[SPARK-15134][EXAMPLE] Indent SparkSession builder patterns and update binary_classification_metrics_example.py

## What changes were proposed in this pull request? This issue addresses the comments in SPARK-15031 and also fix java-linter errors. - Use multiline format in SparkSession builder patterns. - Update `binary_classification_metrics_example.py` to use `SparkSession`. - Fix Java Linter errors (in SPARK-13745, SPARK-15031, and so far) ## How was this patch tested? After passing the Jenkins tests and run `dev/lint-java` manually. Author: Dongjoon Hyun <dongjoon@apache.org> Closes #12911 from dongjoon-hyun/SPARK-15134.
2016-05-05 14:37:50 -07:00 · 2016-05-05 14:37:50 -07:00 · 2c170dd3d7
parent bb9991dec5
commit 2c170dd3d7
142 changed files with 585 additions and 178 deletions
--- a/common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandler.java
+++ b/common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandler.java
@ -87,8 +87,11 @@ public class ExternalShuffleBlockHandler extends RpcHandler {
        blocks.add(blockManager.getBlockData(msg.appId, msg.execId, blockId));
      }
      long streamId = streamManager.registerStream(client.getClientId(), blocks.iterator());
-      logger.trace("Registered streamId {} with {} buffers for client {} from host {}", streamId, 
-        msg.blockIds.length, client.getClientId(), NettyUtils.getRemoteAddress(client.getChannel()));
+      logger.trace("Registered streamId {} with {} buffers for client {} from host {}",
+          streamId,
+          msg.blockIds.length,
+          client.getClientId(),
+          NettyUtils.getRemoteAddress(client.getChannel()));
      callback.onSuccess(new StreamHandle(streamId, msg.blockIds.length).toByteBuffer());

    } else if (msgObj instanceof RegisterExecutor) {
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaAFTSurvivalRegressionExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaAFTSurvivalRegressionExample.java
@ -33,7 +33,10 @@ import org.apache.spark.sql.types.*;

 public class JavaAFTSurvivalRegressionExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaAFTSurvivalRegressionExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaAFTSurvivalRegressionExample")
+      .getOrCreate();

    // $example on$
    List<Row> data = Arrays.asList(
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaALSExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaALSExample.java
@ -81,7 +81,10 @@ public class JavaALSExample {
  // $example off$

  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaALSExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaALSExample")
+      .getOrCreate();

    // $example on$
    JavaRDD<Rating> ratingsRDD = spark
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java
@ -17,8 +17,6 @@

 package org.apache.spark.examples.ml;

-import org.apache.spark.SparkConf;
-import org.apache.spark.api.java.JavaSparkContext;
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.SparkSession;

@ -26,7 +24,6 @@ import org.apache.spark.sql.SparkSession;
 import java.util.Arrays;
 import java.util.List;

-import org.apache.spark.api.java.JavaRDD;
 import org.apache.spark.ml.feature.Binarizer;
 import org.apache.spark.sql.Row;
 import org.apache.spark.sql.RowFactory;
@ -38,7 +35,10 @@ import org.apache.spark.sql.types.StructType;

 public class JavaBinarizerExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaBinarizerExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaBinarizerExample")
+      .getOrCreate();

    // $example on$
    List<Row> data = Arrays.asList(
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaBisectingKMeansExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaBisectingKMeansExample.java
@ -42,7 +42,10 @@ import org.apache.spark.sql.types.StructType;
 public class JavaBisectingKMeansExample {

  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaBisectingKMeansExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaBisectingKMeansExample")
+      .getOrCreate();

    // $example on$
    List<Row> data = Arrays.asList(
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java
@ -35,7 +35,10 @@ import org.apache.spark.sql.types.StructType;

 public class JavaBucketizerExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaBucketizerExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaBucketizerExample")
+      .getOrCreate();

    // $example on$
    double[] splits = {Double.NEGATIVE_INFINITY, -0.5, 0.0, 0.5, Double.POSITIVE_INFINITY};
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.java
@ -17,9 +17,6 @@

 package org.apache.spark.examples.ml;

-import org.apache.spark.SparkConf;
-import org.apache.spark.api.java.JavaRDD;
-import org.apache.spark.api.java.JavaSparkContext;
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.SparkSession;

