All examples under spark scala - String interpolation has implemented

examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassificationMetricsExample.scala

@@ -86,7 +86,7 @@ object BinaryClassificationMetricsExample {
 
     // AUPRC
     val auPRC = metrics.areaUnderPR
-    println("Area under precision-recall curve = " + auPRC)
+    println(s"Area under precision-recall curve = $auPRC")
 
     // Compute thresholds used in ROC and PR curves
     val thresholds = precision.map(_._1)
@@ -96,7 +96,7 @@ object BinaryClassificationMetricsExample {
 
     // AUROC
     val auROC = metrics.areaUnderROC
-    println("Area under ROC = " + auROC)
+    println(s"Area under ROC = $auROC")
     // $example off$
     sc.stop()
   }

examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala

@@ -55,8 +55,8 @@ object DecisionTreeClassificationExample {
       (point.label, prediction)
     }
     val testErr = labelAndPreds.filter(r => r._1 != r._2).count().toDouble / testData.count()
-    println("Test Error = " + testErr)
-    println("Learned classification tree model:\n" + model.toDebugString)
+    println(s"Test Error = $testErr")
+    println(s"Learned classification tree model:\n ${model.toDebugString}")
 
     // Save and load model
     model.save(sc, "target/tmp/myDecisionTreeClassificationModel")

examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRegressionExample.scala

@@ -54,8 +54,8 @@ object DecisionTreeRegressionExample {
       (point.label, prediction)
     }
     val testMSE = labelsAndPredictions.map{ case (v, p) => math.pow(v - p, 2) }.mean()
-    println("Test Mean Squared Error = " + testMSE)
-    println("Learned regression tree model:\n" + model.toDebugString)
+    println(s"Test Mean Squared Error = $testMSE")
+    println(s"Learned regression tree model:\n ${model.toDebugString}")
 
     // Save and load model
     model.save(sc, "target/tmp/myDecisionTreeRegressionModel")

examples/src/main/scala/org/apache/spark/examples/mllib/FPGrowthExample.scala

@@ -74,7 +74,7 @@ object FPGrowthExample {
     println(s"Number of frequent itemsets: ${model.freqItemsets.count()}")
 
     model.freqItemsets.collect().foreach { itemset =>
-      println(itemset.items.mkString("[", ",", "]") + ", " + itemset.freq)
+      println(s"${itemset.items.mkString("[", ",", "]")}, ${itemset.freq}")
     }
 
     sc.stop()

examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingClassificationExample.scala

@@ -54,8 +54,8 @@ object GradientBoostingClassificationExample {
       (point.label, prediction)
     }
     val testErr = labelAndPreds.filter(r => r._1 != r._2).count.toDouble / testData.count()
-    println("Test Error = " + testErr)
-    println("Learned classification GBT model:\n" + model.toDebugString)
+    println(s"Test Error = $testErr")
+    println(s"Learned classification GBT model:\n ${model.toDebugString}")
 
     // Save and load model
     model.save(sc, "target/tmp/myGradientBoostingClassificationModel")

examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingRegressionExample.scala

@@ -53,8 +53,8 @@ object GradientBoostingRegressionExample {
       (point.label, prediction)
     }
     val testMSE = labelsAndPredictions.map{ case(v, p) => math.pow((v - p), 2)}.mean()
-    println("Test Mean Squared Error = " + testMSE)
-    println("Learned regression GBT model:\n" + model.toDebugString)
+    println(s"Test Mean Squared Error = $testMSE")
+    println(s"Learned regression GBT model:\n ${model.toDebugString}")
 
     // Save and load model
     model.save(sc, "target/tmp/myGradientBoostingRegressionModel")

examples/src/main/scala/org/apache/spark/examples/mllib/HypothesisTestingExample.scala

@@ -68,7 +68,7 @@ object HypothesisTestingExample {
     // against the label.
     val featureTestResults: Array[ChiSqTestResult] = Statistics.chiSqTest(obs)
     featureTestResults.zipWithIndex.foreach { case (k, v) =>
-      println("Column " + (v + 1).toString + ":")
+      println(s"Column ${(v + 1).toString} :")
       println(k)
     }  // summary of the test
     // $example off$

examples/src/main/scala/org/apache/spark/examples/mllib/IsotonicRegressionExample.scala

