SPARK-22830 Scala Coding style has been improved in Spark Examples

examples/src/main/scala/org/apache/spark/examples/BroadcastTest.scala

@@ -42,7 +42,7 @@ object BroadcastTest {
     val arr1 = (0 until num).toArray
 
     for (i <- 0 until 3) {
-      println("Iteration " + i)
+      println(s"Iteration ${i}")
       println("===========")
       val startTime = System.nanoTime
       val barr1 = sc.broadcast(arr1)

examples/src/main/scala/org/apache/spark/examples/DFSReadWriteTest.scala

@@ -49,12 +49,10 @@ object DFSReadWriteTest {
   }
 
   private def printUsage(): Unit = {
-    val usage: String = "DFS Read-Write Test\n" +
-    "\n" +
-    "Usage: localFile dfsDir\n" +
-    "\n" +
-    "localFile - (string) local file to use in test\n" +
-    "dfsDir - (string) DFS directory for read/write tests\n"
+    val usage = s"""DFS Read-Write Test 
+    Usage: localFile dfsDir
+    localFile - (string) local file to use in test
+    dfsDir - (string) DFS directory for read/write tests"""
 
     println(usage)
   }
@@ -69,13 +67,13 @@ object DFSReadWriteTest {
 
     localFilePath = new File(args(i))
     if (!localFilePath.exists) {
-      System.err.println("Given path (" + args(i) + ") does not exist.\n")
+      System.err.println(s"Given path (${args(i)}) does not exist")
       printUsage()
       System.exit(1)
     }
 
     if (!localFilePath.isFile) {
-      System.err.println("Given path (" + args(i) + ") is not a file.\n")
+      System.err.println(s"Given path (${args(i)}) is not a file")
       printUsage()
       System.exit(1)
     }
@@ -97,22 +95,22 @@ object DFSReadWriteTest {
   def main(args: Array[String]): Unit = {
     parseArgs(args)
 
-    println("Performing local word count")
+    println(s"Performing local word count")
     val fileContents = readFile(localFilePath.toString())
     val localWordCount = runLocalWordCount(fileContents)
 
-    println("Creating SparkSession")
+    println(s"Creating SparkSession")
     val spark = SparkSession
       .builder
       .appName("DFS Read Write Test")
       .getOrCreate()
 
-    println("Writing local file to DFS")
-    val dfsFilename = dfsDirPath + "/dfs_read_write_test"
+    println(s"Writing local file to DFS")
+    val dfsFilename = s"${dfsDirPath}/dfs_read_write_test"
     val fileRDD = spark.sparkContext.parallelize(fileContents)
     fileRDD.saveAsTextFile(dfsFilename)
 
-    println("Reading file from DFS and running Word Count")
+    println(s"Reading file from DFS and running Word Count")
     val readFileRDD = spark.sparkContext.textFile(dfsFilename)
 
     val dfsWordCount = readFileRDD
@@ -127,11 +125,11 @@ object DFSReadWriteTest {
     spark.stop()
 
     if (localWordCount == dfsWordCount) {
-      println(s"Success! Local Word Count ($localWordCount) " +
-        s"and DFS Word Count ($dfsWordCount) agree.")
+      println(s"Success! Local Word Count ($localWordCount) 
+                and DFS Word Count ($dfsWordCount) agree.")
     } else {
-      println(s"Failure! Local Word Count ($localWordCount) " +
-        s"and DFS Word Count ($dfsWordCount) disagree.")
+      println(s"Failure! Local Word Count ($localWordCount) 
+                and DFS Word Count ($dfsWordCount) disagree.")
     }
 
   }

examples/src/main/scala/org/apache/spark/examples/DriverSubmissionTest.scala

@@ -29,18 +29,18 @@ import org.apache.spark.util.Utils
 object DriverSubmissionTest {
   def main(args: Array[String]) {
     if (args.length < 1) {
-      println("Usage: DriverSubmissionTest <seconds-to-sleep>")
+      println(s"Usage: DriverSubmissionTest <seconds-to-sleep>")
       System.exit(0)
     }
     val numSecondsToSleep = args(0).toInt
 
     val env = System.getenv()
     val properties = Utils.getSystemProperties
 
-    println("Environment variables containing SPARK_TEST:")
+    println(s"Environment variables containing SPARK_TEST:")
     env.asScala.filter { case (k, _) => k.contains("SPARK_TEST")}.foreach(println)
 
