[SPARK-15031][SPARK-15134][EXAMPLE][DOC] Use SparkSession and update indent in examples

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

@@ -32,7 +32,9 @@
 public class JavaDecisionTreeClassificationExample {
   public static void main(String[] args) {
     SparkSession spark = SparkSession
-      .builder().appName("JavaDecisionTreeClassificationExample").getOrCreate();
+      .builder()
+      .appName("JavaDecisionTreeClassificationExample")
+      .getOrCreate();
 
     // $example on$
     // Load the data stored in LIBSVM format as a DataFrame.
@@ -52,10 +54,10 @@ public static void main(String[] args) {
     VectorIndexerModel featureIndexer = new VectorIndexer()
       .setInputCol("features")
       .setOutputCol("indexedFeatures")
-      .setMaxCategories(4) // features with > 4 distinct values are treated as continuous
+      .setMaxCategories(4) // features with > 4 distinct values are treated as continuous.
       .fit(data);
 
-    // Split the data into training and test sets (30% held out for testing)
+    // Split the data into training and test sets (30% held out for testing).
     Dataset<Row>[] splits = data.randomSplit(new double[]{0.7, 0.3});
     Dataset<Row> trainingData = splits[0];
     Dataset<Row> testData = splits[1];
@@ -71,11 +73,11 @@ public static void main(String[] args) {
       .setOutputCol("predictedLabel")
       .setLabels(labelIndexer.labels());
 
-    // Chain indexers and tree in a Pipeline
+    // Chain indexers and tree in a Pipeline.
     Pipeline pipeline = new Pipeline()
       .setStages(new PipelineStage[]{labelIndexer, featureIndexer, dt, labelConverter});
 
-    // Train model.  This also runs the indexers.
+    // Train model. This also runs the indexers.
     PipelineModel model = pipeline.fit(trainingData);
 
     // Make predictions.
@@ -84,7 +86,7 @@ public static void main(String[] args) {
     // Select example rows to display.
     predictions.select("predictedLabel", "label", "features").show(5);
 
-    // Select (prediction, true label) and compute test error
+    // Select (prediction, true label) and compute test error.
     MulticlassClassificationEvaluator evaluator = new MulticlassClassificationEvaluator()
       .setLabelCol("indexedLabel")
       .setPredictionCol("prediction")

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

@@ -33,7 +33,9 @@
 public class JavaDecisionTreeRegressionExample {
   public static void main(String[] args) {
     SparkSession spark = SparkSession
-      .builder().appName("JavaDecisionTreeRegressionExample").getOrCreate();
+      .builder()
+      .appName("JavaDecisionTreeRegressionExample")
+      .getOrCreate();
     // $example on$
     // Load the data stored in LIBSVM format as a DataFrame.
     Dataset<Row> data = spark.read().format("libsvm")
@@ -47,7 +49,7 @@ public static void main(String[] args) {
       .setMaxCategories(4)
       .fit(data);
 
-    // Split the data into training and test sets (30% held out for testing)
+    // Split the data into training and test sets (30% held out for testing).
     Dataset<Row>[] splits = data.randomSplit(new double[]{0.7, 0.3});
     Dataset<Row> trainingData = splits[0];
     Dataset<Row> testData = splits[1];
@@ -56,11 +58,11 @@ public static void main(String[] args) {
     DecisionTreeRegressor dt = new DecisionTreeRegressor()
       .setFeaturesCol("indexedFeatures");
 
-    // Chain indexer and tree in a Pipeline
+    // Chain indexer and tree in a Pipeline.
     Pipeline pipeline = new Pipeline()
       .setStages(new PipelineStage[]{featureIndexer, dt});
 
-    // Train model.  This also runs the indexer.
+    // Train model. This also runs the indexer.
     PipelineModel model = pipeline.fit(trainingData);
 
     // Make predictions.
@@ -69,7 +71,7 @@ public static void main(String[] args) {
     // Select example rows to display.
     predictions.select("label", "features").show(5);
 
-    // Select (prediction, true label) and compute test error
+    // Select (prediction, true label) and compute test error.
     RegressionEvaluator evaluator = new RegressionEvaluator()
       .setLabelCol("label")
       .setPredictionCol("prediction")

