[SPARK-22896] Improvement in String interpolation

## What changes were proposed in this pull request?

* String interpolation in ml pipeline example has been corrected as per scala standard.

## How was this patch tested?
* manually tested.

Author: chetkhatri <[email protected]>

Closes #20070 from chetkhatri/mllib-chetan-contrib.

examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java

@@ -66,7 +66,7 @@ public static void main(String[] args) {
       .setNumBuckets(3);
 
     Dataset<Row> result = discretizer.fit(df).transform(df);
-    result.show();
+    result.show(false);
     // $example off$
     spark.stop();
   }

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

@@ -60,10 +60,6 @@ object SimpleSkewedGroupByTest {
     pairs1.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)}
-    //                           .collectAsMap)
 
     spark.stop()
   }

examples/src/main/scala/org/apache/spark/examples/graphx/Analytics.scala

@@ -145,9 +145,11 @@ object Analytics extends Logging {
           // TriangleCount requires the graph to be partitioned
           .partitionBy(partitionStrategy.getOrElse(RandomVertexCut)).cache()
         val triangles = TriangleCount.run(graph)
-        println("Triangles: " + triangles.vertices.map {
+        val triangleTypes = triangles.vertices.map {
           case (vid, data) => data.toLong
-        }.reduce(_ + _) / 3)
+        }.reduce(_ + _) / 3
+
+        println(s"Triangles: ${triangleTypes}")
         sc.stop()
 
       case _ =>

examples/src/main/scala/org/apache/spark/examples/graphx/SynthBenchmark.scala

@@ -52,7 +52,7 @@ object SynthBenchmark {
       arg =>
         arg.dropWhile(_ == '-').split('=') match {
           case Array(opt, v) => (opt -> v)
-          case _ => throw new IllegalArgumentException("Invalid argument: " + arg)
+          case _ => throw new IllegalArgumentException(s"Invalid argument: $arg")
         }
     }
 
@@ -76,7 +76,7 @@ object SynthBenchmark {
       case ("sigma", v) => sigma = v.toDouble
       case ("degFile", v) => degFile = v
       case ("seed", v) => seed = v.toInt
-      case (opt, _) => throw new IllegalArgumentException("Invalid option: " + opt)
+      case (opt, _) => throw new IllegalArgumentException(s"Invalid option: $opt")
     }
 
     val conf = new SparkConf()
@@ -86,7 +86,7 @@ object SynthBenchmark {
     val sc = new SparkContext(conf)
 
     // Create the graph
-    println(s"Creating graph...")
+    println("Creating graph...")
     val unpartitionedGraph = GraphGenerators.logNormalGraph(sc, numVertices,
       numEPart.getOrElse(sc.defaultParallelism), mu, sigma, seed)
     // Repartition the graph

examples/src/main/scala/org/apache/spark/examples/ml/ChiSquareTestExample.scala

@@ -52,9 +52,9 @@ object ChiSquareTestExample {
 
     val df = data.toDF("label", "features")
     val chi = ChiSquareTest.test(df, "features", "label").head
-    println("pValues = " + chi.getAs[Vector](0))
-    println("degreesOfFreedom = " + chi.getSeq[Int](1).mkString("[", ",", "]"))
-    println("statistics = " + chi.getAs[Vector](2))
+    println(s"pValues = ${chi.getAs[Vector](0)}")
+    println(s"degreesOfFreedom ${chi.getSeq[Int](1).mkString("[", ",", "]")}")
+    println(s"statistics ${chi.getAs[Vector](2)}")
     // $example off$
 
     spark.stop()

examples/src/main/scala/org/apache/spark/examples/ml/CorrelationExample.scala

@@ -51,10 +51,10 @@ object CorrelationExample {
 
     val df = data.map(Tuple1.apply).toDF("features")
     val Row(coeff1: Matrix) = Correlation.corr(df, "features").head
-    println("Pearson correlation matrix:\n" + coeff1.toString)
+    println(s"Pearson correlation matrix:\n $coeff1")
 
     val Row(coeff2: Matrix) = Correlation.corr(df, "features", "spearman").head
-    println("Spearman correlation matrix:\n" + coeff2.toString)
+    println(s"Spearman correlation matrix:\n $coeff2")
     // $example off$
 
     spark.stop()

examples/src/main/scala/org/apache/spark/examples/ml/DataFrameExample.scala

@@ -47,7 +47,7 @@ object DataFrameExample {
     val parser = new OptionParser[Params]("DataFrameExample") {
       head("DataFrameExample: an example app using DataFrame for ML.")
       opt[String]("input")
-        .text(s"input path to dataframe")
+        .text("input path to dataframe")
         .action((x, c) => c.copy(input = x))
       checkConfig { params =>
         success
@@ -93,7 +93,7 @@ object DataFrameExample {
     // Load the records back.
     println(s"Loading Parquet file with UDT from $outputDir.")
     val newDF = spark.read.parquet(outputDir)
-    println(s"Schema from Parquet:")
+    println("Schema from Parquet:")
     newDF.printSchema()
 
     spark.stop()