@@ -56,7 +56,7 @@ object IsotonicRegressionExample {
 
     // Calculate mean squared error between predicted and real labels.
     val meanSquaredError = predictionAndLabel.map { case (p, l) => math.pow((p - l), 2) }.mean()
-    println("Mean Squared Error = " + meanSquaredError)
+    println(s"Mean Squared Error = $meanSquaredError")
 
     // Save and load model
     model.save(sc, "target/tmp/myIsotonicRegressionModel")

examples/src/main/scala/org/apache/spark/examples/mllib/KMeansExample.scala

@@ -43,7 +43,7 @@ object KMeansExample {
 
     // Evaluate clustering by computing Within Set Sum of Squared Errors
     val WSSSE = clusters.computeCost(parsedData)
-    println("Within Set Sum of Squared Errors = " + WSSSE)
+    println(s"Within Set Sum of Squared Errors = $WSSSE")
 
     // Save and load model
     clusters.save(sc, "target/org/apache/spark/KMeansExample/KMeansModel")

examples/src/main/scala/org/apache/spark/examples/mllib/LBFGSExample.scala

@@ -82,7 +82,7 @@ object LBFGSExample {
 
     println("Loss of each step in training process")
     loss.foreach(println)
-    println("Area under ROC = " + auROC)
+    println(s"Area under ROC = $auROC")
     // $example off$
 
     sc.stop()

examples/src/main/scala/org/apache/spark/examples/mllib/LatentDirichletAllocationExample.scala

@@ -42,11 +42,11 @@ object LatentDirichletAllocationExample {
     val ldaModel = new LDA().setK(3).run(corpus)
 
     // Output topics. Each is a distribution over words (matching word count vectors)
-    println("Learned topics (as distributions over vocab of " + ldaModel.vocabSize + " words):")
+    println(s"Learned topics (as distributions over vocab of ${ldaModel.vocabSize} words):")
     val topics = ldaModel.topicsMatrix
     for (topic <- Range(0, 3)) {
-      print("Topic " + topic + ":")
-      for (word <- Range(0, ldaModel.vocabSize)) { print(" " + topics(word, topic)); }
+      print(s"Topic $topic :")
+      for (word <- Range(0, ldaModel.vocabSize)) { print(s" ${topics(word, topic)}") }
       println()
     }
 

examples/src/main/scala/org/apache/spark/examples/mllib/LinearRegressionWithSGDExample.scala

@@ -52,7 +52,7 @@ object LinearRegressionWithSGDExample {
       (point.label, prediction)
     }
     val MSE = valuesAndPreds.map{ case(v, p) => math.pow((v - p), 2) }.mean()
-    println("training Mean Squared Error = " + MSE)
+    println(s"training Mean Squared Error $MSE")
 
     // Save and load model
     model.save(sc, "target/tmp/scalaLinearRegressionWithSGDModel")

examples/src/main/scala/org/apache/spark/examples/mllib/PCAExample.scala

@@ -65,8 +65,8 @@ object PCAExample {
     val MSE = valuesAndPreds.map { case (v, p) => math.pow((v - p), 2) }.mean()
     val MSE_pca = valuesAndPreds_pca.map { case (v, p) => math.pow((v - p), 2) }.mean()
 
-    println("Mean Squared Error = " + MSE)
-    println("PCA Mean Squared Error = " + MSE_pca)
+    println(s"Mean Squared Error = $MSE")
+    println(s"PCA Mean Squared Error = $MSE_pca")
     // $example off$
 
     sc.stop()

examples/src/main/scala/org/apache/spark/examples/mllib/PMMLModelExportExample.scala

@@ -41,7 +41,7 @@ object PMMLModelExportExample {
     val clusters = KMeans.train(parsedData, numClusters, numIterations)
 
     // Export to PMML to a String in PMML format
-    println("PMML Model:\n" + clusters.toPMML)
+    println(s"PMML Model:\n ${clusters.toPMML}")
 