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

@@ -62,15 +62,15 @@ public static void main(String[] args) throws Exception {
         new LabeledPoint(1.0, Vectors.dense(0.0, 1.2, -0.5)));
     Dataset<Row> training = spark.createDataFrame(localTraining, LabeledPoint.class);
 
-    // Create a LogisticRegression instance.  This instance is an Estimator.
+    // Create a LogisticRegression instance. This instance is an Estimator.
     MyJavaLogisticRegression lr = new MyJavaLogisticRegression();
     // Print out the parameters, documentation, and any default values.
     System.out.println("MyJavaLogisticRegression parameters:\n" + lr.explainParams() + "\n");
 
     // We may set parameters using setter methods.
     lr.setMaxIter(10);
 
-    // Learn a LogisticRegression model.  This uses the parameters stored in lr.
+    // Learn a LogisticRegression model. This uses the parameters stored in lr.
     MyJavaLogisticRegressionModel model = lr.fit(training);
 
     // Prepare test data.
@@ -214,7 +214,7 @@ public Vector predictRaw(Vector features) {
   }
 
   /**
-   * Number of classes the label can take.  2 indicates binary classification.
+   * Number of classes the label can take. 2 indicates binary classification.
    */
   public int numClasses() { return 2; }
 

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

@@ -38,7 +38,9 @@
 public class JavaEstimatorTransformerParamExample {
   public static void main(String[] args) {
     SparkSession spark = SparkSession
-      .builder().appName("JavaEstimatorTransformerParamExample").getOrCreate();
+      .builder()
+      .appName("JavaEstimatorTransformerParamExample")
+      .getOrCreate();
 
     // $example on$
     // Prepare training data.

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

@@ -75,11 +75,11 @@ public static void main(String[] args) {
       .setOutputCol("predictedLabel")
       .setLabels(labelIndexer.labels());
 
-    // Chain indexers and GBT in a Pipeline
+    // Chain indexers and GBT in a Pipeline.
     Pipeline pipeline = new Pipeline()
       .setStages(new PipelineStage[] {labelIndexer, featureIndexer, gbt, labelConverter});
 
-    // Train model.  This also runs the indexers.
+    // Train model. This also runs the indexers.
     PipelineModel model = pipeline.fit(trainingData);
 
     // Make predictions.
@@ -88,7 +88,7 @@ public static void main(String[] args) {
     // Select example rows to display.
     predictions.select("predictedLabel", "label", "features").show(5);
 
-    // Select (prediction, true label) and compute test error
+    // Select (prediction, true label) and compute test error.
     MulticlassClassificationEvaluator evaluator = new MulticlassClassificationEvaluator()
       .setLabelCol("indexedLabel")
       .setPredictionCol("prediction")

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

@@ -34,7 +34,9 @@
 public class JavaGradientBoostedTreeRegressorExample {
   public static void main(String[] args) {
     SparkSession spark = SparkSession
-      .builder().appName("JavaGradientBoostedTreeRegressorExample").getOrCreate();
+      .builder()
+      .appName("JavaGradientBoostedTreeRegressorExample")
+      .getOrCreate();
 
     // $example on$
     // Load and parse the data file, converting it to a DataFrame.
@@ -48,7 +50,7 @@ public static void main(String[] args) {
       .setMaxCategories(4)
       .fit(data);
 
-    // Split the data into training and test sets (30% held out for testing)
+    // Split the data into training and test sets (30% held out for testing).
     Dataset<Row>[] splits = data.randomSplit(new double[] {0.7, 0.3});
     Dataset<Row> trainingData = splits[0];
     Dataset<Row> testData = splits[1];
@@ -59,10 +61,10 @@ public static void main(String[] args) {
       .setFeaturesCol("indexedFeatures")
       .setMaxIter(10);
 
-    // Chain indexer and GBT in a Pipeline
+    // Chain indexer and GBT in a Pipeline.
     Pipeline pipeline = new Pipeline().setStages(new PipelineStage[] {featureIndexer, gbt});
 
-    // Train model.  This also runs the indexer.
+    // Train model. This also runs the indexer.
     PipelineModel model = pipeline.fit(trainingData);
 