@ -40,7 +37,10 @@ import org.apache.spark.sql.types.StructType;

 public class JavaChiSqSelectorExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaChiSqSelectorExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaChiSqSelectorExample")
+      .getOrCreate();

    // $example on$
    List<Row> data = Arrays.asList(
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaCountVectorizerExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaCountVectorizerExample.java
@ -32,7 +32,10 @@ import org.apache.spark.sql.types.*;

 public class JavaCountVectorizerExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaCountVectorizerExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaCountVectorizerExample")
+      .getOrCreate();

    // $example on$
    // Input data: Each row is a bag of words from a sentence or document.
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java
@ -17,8 +17,6 @@

 package org.apache.spark.examples.ml;

-import org.apache.spark.SparkConf;
-import org.apache.spark.api.java.JavaSparkContext;
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.SparkSession;

@ -26,7 +24,6 @@ import org.apache.spark.sql.SparkSession;
 import java.util.Arrays;
 import java.util.List;

-import org.apache.spark.api.java.JavaRDD;
 import org.apache.spark.ml.feature.DCT;
 import org.apache.spark.mllib.linalg.VectorUDT;
 import org.apache.spark.mllib.linalg.Vectors;
@ -39,7 +36,10 @@ import org.apache.spark.sql.types.StructType;

 public class JavaDCTExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaDCTExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaDCTExample")
+      .getOrCreate();

    // $example on$
    List<Row> data = Arrays.asList(
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaDeveloperApiExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaDeveloperApiExample.java
@ -49,7 +49,10 @@ import org.apache.spark.sql.SparkSession;
 public class JavaDeveloperApiExample {

  public static void main(String[] args) throws Exception {
-    SparkSession spark = SparkSession.builder().appName("JavaDeveloperApiExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaDeveloperApiExample")
+      .getOrCreate();

    // Prepare training data.
    List<LabeledPoint> localTraining = Lists.newArrayList(
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java
@ -17,8 +17,6 @@

 package org.apache.spark.examples.ml;

-import org.apache.spark.SparkConf;
-import org.apache.spark.api.java.JavaSparkContext;
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.SparkSession;

@ -27,7 +25,6 @@ import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.List;

-import org.apache.spark.api.java.JavaRDD;
 import org.apache.spark.ml.feature.ElementwiseProduct;
 import org.apache.spark.mllib.linalg.Vector;
 import org.apache.spark.mllib.linalg.VectorUDT;
@ -42,7 +39,9 @@ import org.apache.spark.sql.types.StructType;
 public class JavaElementwiseProductExample {
  public static void main(String[] args) {
    SparkSession spark = SparkSession
-      .builder().appName("JavaElementwiseProductExample").getOrCreate();
+      .builder()
+      .appName("JavaElementwiseProductExample")
+      .getOrCreate();

    // $example on$
    // Create some vector data; also works for sparse vectors
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java
@ -17,8 +17,6 @@

 package org.apache.spark.examples.ml;

-import org.apache.spark.SparkConf;
-import org.apache.spark.api.java.JavaSparkContext;
 // $example on$
 import org.apache.spark.ml.Pipeline;
 import org.apache.spark.ml.PipelineModel;
@ -35,11 +33,15 @@ import org.apache.spark.sql.SparkSession;
 public class JavaGradientBoostedTreeClassifierExample {
  public static void main(String[] args) {
    SparkSession spark = SparkSession
-      .builder().appName("JavaGradientBoostedTreeClassifierExample").getOrCreate();
+      .builder()
+      .appName("JavaGradientBoostedTreeClassifierExample")
+      .getOrCreate();

    // $example on$
    // Load and parse the data file, converting it to a DataFrame.
-    Dataset<Row> data = spark.read().format("libsvm")
+    Dataset<Row> data = spark
+      .read()
+      .format("libsvm")
      .load("data/mllib/sample_libsvm_data.txt");

    // Index labels, adding metadata to the label column.
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java
@ -37,7 +37,10 @@ import org.apache.spark.sql.types.StructType;

 public class JavaIndexToStringExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaIndexToStringExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaIndexToStringExample")
+      .getOrCreate();