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

@@ -83,10 +83,10 @@ object DecisionTreeClassificationExample {
       .setPredictionCol("prediction")
       .setMetricName("accuracy")
     val accuracy = evaluator.evaluate(predictions)
-    println("Test Error = " + (1.0 - accuracy))
+    println(s"Test Error = ${(1.0 - accuracy)}")
 
     val treeModel = model.stages(2).asInstanceOf[DecisionTreeClassificationModel]
-    println("Learned classification tree model:\n" + treeModel.toDebugString)
+    println(s"Learned classification tree model:\n ${treeModel.toDebugString}")
     // $example off$
 
     spark.stop()

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

@@ -73,10 +73,10 @@ object DecisionTreeRegressionExample {
       .setPredictionCol("prediction")
       .setMetricName("rmse")
     val rmse = evaluator.evaluate(predictions)
-    println("Root Mean Squared Error (RMSE) on test data = " + rmse)
+    println(s"Root Mean Squared Error (RMSE) on test data = $rmse")
 
     val treeModel = model.stages(1).asInstanceOf[DecisionTreeRegressionModel]
-    println("Learned regression tree model:\n" + treeModel.toDebugString)
+    println(s"Learned regression tree model:\n ${treeModel.toDebugString}")
     // $example off$
 
     spark.stop()

examples/src/main/scala/org/apache/spark/examples/ml/DeveloperApiExample.scala

@@ -53,7 +53,7 @@ object DeveloperApiExample {
     // Create a LogisticRegression instance. This instance is an Estimator.
     val lr = new MyLogisticRegression()
     // Print out the parameters, documentation, and any default values.
-    println("MyLogisticRegression parameters:\n" + lr.explainParams() + "\n")
+    println(s"MyLogisticRegression parameters:\n ${lr.explainParams()}")
 
     // We may set parameters using setter methods.
     lr.setMaxIter(10)
@@ -169,10 +169,10 @@ private class MyLogisticRegressionModel(
     Vectors.dense(-margin, margin)
   }
 
-  /** Number of classes the label can take. 2 indicates binary classification. */
+  // Number of classes the label can take. 2 indicates binary classification.
   override val numClasses: Int = 2
 
-  /** Number of features the model was trained on. */
+  // Number of features the model was trained on.
   override val numFeatures: Int = coefficients.size
 
   /**

examples/src/main/scala/org/apache/spark/examples/ml/EstimatorTransformerParamExample.scala

@@ -46,7 +46,7 @@ object EstimatorTransformerParamExample {
     // Create a LogisticRegression instance. This instance is an Estimator.
     val lr = new LogisticRegression()
     // Print out the parameters, documentation, and any default values.
-    println("LogisticRegression parameters:\n" + lr.explainParams() + "\n")
+    println(s"LogisticRegression parameters:\n ${lr.explainParams()}\n")
 
     // We may set parameters using setter methods.
     lr.setMaxIter(10)
@@ -58,7 +58,7 @@ object EstimatorTransformerParamExample {
     // we can view the parameters it used during fit().
     // This prints the parameter (name: value) pairs, where names are unique IDs for this
     // LogisticRegression instance.
-    println("Model 1 was fit using parameters: " + model1.parent.extractParamMap)
+    println(s"Model 1 was fit using parameters: ${model1.parent.extractParamMap}")
 
     // We may alternatively specify parameters using a ParamMap,
     // which supports several methods for specifying parameters.
@@ -73,7 +73,7 @@ object EstimatorTransformerParamExample {
     // Now learn a new model using the paramMapCombined parameters.
     // paramMapCombined overrides all parameters set earlier via lr.set* methods.
     val model2 = lr.fit(training, paramMapCombined)
-    println("Model 2 was fit using parameters: " + model2.parent.extractParamMap)
+    println(s"Model 2 was fit using parameters: ${model2.parent.extractParamMap}")
 
     // Prepare test data.
     val test = spark.createDataFrame(Seq(

examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeClassifierExample.scala

@@ -86,10 +86,10 @@ object GradientBoostedTreeClassifierExample {
       .setPredictionCol("prediction")
       .setMetricName("accuracy")
     val accuracy = evaluator.evaluate(predictions)
-    println("Test Error = " + (1.0 - accuracy))
+    println(s"Test Error = ${1.0 - accuracy}")
 
     val gbtModel = model.stages(2).asInstanceOf[GBTClassificationModel]
-    println("Learned classification GBT model:\n" + gbtModel.toDebugString)
+    println(s"Learned classification GBT model:\n ${gbtModel.toDebugString}")
     // $example off$
 
     spark.stop()

examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeRegressorExample.scala

@@ -73,10 +73,10 @@ object GradientBoostedTreeRegressorExample {
       .setPredictionCol("prediction")
       .setMetricName("rmse")
     val rmse = evaluator.evaluate(predictions)
-    println("Root Mean Squared Error (RMSE) on test data = " + rmse)
+    println(s"Root Mean Squared Error (RMSE) on test data = $rmse")
 
     val gbtModel = model.stages(1).asInstanceOf[GBTRegressionModel]
-    println("Learned regression GBT model:\n" + gbtModel.toDebugString)
+    println(s"Learned regression GBT model:\n ${gbtModel.toDebugString}")
     // $example off$
 
     spark.stop()

examples/src/main/scala/org/apache/spark/examples/ml/MulticlassLogisticRegressionWithElasticNetExample.scala