-    println("System properties containing spark.test:")
+    println(s"System properties containing spark.test:")
     properties.filter { case (k, _) => k.toString.contains("spark.test") }.foreach(println)
 
     for (i <- 1 until numSecondsToSleep) {

examples/src/main/scala/org/apache/spark/examples/HdfsTest.scala

@@ -26,7 +26,7 @@ object HdfsTest {
   /** Usage: HdfsTest [file] */
   def main(args: Array[String]) {
     if (args.length < 1) {
-      System.err.println("Usage: HdfsTest <file>")
+      System.err.println(s"Usage: HdfsTest <file>")
       System.exit(1)
     }
     val spark = SparkSession
@@ -39,7 +39,7 @@ object HdfsTest {
       val start = System.currentTimeMillis()
       for (x <- mapped) { x + 2 }
       val end = System.currentTimeMillis()
-      println("Iteration " + iter + " took " + (end-start) + " ms")
+      println(s"Iteration ${iter} took ${(end-start)} ${ms}")
     }
     spark.stop()
   }

examples/src/main/scala/org/apache/spark/examples/LocalALS.scala

@@ -95,7 +95,7 @@ object LocalALS {
 
   def showWarning() {
     System.err.println(
-      """WARN: This is a naive implementation of ALS and is given as an example!
+      s"""WARN: This is a naive implementation of ALS and is given as an example!
         |Please use org.apache.spark.ml.recommendation.ALS
         |for more conventional use.
       """.stripMargin)
@@ -110,7 +110,7 @@ object LocalALS {
         F = f.toInt
         ITERATIONS = iters.toInt
       case _ =>
-        System.err.println("Usage: LocalALS <M> <U> <F> <iters>")
+        System.err.println(s"Usage: LocalALS <M> <U> <F> <iters>")
         System.exit(1)
     }
 
@@ -129,8 +129,7 @@ object LocalALS {
       println(s"Iteration $iter:")
       ms = (0 until M).map(i => updateMovie(i, ms(i), us, R)).toArray
       us = (0 until U).map(j => updateUser(j, us(j), ms, R)).toArray
-      println("RMSE = " + rmse(R, ms, us))
-      println()
+      println(s"RMSE = ${rmse(R, ms, us)}")
     }
   }
 

examples/src/main/scala/org/apache/spark/examples/LocalFileLR.scala

@@ -41,7 +41,7 @@ object LocalFileLR {
 
   def showWarning() {
     System.err.println(
-      """WARN: This is a naive implementation of Logistic Regression and is given as an example!
+      s"""WARN: This is a naive implementation of Logistic Regression and is given as an example!
         |Please use org.apache.spark.ml.classification.LogisticRegression
         |for more conventional use.
       """.stripMargin)
@@ -58,10 +58,10 @@ object LocalFileLR {
 
     // Initialize w to a random value
     val w = DenseVector.fill(D) {2 * rand.nextDouble - 1}
-    println("Initial w: " + w)
+    println(s"Initial w: ${w}")
 
     for (i <- 1 to ITERATIONS) {
-      println("On iteration " + i)
+      println(s"On iteration ${i}")
       val gradient = DenseVector.zeros[Double](D)
       for (p <- points) {
         val scale = (1 / (1 + math.exp(-p.y * (w.dot(p.x)))) - 1) * p.y
@@ -71,7 +71,7 @@ object LocalFileLR {
     }
 
     fileSrc.close()
-    println("Final w: " + w)
+    println(s"Final w: ${w}")
   }
 }
 // scalastyle:on println

examples/src/main/scala/org/apache/spark/examples/LocalKMeans.scala

@@ -64,7 +64,7 @@ object LocalKMeans {
 
   def showWarning() {
     System.err.println(
-      """WARN: This is a naive implementation of KMeans Clustering and is given as an example!
+      s"""WARN: This is a naive implementation of KMeans Clustering and is given as an example!
         |Please use org.apache.spark.ml.clustering.KMeans
         |for more conventional use.
       """.stripMargin)
@@ -88,7 +88,7 @@ object LocalKMeans {
       kPoints.put(i, iter.next())
     }
 