    // $example on$
    List<Row> data = Arrays.asList(
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaKMeansExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaKMeansExample.java
@ -70,7 +70,10 @@ public class JavaKMeansExample {
    int k = Integer.parseInt(args[1]);

    // Parses the arguments
-    SparkSession spark = SparkSession.builder().appName("JavaKMeansExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaKMeansExample")
+      .getOrCreate();

    // $example on$
    // Loads data
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaLDAExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaLDAExample.java
@ -65,7 +65,10 @@ public class JavaLDAExample {
    String inputFile = "data/mllib/sample_lda_data.txt";

    // Parses the arguments
-    SparkSession spark = SparkSession.builder().appName("JavaLDAExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaLDAExample")
+      .getOrCreate();

    // Loads data
    JavaRDD<Row> points = spark.read().text(inputFile).javaRDD().map(new ParseVector());
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaMaxAbsScalerExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaMaxAbsScalerExample.java
@ -28,13 +28,19 @@ import org.apache.spark.sql.SparkSession;
 public class JavaMaxAbsScalerExample {

  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaMaxAbsScalerExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaMaxAbsScalerExample")
+      .getOrCreate();

    // $example on$
-    Dataset<Row> dataFrame = spark.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt");
+    Dataset<Row> dataFrame = spark
+      .read()
+      .format("libsvm")
+      .load("data/mllib/sample_libsvm_data.txt");
    MaxAbsScaler scaler = new MaxAbsScaler()
-        .setInputCol("features")
-        .setOutputCol("scaledFeatures");
+      .setInputCol("features")
+      .setOutputCol("scaledFeatures");

    // Compute summary statistics and generate MaxAbsScalerModel
    MaxAbsScalerModel scalerModel = scaler.fit(dataFrame);
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java
@ -28,10 +28,16 @@ import org.apache.spark.sql.Row;

 public class JavaMinMaxScalerExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaMinMaxScalerExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaMinMaxScalerExample")
+      .getOrCreate();

    // $example on$
-    Dataset<Row> dataFrame = spark.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt");
+    Dataset<Row> dataFrame = spark
+      .read()
+      .format("libsvm")
+      .load("data/mllib/sample_libsvm_data.txt");
    MinMaxScaler scaler = new MinMaxScaler()
      .setInputCol("features")
      .setOutputCol("scaledFeatures");
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaNGramExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaNGramExample.java
@ -35,7 +35,10 @@ import org.apache.spark.sql.types.StructType;

 public class JavaNGramExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaNGramExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaNGramExample")
+      .getOrCreate();

    // $example on$
    List<Row> data = Arrays.asList(
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java
@ -32,7 +32,10 @@ import org.apache.spark.sql.SparkSession;
 public class JavaNaiveBayesExample {

  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaNaiveBayesExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaNaiveBayesExample")
+      .getOrCreate();

    // $example on$
    // Load training data
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaNormalizerExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaNormalizerExample.java
@ -27,7 +27,10 @@ import org.apache.spark.sql.Row;

 public class JavaNormalizerExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaNormalizerExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaNormalizerExample")
+      .getOrCreate();

    // $example on$
    Dataset<Row> dataFrame =
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java
@ -37,7 +37,10 @@ import org.apache.spark.sql.types.StructType;

 public class JavaOneHotEncoderExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaOneHotEncoderExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaOneHotEncoderExample")
+      .getOrCreate();

    // $example on$
    List<Row> data = Arrays.asList(
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaOneVsRestExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaOneVsRestExample.java
@ -58,7 +58,10 @@ public class JavaOneVsRestExample {
  public static void main(String[] args) {
    // parse the arguments
    Params params = parse(args);
-    SparkSession spark = SparkSession.builder().appName("JavaOneVsRestExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaOneVsRestExample")
+      .getOrCreate();

    // $example on$
    // configure the base classifier
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaPCAExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaPCAExample.java
@ -37,7 +37,10 @@ import org.apache.spark.sql.types.StructType;

 public class JavaPCAExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaPCAExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaPCAExample")
+      .getOrCreate();

