[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.

(cherry picked from commit 9a2b65a)
Signed-off-by: Sean Owen <[email protected]>

Author: chetkhatri

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
 
   /**