SPARK-22896 Improvement in String interpolation

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.toString}")
 
     val Row(coeff2: Matrix) = Correlation.corr(df, "features", "spearman").head
-    println("Spearman correlation matrix:\n" + coeff2.toString)
+    println(s"Spearman correlation matrix:\n ${coeff2.toString}")
     // $example off$
 
     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/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

@@ -31,12 +31,11 @@ object QuantileDiscretizerExample {
 
     // $example on$
     val data = Array((0, 18.0), (1, 19.0), (2, 8.0), (3, 5.0), (4, 2.2))
-    val df = spark.createDataFrame(data).toDF("id", "hour")
+    val df = spark.createDataFrame(data).toDF("id", "hour").repartition(1)
     // $example off$
     // 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)
 
     // $example on$
     val discretizer = new QuantileDiscretizer()
@@ -45,7 +44,7 @@ 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()