     // Make predictions.
@@ -71,7 +73,7 @@ public static void main(String[] args) {
     // Select example rows to display.
     predictions.select("prediction", "label", "features").show(5);
 
-    // Select (prediction, true label) and compute test error
+    // Select (prediction, true label) and compute test error.
     RegressionEvaluator evaluator = new RegressionEvaluator()
       .setLabelCol("label")
       .setPredictionCol("prediction")

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

@@ -30,10 +30,12 @@
 public class JavaLinearRegressionWithElasticNetExample {
   public static void main(String[] args) {
     SparkSession spark = SparkSession
-      .builder().appName("JavaLinearRegressionWithElasticNetExample").getOrCreate();
+      .builder()
+      .appName("JavaLinearRegressionWithElasticNetExample")
+      .getOrCreate();
 
     // $example on$
-    // Load training data
+    // Load training data.
     Dataset<Row> training = spark.read().format("libsvm")
       .load("data/mllib/sample_linear_regression_data.txt");
 
@@ -42,14 +44,14 @@ public static void main(String[] args) {
       .setRegParam(0.3)
       .setElasticNetParam(0.8);
 
-    // Fit the model
+    // Fit the model.
     LinearRegressionModel lrModel = lr.fit(training);
 
-    // Print the coefficients and intercept for linear regression
+    // Print the coefficients and intercept for linear regression.
     System.out.println("Coefficients: "
       + lrModel.coefficients() + " Intercept: " + lrModel.intercept());
 
-    // Summarize the model over the training set and print out some metrics
+    // Summarize the model over the training set and print out some metrics.
     LinearRegressionTrainingSummary trainingSummary = lrModel.summary();
     System.out.println("numIterations: " + trainingSummary.totalIterations());
     System.out.println("objectiveHistory: " + Vectors.dense(trainingSummary.objectiveHistory()));

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

@@ -31,7 +31,9 @@
 public class JavaLogisticRegressionSummaryExample {
   public static void main(String[] args) {
     SparkSession spark = SparkSession
-      .builder().appName("JavaLogisticRegressionSummaryExample").getOrCreate();
+      .builder()
+      .appName("JavaLogisticRegressionSummaryExample")
+      .getOrCreate();
 
     // Load training data
     Dataset<Row> training = spark.read().format("libsvm")

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

@@ -28,7 +28,9 @@
 public class JavaLogisticRegressionWithElasticNetExample {
   public static void main(String[] args) {
     SparkSession spark = SparkSession
-      .builder().appName("JavaLogisticRegressionWithElasticNetExample").getOrCreate();
+      .builder()
+      .appName("JavaLogisticRegressionWithElasticNetExample")
+      .getOrCreate();
 
     // $example on$
     // Load training data

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

@@ -43,7 +43,9 @@
 public class JavaModelSelectionViaCrossValidationExample {
   public static void main(String[] args) {
     SparkSession spark = SparkSession
-      .builder().appName("JavaModelSelectionViaCrossValidationExample").getOrCreate();
+      .builder()
+      .appName("JavaModelSelectionViaCrossValidationExample")
+      .getOrCreate();
 
     // $example on$
     // Prepare training documents, which are labeled.

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

@@ -43,7 +43,9 @@
 public class JavaModelSelectionViaTrainValidationSplitExample {
   public static void main(String[] args) {
     SparkSession spark = SparkSession
-      .builder().appName("JavaModelSelectionViaTrainValidationSplitExample").getOrCreate();
+      .builder()
+      .appName("JavaModelSelectionViaTrainValidationSplitExample")
+      .getOrCreate();
 
     // $example on$
     Dataset<Row> data = spark.read().format("libsvm")

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

@@ -33,7 +33,9 @@ public class JavaMultilayerPerceptronClassifierExample {
 
   public static void main(String[] args) {
     SparkSession spark = SparkSession
-      .builder().appName("JavaMultilayerPerceptronClassifierExample").getOrCreate();
+      .builder()
+      .appName("JavaMultilayerPerceptronClassifierExample")
+      .getOrCreate();
 