    // $example on$
    List<Row> data = Arrays.asList(
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaPipelineExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaPipelineExample.java
@ -36,7 +36,10 @@ import org.apache.spark.sql.SparkSession;
 */
 public class JavaPipelineExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaPipelineExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaPipelineExample")
+      .getOrCreate();

    // $example on$
    // Prepare training documents, which are labeled.
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaPolynomialExpansionExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaPolynomialExpansionExample.java
@ -36,7 +36,10 @@ import org.apache.spark.sql.types.StructType;

 public class JavaPolynomialExpansionExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaPolynomialExpansionExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaPolynomialExpansionExample")
+      .getOrCreate();

    // $example on$
    PolynomialExpansion polyExpansion = new PolynomialExpansion()
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaRFormulaExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaRFormulaExample.java
@ -35,7 +35,10 @@ import static org.apache.spark.sql.types.DataTypes.*;

 public class JavaRFormulaExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaRFormulaExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaRFormulaExample")
+      .getOrCreate();

    // $example on$
    StructType schema = createStructType(new StructField[]{
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaSQLTransformerExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaSQLTransformerExample.java
@ -31,7 +31,10 @@ import org.apache.spark.sql.types.*;

 public class JavaSQLTransformerExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaSQLTransformerExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaSQLTransformerExample")
+      .getOrCreate();

    // $example on$
    List<Row> data = Arrays.asList(
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java
@ -40,7 +40,10 @@ import org.apache.spark.sql.SparkSession;
 public class JavaSimpleParamsExample {

  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaSimpleParamsExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaSimpleParamsExample")
+      .getOrCreate();

    // Prepare training data.
    // We use LabeledPoint, which is a JavaBean.  Spark SQL can convert RDDs of JavaBeans
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaStandardScalerExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaStandardScalerExample.java
@ -28,7 +28,10 @@ import org.apache.spark.sql.Row;

 public class JavaStandardScalerExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaStandardScalerExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaStandardScalerExample")
+      .getOrCreate();

    // $example on$
    Dataset<Row> dataFrame =
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaStopWordsRemoverExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaStopWordsRemoverExample.java
@ -36,7 +36,10 @@ import org.apache.spark.sql.types.StructType;
 public class JavaStopWordsRemoverExample {

  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaStopWordsRemoverExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaStopWordsRemoverExample")
+      .getOrCreate();

    // $example on$
    StopWordsRemover remover = new StopWordsRemover()
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaStringIndexerExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaStringIndexerExample.java
@ -35,7 +35,10 @@ import static org.apache.spark.sql.types.DataTypes.*;

 public class JavaStringIndexerExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaStringIndexerExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaStringIndexerExample")
+      .getOrCreate();

    // $example on$
    List<Row> data = Arrays.asList(
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaTfIdfExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaTfIdfExample.java
@ -38,7 +38,10 @@ import org.apache.spark.sql.types.StructType;

 public class JavaTfIdfExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaTfIdfExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaTfIdfExample")
+      .getOrCreate();

    // $example on$
    List<Row> data = Arrays.asList(
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java
@ -36,7 +36,10 @@ import org.apache.spark.sql.types.StructType;

 public class JavaTokenizerExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaTokenizerExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaTokenizerExample")
+      .getOrCreate();

    // $example on$
    List<Row> data = Arrays.asList(
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java
@ -35,7 +35,10 @@ import static org.apache.spark.sql.types.DataTypes.*;

 public class JavaVectorAssemblerExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaVectorAssemblerExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaVectorAssemblerExample")
+      .getOrCreate();

    // $example on$
    StructType schema = createStructType(new StructField[]{
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorIndexerExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorIndexerExample.java
@ -30,7 +30,10 @@ import org.apache.spark.sql.Row;

 public class JavaVectorIndexerExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaVectorIndexerExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaVectorIndexerExample")
+      .getOrCreate();

    // $example on$
    Dataset<Row> data = spark.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt");
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSlicerExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSlicerExample.java
@ -37,7 +37,10 @@ import org.apache.spark.sql.types.*;

 public class JavaVectorSlicerExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaVectorSlicerExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaVectorSlicerExample")
+      .getOrCreate();