     // Export the model to a local file in PMML format
     clusters.toPMML("/tmp/kmeans.xml")

examples/src/main/scala/org/apache/spark/examples/mllib/PrefixSpanExample.scala

@@ -42,8 +42,8 @@ object PrefixSpanExample {
     val model = prefixSpan.run(sequences)
     model.freqSequences.collect().foreach { freqSequence =>
       println(
-        freqSequence.sequence.map(_.mkString("[", ", ", "]")).mkString("[", ", ", "]") +
-          ", " + freqSequence.freq)
+        s"${freqSequence.sequence.map(_.mkString("[", ", ", "]")).mkString("[", ", ", "]")}," +
+          s" ${freqSequence.freq}")
     }
     // $example off$
 

examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala

@@ -55,8 +55,8 @@ object RandomForestClassificationExample {
       (point.label, prediction)
     }
     val testErr = labelAndPreds.filter(r => r._1 != r._2).count.toDouble / testData.count()
-    println("Test Error = " + testErr)
-    println("Learned classification forest model:\n" + model.toDebugString)
+    println(s"Test Error = $testErr")
+    println(s"Learned classification forest model:\n ${model.toDebugString}")
 
     // Save and load model
     model.save(sc, "target/tmp/myRandomForestClassificationModel")

examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestRegressionExample.scala

@@ -55,8 +55,8 @@ object RandomForestRegressionExample {
       (point.label, prediction)
     }
     val testMSE = labelsAndPredictions.map{ case(v, p) => math.pow((v - p), 2)}.mean()
-    println("Test Mean Squared Error = " + testMSE)
-    println("Learned regression forest model:\n" + model.toDebugString)
+    println(s"Test Mean Squared Error = $testMSE")
+    println(s"Learned regression forest model:\n ${model.toDebugString}")
 
     // Save and load model
     model.save(sc, "target/tmp/myRandomForestRegressionModel")

examples/src/main/scala/org/apache/spark/examples/mllib/RecommendationExample.scala

@@ -56,7 +56,7 @@ object RecommendationExample {
       val err = (r1 - r2)
       err * err
     }.mean()
-    println("Mean Squared Error = " + MSE)
+    println(s"Mean Squared Error = $MSE")
 
     // Save and load model
     model.save(sc, "target/tmp/myCollaborativeFilter")

examples/src/main/scala/org/apache/spark/examples/mllib/SVMWithSGDExample.scala

@@ -57,7 +57,7 @@ object SVMWithSGDExample {
     val metrics = new BinaryClassificationMetrics(scoreAndLabels)
     val auROC = metrics.areaUnderROC()
 
-    println("Area under ROC = " + auROC)
+    println(s"Area under ROC = $auROC")
 
     // Save and load model
     model.save(sc, "target/tmp/scalaSVMWithSGDModel")

examples/src/main/scala/org/apache/spark/examples/mllib/SimpleFPGrowth.scala

@@ -42,15 +42,13 @@ object SimpleFPGrowth {
     val model = fpg.run(transactions)
 
     model.freqItemsets.collect().foreach { itemset =>
-      println(itemset.items.mkString("[", ",", "]") + ", " + itemset.freq)
+      println(s"${itemset.items.mkString("[", ",", "]")},${itemset.freq}")
     }
 
     val minConfidence = 0.8
     model.generateAssociationRules(minConfidence).collect().foreach { rule =>
-      println(
-        rule.antecedent.mkString("[", ",", "]")
-          + " => " + rule.consequent .mkString("[", ",", "]")
-          + ", " + rule.confidence)
+      println(s"${rule.antecedent.mkString("[", ",", "]")}=> " +
+        s"${rule.consequent .mkString("[", ",", "]")},${rule.confidence}")
     }
     // $example off$
 

examples/src/main/scala/org/apache/spark/examples/mllib/StratifiedSamplingExample.scala

@@ -41,10 +41,10 @@ object StratifiedSamplingExample {
     val exactSample = data.sampleByKeyExact(withReplacement = false, fractions = fractions)
     // $example off$
 
-    println("approxSample size is " + approxSample.collect().size.toString)
+    println(s"approxSample size is ${approxSample.collect().size.toString}")
     approxSample.collect().foreach(println)
 
-    println("exactSample its size is " + exactSample.collect().size.toString)
+    println(s"exactSample its size is ${exactSample.collect().size.toString}")
     exactSample.collect().foreach(println)
 
     sc.stop()

examples/src/main/scala/org/apache/spark/examples/mllib/TallSkinnyPCA.scala

@@ -54,7 +54,7 @@ object TallSkinnyPCA {
     // Compute principal components.
     val pc = mat.computePrincipalComponents(mat.numCols().toInt)
 