-    println("Initial centers: " + kPoints)
+    println(s"Initial centers: ${kPoints}")
 
     while(tempDist > convergeDist) {
       val closest = data.map (p => (closestPoint(p, kPoints), (p, 1)))
@@ -114,7 +114,7 @@ object LocalKMeans {
       }
     }
 
-    println("Final centers: " + kPoints)
+    println(s"Final centers: ${kPoints}")
   }
 }
 // scalastyle:on println

examples/src/main/scala/org/apache/spark/examples/LocalLR.scala

@@ -48,7 +48,7 @@ object LocalLR {
 
   def showWarning() {
     System.err.println(
-      """WARN: This is a naive implementation of Logistic Regression and is given as an example!
+      s"""WARN: This is a naive implementation of Logistic Regression and is given as an example!
         |Please use org.apache.spark.ml.classification.LogisticRegression
         |for more conventional use.
       """.stripMargin)
@@ -61,10 +61,10 @@ object LocalLR {
     val data = generateData
     // Initialize w to a random value
     val w = DenseVector.fill(D) {2 * rand.nextDouble - 1}
-    println("Initial w: " + w)
+    println(s"Initial w: ${w}")
 
     for (i <- 1 to ITERATIONS) {
-      println("On iteration " + i)
+      println(s"On iteration ${i}")
       val gradient = DenseVector.zeros[Double](D)
       for (p <- data) {
         val scale = (1 / (1 + math.exp(-p.y * (w.dot(p.x)))) - 1) * p.y
@@ -73,7 +73,7 @@ object LocalLR {
       w -= gradient
     }
 
-    println("Final w: " + w)
+    println(s"Final w: ${w}")
   }
 }
 // scalastyle:on println

examples/src/main/scala/org/apache/spark/examples/LocalPi.scala

@@ -28,7 +28,7 @@ object LocalPi {
       val y = random * 2 - 1
       if (x*x + y*y <= 1) count += 1
     }
-    println("Pi is roughly " + 4 * count / 100000.0)
+    println(s"Pi is roughly ${4 * count / 100000.0}")
   }
 }
 // scalastyle:on println

examples/src/main/scala/org/apache/spark/examples/LogQuery.scala

@@ -27,7 +27,7 @@ import org.apache.spark.{SparkConf, SparkContext}
  */
 object LogQuery {
   val exampleApacheLogs = List(
-    """10.10.10.10 - "FRED" [18/Jan/2013:17:56:07 +1100] "GET http://images.com/2013/Generic.jpg
+    s"""10.10.10.10 - "FRED" [18/Jan/2013:17:56:07 +1100] "GET http://images.com/2013/Generic.jpg
       | HTTP/1.1" 304 315 "http://referall.com/" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1;
       | GTB7.4; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; .NET CLR 3.0.04506.648; .NET CLR
       | 3.5.21022; .NET CLR 3.0.4506.2152; .NET CLR 1.0.3705; .NET CLR 1.1.4322; .NET CLR

examples/src/main/scala/org/apache/spark/examples/SimpleSkewedGroupByTest.scala

@@ -59,7 +59,7 @@ object SimpleSkewedGroupByTest {
     // Enforce that everything has been calculated and in cache
     pairs1.count
 
-    println("RESULT: " + pairs1.groupByKey(numReducers).count)
+    println(s"RESULT: ${pairs1.groupByKey(numReducers).count}")
     // Print how many keys each reducer got (for debugging)
     // println("RESULT: " + pairs1.groupByKey(numReducers)
     //                           .map{case (k,v) => (k, v.size)}

examples/src/main/scala/org/apache/spark/examples/SparkALS.scala

@@ -80,7 +80,7 @@ object SparkALS {
 
   def showWarning() {
     System.err.println(
-      """WARN: This is a naive implementation of ALS and is given as an example!
+      s"""WARN: This is a naive implementation of ALS and is given as an example!
         |Please use org.apache.spark.ml.recommendation.ALS
         |for more conventional use.
       """.stripMargin)
@@ -100,7 +100,7 @@ object SparkALS {
         ITERATIONS = iters.getOrElse("5").toInt
         slices = slices_.getOrElse("2").toInt
       case _ =>
-        System.err.println("Usage: SparkALS [M] [U] [F] [iters] [partitions]")
+        System.err.println(s"Usage: SparkALS [M] [U] [F] [iters] [partitions]")
         System.exit(1)
     }
 