    // $example on$
    Attribute[] attrs = new Attribute[]{
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaWord2VecExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaWord2VecExample.java
@ -32,7 +32,10 @@ import org.apache.spark.sql.types.*;

 public class JavaWord2VecExample {
  public static void main(String[] args) {
-    SparkSession spark = SparkSession.builder().appName("JavaWord2VecExample").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaWord2VecExample")
+      .getOrCreate();

    // $example on$
    // Input data: Each row is a bag of words from a sentence or document.
--- a/examples/src/main/java/org/apache/spark/examples/sql/JavaSparkSQL.java
+++ b/examples/src/main/java/org/apache/spark/examples/sql/JavaSparkSQL.java
@ -51,7 +51,10 @@ public class JavaSparkSQL {
  }

  public static void main(String[] args) throws Exception {
-    SparkSession spark = SparkSession.builder().appName("JavaSparkSQL").getOrCreate();
+    SparkSession spark = SparkSession
+      .builder()
+      .appName("JavaSparkSQL")
+      .getOrCreate();

    System.out.println("=== Data source: RDD ===");
    // Load a text file and convert each line to a Java Bean.
@ -147,7 +150,8 @@ public class JavaSparkSQL {
    // a RDD[String] storing one JSON object per string.
    List<String> jsonData = Arrays.asList(
          "{\"name\":\"Yin\",\"address\":{\"city\":\"Columbus\",\"state\":\"Ohio\"}}");
-    JavaRDD<String> anotherPeopleRDD = spark.createDataFrame(jsonData, String.class).toJSON().javaRDD();
+    JavaRDD<String> anotherPeopleRDD = spark
+      .createDataFrame(jsonData, String.class).toJSON().javaRDD();
    Dataset<Row> peopleFromJsonRDD = spark.read().json(anotherPeopleRDD);

    // Take a look at the schema of this new DataFrame.
--- a/examples/src/main/java/org/apache/spark/examples/streaming/JavaSqlNetworkWordCount.java
+++ b/examples/src/main/java/org/apache/spark/examples/streaming/JavaSqlNetworkWordCount.java
@ -115,7 +115,10 @@ class JavaSparkSessionSingleton {
  private static transient SparkSession instance = null;
  public static SparkSession getInstance(SparkConf sparkConf) {
    if (instance == null) {
-      instance = SparkSession.builder().config(sparkConf).getOrCreate();
+      instance = SparkSession
+        .builder()
+        .config(sparkConf)
+        .getOrCreate();
    }
    return instance;
  }
--- a/examples/src/main/python/ml/als_example.py
+++ b/examples/src/main/python/ml/als_example.py
@ -30,7 +30,10 @@ from pyspark.sql import Row
 # $example off$

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("ALSExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("ALSExample")\
+        .getOrCreate()

    # $example on$
    lines = spark.read.text("data/mllib/als/sample_movielens_ratings.txt").rdd
--- a/examples/src/main/python/ml/binarizer_example.py
+++ b/examples/src/main/python/ml/binarizer_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import Binarizer
 # $example off$

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("BinarizerExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("BinarizerExample")\
+        .getOrCreate()

    # $example on$
    continuousDataFrame = spark.createDataFrame([
--- a/examples/src/main/python/ml/bisecting_k_means_example.py
+++ b/examples/src/main/python/ml/bisecting_k_means_example.py
@ -30,7 +30,10 @@ A simple example demonstrating a bisecting k-means clustering.
 """

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("PythonBisectingKMeansExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("PythonBisectingKMeansExample")\
+        .getOrCreate()

    # $example on$
    data = spark.read.text("data/mllib/kmeans_data.txt").rdd
--- a/examples/src/main/python/ml/bucketizer_example.py
+++ b/examples/src/main/python/ml/bucketizer_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import Bucketizer
 # $example off$

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("BucketizerExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("BucketizerExample")\
+        .getOrCreate()

    # $example on$
    splits = [-float("inf"), -0.5, 0.0, 0.5, float("inf")]
--- a/examples/src/main/python/ml/chisq_selector_example.py
+++ b/examples/src/main/python/ml/chisq_selector_example.py
@ -24,7 +24,10 @@ from pyspark.mllib.linalg import Vectors
 # $example off$