-    println("Principal components are:\n" + pc)
+    println(s"Principal components are:\n $pc")
 
     sc.stop()
   }

examples/src/main/scala/org/apache/spark/examples/mllib/TallSkinnySVD.scala

@@ -54,7 +54,7 @@ object TallSkinnySVD {
     // Compute SVD.
     val svd = mat.computeSVD(mat.numCols().toInt)
 
-    println("Singular values are " + svd.s)
+    println(s"Singular values are ${svd.s}")
 
     sc.stop()
   }

examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala

@@ -82,9 +82,9 @@ class CustomReceiver(host: String, port: Int)
    var socket: Socket = null
    var userInput: String = null
    try {
-     logInfo("Connecting to " + host + ":" + port)
+     logInfo(s"Connecting to $host $port")
      socket = new Socket(host, port)
-     logInfo("Connected to " + host + ":" + port)
+     logInfo(s"Connected to $host : $port")
      val reader = new BufferedReader(
        new InputStreamReader(socket.getInputStream(), StandardCharsets.UTF_8))
      userInput = reader.readLine()
@@ -98,7 +98,7 @@ class CustomReceiver(host: String, port: Int)
      restart("Trying to connect again")
    } catch {
      case e: java.net.ConnectException =>
-       restart("Error connecting to " + host + ":" + port, e)
+       restart(s"Error connecting to $host : $port", e)
      case t: Throwable =>
        restart("Error receiving data", t)
    }

examples/src/main/scala/org/apache/spark/examples/streaming/RawNetworkGrep.scala

@@ -54,7 +54,7 @@ object RawNetworkGrep {
       ssc.rawSocketStream[String](host, port, StorageLevel.MEMORY_ONLY_SER_2)).toArray
     val union = ssc.union(rawStreams)
     union.filter(_.contains("the")).count().foreachRDD(r =>
-      println("Grep count: " + r.collect().mkString))
+      println(s"Grep count: ${r.collect().mkString}"))
     ssc.start()
     ssc.awaitTermination()
   }

examples/src/main/scala/org/apache/spark/examples/streaming/RecoverableNetworkWordCount.scala

@@ -130,18 +130,18 @@ object RecoverableNetworkWordCount {
           true
         }
       }.collect().mkString("[", ", ", "]")
-      val output = "Counts at time " + time + " " + counts
+      val output = s"Counts at time $time $counts"
       println(output)
-      println("Dropped " + droppedWordsCounter.value + " word(s) totally")
-      println("Appending to " + outputFile.getAbsolutePath)
+      println(s"Dropped ${droppedWordsCounter.value} word(s) totally")
+      println(s"Appending to ${outputFile.getAbsolutePath}")
       Files.append(output + "\n", outputFile, Charset.defaultCharset())
     }
     ssc
   }
 
   def main(args: Array[String]) {
     if (args.length != 4) {
-      System.err.println("Your arguments were " + args.mkString("[", ", ", "]"))
+      System.err.println(s"Your arguments were ${args.mkString("[", ", ", "]")}")
       System.err.println(
         """
           |Usage: RecoverableNetworkWordCount <hostname> <port> <checkpoint-directory>

examples/src/main/scala/org/apache/spark/examples/streaming/clickstream/PageViewGenerator.scala

@@ -90,13 +90,13 @@ object PageViewGenerator {
     val viewsPerSecond = args(1).toFloat
     val sleepDelayMs = (1000.0 / viewsPerSecond).toInt
     val listener = new ServerSocket(port)
-    println("Listening on port: " + port)
+    println(s"Listening on port: $port")
 
     while (true) {
       val socket = listener.accept()
       new Thread() {
         override def run(): Unit = {
-          println("Got client connected from: " + socket.getInetAddress)
+          println(s"Got client connected from: ${socket.getInetAddress}")
           val out = new PrintWriter(socket.getOutputStream(), true)
 
           while (true) {

examples/src/main/scala/org/apache/spark/examples/streaming/clickstream/PageViewStream.scala

@@ -104,8 +104,8 @@ object PageViewStream {
           .foreachRDD((rdd, time) => rdd.join(userList)
             .map(_._2._2)
             .take(10)
-            .foreach(u => println("Saw user %s at time %s".format(u, time))))
-      case _ => println("Invalid metric entered: " + metric)
+            .foreach(u => println(s"Saw user $u at time $time")))
+      case _ => println(s"Invalid metric entered: $metric")
     }
 
     ssc.start()