@@ -135,10 +135,8 @@ object SparkALS {
                 .map(i => update(i, usb.value(i), msb.value, Rc.value.transpose()))
                 .collect()
       usb = sc.broadcast(us) // Re-broadcast us because it was updated
-      println("RMSE = " + rmse(R, ms, us))
-      println()
+      println(s"RMSE = ${rmse(R, ms, us)}")
     }
-
     spark.stop()
   }
 

examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala

@@ -51,7 +51,7 @@ object SparkHdfsLR {
 
   def showWarning() {
     System.err.println(
-      """WARN: This is a naive implementation of Logistic Regression and is given as an example!
+      s"""WARN: This is a naive implementation of Logistic Regression and is given as an example!
         |Please use org.apache.spark.ml.classification.LogisticRegression
         |for more conventional use.
       """.stripMargin)
@@ -60,7 +60,7 @@ object SparkHdfsLR {
   def main(args: Array[String]) {
 
     if (args.length < 2) {
-      System.err.println("Usage: SparkHdfsLR <file> <iters>")
+      System.err.println(s"Usage: SparkHdfsLR <file> <iters>")
       System.exit(1)
     }
 
@@ -79,17 +79,17 @@ object SparkHdfsLR {
 
     // Initialize w to a random value
     val w = DenseVector.fill(D) {2 * rand.nextDouble - 1}
-    println("Initial w: " + w)
+    println(s"Initial w: ${w}")
 
     for (i <- 1 to ITERATIONS) {
-      println("On iteration " + i)
+      println(s"On iteration ${i}")
       val gradient = points.map { p =>
         p.x * (1 / (1 + exp(-p.y * (w.dot(p.x)))) - 1) * p.y
       }.reduce(_ + _)
       w -= gradient
     }
 
-    println("Final w: " + w)
+    println(s"Final w: ${w}")
     spark.stop()
   }
 }

examples/src/main/scala/org/apache/spark/examples/SparkKMeans.scala

@@ -51,7 +51,7 @@ object SparkKMeans {
 
   def showWarning() {
     System.err.println(
-      """WARN: This is a naive implementation of KMeans Clustering and is given as an example!
+      s"""WARN: This is a naive implementation of KMeans Clustering and is given as an example!
         |Please use org.apache.spark.ml.clustering.KMeans
         |for more conventional use.
       """.stripMargin)
@@ -60,7 +60,7 @@ object SparkKMeans {
   def main(args: Array[String]) {
 
     if (args.length < 3) {
-      System.err.println("Usage: SparkKMeans <file> <k> <convergeDist>")
+      System.err.println(s"Usage: SparkKMeans <file> <k> <convergeDist>")
       System.exit(1)
     }
 
@@ -95,10 +95,10 @@ object SparkKMeans {
       for (newP <- newPoints) {
         kPoints(newP._1) = newP._2
       }
-      println("Finished iteration (delta = " + tempDist + ")")
+      println(s"Finished iteration (delta = ${tempDist})")
     }
 
-    println("Final centers:")
+    println(s"Final centers:")
     kPoints.foreach(println)
     spark.stop()
   }

examples/src/main/scala/org/apache/spark/examples/SparkLR.scala

@@ -53,7 +53,7 @@ object SparkLR {
 
   def showWarning() {
     System.err.println(
-      """WARN: This is a naive implementation of Logistic Regression and is given as an example!
+      s"""WARN: This is a naive implementation of Logistic Regression and is given as an example!
         |Please use org.apache.spark.ml.classification.LogisticRegression
         |for more conventional use.
       """.stripMargin)
@@ -73,17 +73,17 @@ object SparkLR {
 
     // Initialize w to a random value
     val w = DenseVector.fill(D) {2 * rand.nextDouble - 1}
-    println("Initial w: " + w)
+    println(s"Initial w: ${w}")
 
     for (i <- 1 to ITERATIONS) {
-      println("On iteration " + i)
+      println(s"On iteration ${i}")
       val gradient = points.map { p =>
         p.x * (1 / (1 + exp(-p.y * (w.dot(p.x)))) - 1) * p.y
       }.reduce(_ + _)
       w -= gradient
     }
 
-    println("Final w: " + w)
+    println(s"Final w: ${w}")
 
     spark.stop()
   }