double,
       nPoints: Int,
-      seed: Int): Seq[LabeledPoint]  = {
+      seed: Int): Seq[LabeledPoint] = {
     val rnd = new Random(seed)
     val x1 = Array.fill[Double](nPoints)(rnd.nextGaussian())
 
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/optimization/NNLSSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/optimization/NNLSSuite.scala
index 22855e4e8f..bb723fc471 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/optimization/NNLSSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/optimization/NNLSSuite.scala
@@ -68,12 +68,14 @@ class NNLSSuite extends FunSuite {
 
   test("NNLS: nonnegativity constraint active") {
     val n = 5
+    // scalastyle:off
     val ata = new DoubleMatrix(Array(
       Array( 4.377, -3.531, -1.306, -0.139,  3.418),
       Array(-3.531,  4.344,  0.934,  0.305, -2.140),
       Array(-1.306,  0.934,  2.644, -0.203, -0.170),
       Array(-0.139,  0.305, -0.203,  5.883,  1.428),
       Array( 3.418, -2.140, -0.170,  1.428,  4.684)))
+    // scalastyle:on
     val atb = new DoubleMatrix(Array(-1.632, 2.115, 1.094, -1.025, -0.636))
 
     val goodx = Array(0.13025, 0.54506, 0.2874, 0.0, 0.028628)
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/regression/LassoSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/regression/LassoSuite.scala
index c9f5dc069e..71dce50922 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/regression/LassoSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/regression/LassoSuite.scala
@@ -67,11 +67,12 @@ class LassoSuite extends FunSuite with MLlibTestSparkContext {
     assert(weight1 >= -1.60 && weight1 <= -1.40, weight1 + " not in [-1.6, -1.4]")
     assert(weight2 >= -1.0e-3 && weight2 <= 1.0e-3, weight2 + " not in [-0.001, 0.001]")
 
-    val validationData = LinearDataGenerator.generateLinearInput(A, Array[Double](B,C), nPoints, 17)
+    val validationData = LinearDataGenerator
+      .generateLinearInput(A, Array[Double](B, C), nPoints, 17)
       .map { case LabeledPoint(label, features) =>
       LabeledPoint(label, Vectors.dense(1.0 +: features.toArray))
     }
-    val validationRDD  = sc.parallelize(validationData, 2)
+    val validationRDD = sc.parallelize(validationData, 2)
 
     // Test prediction on RDD.
     validatePrediction(model.predict(validationRDD.map(_.features)).collect(), validationData)
@@ -110,11 +111,12 @@ class LassoSuite extends FunSuite with MLlibTestSparkContext {
     assert(weight1 >= -1.60 && weight1 <= -1.40, weight1 + " not in [-1.6, -1.4]")
     assert(weight2 >= -1.0e-3 && weight2 <= 1.0e-3, weight2 + " not in [-0.001, 0.001]")
 
-    val validationData = LinearDataGenerator.generateLinearInput(A, Array[Double](B,C), nPoints, 17)
+    val validationData = LinearDataGenerator
+      .generateLinearInput(A, Array[Double](B, C), nPoints, 17)
       .map { case LabeledPoint(label, features) =>
       LabeledPoint(label, Vectors.dense(1.0 +: features.toArray))
     }
-    val validationRDD  = sc.parallelize(validationData,2)
+    val validationRDD = sc.parallelize(validationData, 2)
 
     // Test prediction on RDD.
     validatePrediction(model.predict(validationRDD.map(_.features)).collect(), validationData)
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 d20a09b4b4..a7e6fce31f 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
@@ -96,11 +96,13 @@ class CorrelationSuite extends FunSuite with MLlibTestSparkContext {
     val X = sc.parallelize(data)
     val defaultMat = Statistics.corr(X)
     val pearsonMat = Statistics.corr(X, "pearson")
+    // scalastyle:off
     val expected = BDM(
       (1.00000000, 0.05564149, Double.NaN, 0.4004714),
       (0.05564149, 1.00000000, Double.NaN, 0.9135959),
       (Double.NaN, Double.NaN, 1.00000000, Double.NaN),
-      (0.40047142, 0.91359586, Double.NaN,1.0000000))
+      (0.40047142, 0.91359586, Double.NaN, 1.0000000))
+    // scalastyle:on
     assert(matrixApproxEqual(defaultMat.toBreeze, expected))
     assert(matrixApproxEqual(pearsonMat.toBreeze, expected))
   }
@@ -108,11 +110,13 @@ class CorrelationSuite extends FunSuite with MLlibTestSparkContext {
   test("corr(X) spearman") {
     val X = sc.parallelize(data)
     val spearmanMat = Statistics.corr(X, "spearman")
+    // scalastyle:off
     val expected = BDM(
       (1.0000000,  0.1054093,  Double.NaN, 0.4000000),
       (0.1054093,  1.0000000,  Double.NaN, 0.9486833),
       (Double.NaN, Double.NaN, 1.00000000, Double.NaN),
       (0.4000000,  0.9486833,  Double.NaN, 1.0000000))
+    // scalastyle:on
     assert(matrixApproxEqual(spearmanMat.toBreeze, expected))
   }
 
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala
index 668fc1d43c..cdece2c174 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala
@@ -168,7 +168,7 @@ class MLUtilsSuite extends FunSuite with MLlibTestSparkContext {
             "Each training+validation set combined should contain all of the data.")
         }
         // K fold cross validation should only have each element in the validation set exactly once
-        assert(foldedRdds.map(_._2).reduce((x,y) => x.union(y)).collect().sorted ===
+        assert(foldedRdds.map(_._2).reduce((x, y) => x.union(y)).collect().sorted ===
           data.collect().sorted)
       }
     }