@@ -48,7 +48,7 @@ object MulticlassLogisticRegressionWithElasticNetExample {
 
     // Print the coefficients and intercept for multinomial logistic regression
     println(s"Coefficients: \n${lrModel.coefficientMatrix}")
-    println(s"Intercepts: ${lrModel.interceptVector}")
+    println(s"Intercepts: \n${lrModel.interceptVector}")
     // $example off$
 
     spark.stop()

examples/src/main/scala/org/apache/spark/examples/ml/MultilayerPerceptronClassifierExample.scala

@@ -66,7 +66,7 @@ object MultilayerPerceptronClassifierExample {
     val evaluator = new MulticlassClassificationEvaluator()
       .setMetricName("accuracy")
 
-    println("Test set accuracy = " + evaluator.evaluate(predictionAndLabels))
+    println(s"Test set accuracy = ${evaluator.evaluate(predictionAndLabels)}")
     // $example off$
 
     spark.stop()

examples/src/main/scala/org/apache/spark/examples/ml/NaiveBayesExample.scala

@@ -52,7 +52,7 @@ object NaiveBayesExample {
       .setPredictionCol("prediction")
       .setMetricName("accuracy")
     val accuracy = evaluator.evaluate(predictions)
-    println("Test set accuracy = " + accuracy)
+    println(s"Test set accuracy = $accuracy")
     // $example off$
 
     spark.stop()

examples/src/main/scala/org/apache/spark/examples/ml/QuantileDiscretizerExample.scala

@@ -36,7 +36,7 @@ object QuantileDiscretizerExample {
     // Output of QuantileDiscretizer for such small datasets can depend on the number of
     // partitions. Here we force a single partition to ensure consistent results.
     // Note this is not necessary for normal use cases
-        .repartition(1)
+      .repartition(1)
 
     // $example on$
     val discretizer = new QuantileDiscretizer()
@@ -45,7 +45,7 @@ object QuantileDiscretizerExample {
       .setNumBuckets(3)
 
     val result = discretizer.fit(df).transform(df)
-    result.show()
+    result.show(false)
     // $example off$
 
     spark.stop()

examples/src/main/scala/org/apache/spark/examples/ml/RandomForestClassifierExample.scala

@@ -85,10 +85,10 @@ object RandomForestClassifierExample {
       .setPredictionCol("prediction")
       .setMetricName("accuracy")
     val accuracy = evaluator.evaluate(predictions)
-    println("Test Error = " + (1.0 - accuracy))
+    println(s"Test Error = ${(1.0 - accuracy)}")
 
     val rfModel = model.stages(2).asInstanceOf[RandomForestClassificationModel]
-    println("Learned classification forest model:\n" + rfModel.toDebugString)
+    println(s"Learned classification forest model:\n ${rfModel.toDebugString}")
     // $example off$
 
     spark.stop()

examples/src/main/scala/org/apache/spark/examples/ml/RandomForestRegressorExample.scala

@@ -72,10 +72,10 @@ object RandomForestRegressorExample {
       .setPredictionCol("prediction")
       .setMetricName("rmse")
     val rmse = evaluator.evaluate(predictions)
-    println("Root Mean Squared Error (RMSE) on test data = " + rmse)
+    println(s"Root Mean Squared Error (RMSE) on test data = $rmse")
 
     val rfModel = model.stages(1).asInstanceOf[RandomForestRegressionModel]
-    println("Learned regression forest model:\n" + rfModel.toDebugString)
+    println(s"Learned regression forest model:\n ${rfModel.toDebugString}")
     // $example off$
 
     spark.stop()

examples/src/main/scala/org/apache/spark/examples/ml/VectorIndexerExample.scala

@@ -41,8 +41,8 @@ object VectorIndexerExample {
     val indexerModel = indexer.fit(data)
 
     val categoricalFeatures: Set[Int] = indexerModel.categoryMaps.keys.toSet
-    println(s"Chose ${categoricalFeatures.size} categorical features: " +
-      categoricalFeatures.mkString(", "))
+    println(s"Chose ${categoricalFeatures.size} " +
+      s"categorical features: ${categoricalFeatures.mkString(", ")}")
 
     // Create new column "indexed" with categorical values transformed to indices
     val indexedData = indexerModel.transform(data)

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

@@ -42,9 +42,8 @@ object AssociationRulesExample {
     val results = ar.run(freqItemsets)
 
     results.collect().foreach { rule =>
-      println("[" + rule.antecedent.mkString(",")
-        + "=>"
-        + rule.consequent.mkString(",") + "]," + rule.confidence)
+    println(s"[${rule.antecedent.mkString(",")}=>${rule.consequent.mkString(",")} ]" +
+        s" ${rule.confidence}")
     }
     // $example off$
 
@@ -53,3 +52,4 @@ object AssociationRulesExample {
 
 }
 // scalastyle:on println
+

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)} :")
       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")