     // $example on$
     // Load training data

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

@@ -35,7 +35,9 @@
 public class JavaQuantileDiscretizerExample {
   public static void main(String[] args) {
     SparkSession spark = SparkSession
-      .builder().appName("JavaQuantileDiscretizerExample").getOrCreate();
+      .builder()
+      .appName("JavaQuantileDiscretizerExample")
+      .getOrCreate();
 
     // $example on$
     List<Row> data = Arrays.asList(

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

@@ -33,7 +33,9 @@
 public class JavaRandomForestClassifierExample {
   public static void main(String[] args) {
     SparkSession spark = SparkSession
-      .builder().appName("JavaRandomForestClassifierExample").getOrCreate();
+      .builder()
+      .appName("JavaRandomForestClassifierExample")
+      .getOrCreate();
 
     // $example on$
     // Load and parse the data file, converting it to a DataFrame.

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

@@ -34,7 +34,9 @@
 public class JavaRandomForestRegressorExample {
   public static void main(String[] args) {
     SparkSession spark = SparkSession
-      .builder().appName("JavaRandomForestRegressorExample").getOrCreate();
+      .builder()
+      .appName("JavaRandomForestRegressorExample")
+      .getOrCreate();
 
     // $example on$
     // Load and parse the data file, converting it to a DataFrame.
@@ -62,7 +64,7 @@ public static void main(String[] args) {
     Pipeline pipeline = new Pipeline()
       .setStages(new PipelineStage[] {featureIndexer, rf});
 
-    // Train model.  This also runs the indexer.
+    // Train model. This also runs the indexer.
     PipelineModel model = pipeline.fit(trainingData);
 
     // Make predictions.

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

@@ -46,7 +46,7 @@ public static void main(String[] args) {
       .getOrCreate();
 
     // Prepare training data.
-    // We use LabeledPoint, which is a JavaBean.  Spark SQL can convert RDDs of JavaBeans
+    // We use LabeledPoint, which is a JavaBean. Spark SQL can convert RDDs of JavaBeans
     // into DataFrames, where it uses the bean metadata to infer the schema.
     List<LabeledPoint> localTraining = Lists.newArrayList(
       new LabeledPoint(1.0, Vectors.dense(0.0, 1.1, 0.1)),
@@ -56,7 +56,7 @@ public static void main(String[] args) {
     Dataset<Row> training =
       spark.createDataFrame(localTraining, LabeledPoint.class);
 
-    // Create a LogisticRegression instance.  This instance is an Estimator.
+    // Create a LogisticRegression instance. This instance is an Estimator.
     LogisticRegression lr = new LogisticRegression();
     // Print out the parameters, documentation, and any default values.
     System.out.println("LogisticRegression parameters:\n" + lr.explainParams() + "\n");
@@ -65,7 +65,7 @@ public static void main(String[] args) {
     lr.setMaxIter(10)
       .setRegParam(0.01);
 
-    // Learn a LogisticRegression model.  This uses the parameters stored in lr.
+    // Learn a LogisticRegression model. This uses the parameters stored in lr.
     LogisticRegressionModel model1 = lr.fit(training);
     // Since model1 is a Model (i.e., a Transformer produced by an Estimator),
     // we can view the parameters it used during fit().
@@ -82,7 +82,7 @@ public static void main(String[] args) {
 
     // One can also combine ParamMaps.
     ParamMap paramMap2 = new ParamMap();
-    paramMap2.put(lr.probabilityCol().w("myProbability")); // Change output column name
+    paramMap2.put(lr.probabilityCol().w("myProbability")); // Change output column name.
     ParamMap paramMapCombined = paramMap.$plus$plus(paramMap2);
 
     // Now learn a new model using the paramMapCombined parameters.

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

@@ -43,7 +43,9 @@ public class JavaSimpleTextClassificationPipeline {
 
   public static void main(String[] args) {
     SparkSession spark = SparkSession
-      .builder().appName("JavaSimpleTextClassificationPipeline").getOrCreate();
+      .builder()
+      .appName("JavaSimpleTextClassificationPipeline")
+      .getOrCreate();
 
     // Prepare training documents, which are labeled.
     List<LabeledDocument> localTraining = Lists.newArrayList(