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("ChiSqSelectorExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("ChiSqSelectorExample")\
+        .getOrCreate()

    # $example on$
    df = spark.createDataFrame([
--- a/examples/src/main/python/ml/count_vectorizer_example.py
+++ b/examples/src/main/python/ml/count_vectorizer_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import CountVectorizer
 # $example off$

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("CountVectorizerExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("CountVectorizerExample")\
+        .getOrCreate()

    # $example on$
    # Input data: Each row is a bag of words with a ID.
--- a/examples/src/main/python/ml/cross_validator.py
+++ b/examples/src/main/python/ml/cross_validator.py
@ -35,7 +35,10 @@ Run with:
 """

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("CrossValidatorExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("CrossValidatorExample")\
+        .getOrCreate()
    # $example on$
    # Prepare training documents, which are labeled.
    training = spark.createDataFrame([
--- a/examples/src/main/python/ml/dataframe_example.py
+++ b/examples/src/main/python/ml/dataframe_example.py
@ -33,7 +33,10 @@ if __name__ == "__main__":
    if len(sys.argv) > 2:
        print("Usage: dataframe_example.py <libsvm file>", file=sys.stderr)
        exit(-1)
-    spark = SparkSession.builder.appName("DataFrameExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("DataFrameExample")\
+        .getOrCreate()
    if len(sys.argv) == 2:
        input = sys.argv[1]
    else:
--- a/examples/src/main/python/ml/dct_example.py
+++ b/examples/src/main/python/ml/dct_example.py
@ -24,7 +24,10 @@ from pyspark.mllib.linalg import Vectors
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("DCTExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("DCTExample")\
+        .getOrCreate()

    # $example on$
    df = spark.createDataFrame([
--- a/examples/src/main/python/ml/decision_tree_classification_example.py
+++ b/examples/src/main/python/ml/decision_tree_classification_example.py
@ -29,7 +29,10 @@ from pyspark.ml.evaluation import MulticlassClassificationEvaluator
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("decision_tree_classification_example").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("decision_tree_classification_example")\
+        .getOrCreate()

    # $example on$
    # Load the data stored in LIBSVM format as a DataFrame.
--- a/examples/src/main/python/ml/decision_tree_regression_example.py
+++ b/examples/src/main/python/ml/decision_tree_regression_example.py
@ -29,7 +29,10 @@ from pyspark.ml.evaluation import RegressionEvaluator
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("decision_tree_classification_example").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("decision_tree_classification_example")\
+        .getOrCreate()

    # $example on$
    # Load the data stored in LIBSVM format as a DataFrame.
--- a/examples/src/main/python/ml/elementwise_product_example.py
+++ b/examples/src/main/python/ml/elementwise_product_example.py
@ -24,7 +24,10 @@ from pyspark.mllib.linalg import Vectors
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("ElementwiseProductExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("ElementwiseProductExample")\
+        .getOrCreate()

    # $example on$
    data = [(Vectors.dense([1.0, 2.0, 3.0]),), (Vectors.dense([4.0, 5.0, 6.0]),)]
--- a/examples/src/main/python/ml/estimator_transformer_param_example.py
+++ b/examples/src/main/python/ml/estimator_transformer_param_example.py
@ -26,7 +26,10 @@ from pyspark.ml.classification import LogisticRegression
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("EstimatorTransformerParamExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("EstimatorTransformerParamExample")\
+        .getOrCreate()

    # $example on$
    # Prepare training data from a list of (label, features) tuples.
--- a/examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py
+++ b/examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py
@ -29,7 +29,10 @@ from pyspark.ml.evaluation import MulticlassClassificationEvaluator
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("gradient_boosted_tree_classifier_example").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("gradient_boosted_tree_classifier_example")\
+        .getOrCreate()

    # $example on$
    # Load and parse the data file, converting it to a DataFrame.
--- a/examples/src/main/python/ml/gradient_boosted_tree_regressor_example.py
+++ b/examples/src/main/python/ml/gradient_boosted_tree_regressor_example.py
@ -29,7 +29,10 @@ from pyspark.ml.evaluation import RegressionEvaluator
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("gradient_boosted_tree_regressor_example").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("gradient_boosted_tree_regressor_example")\
+        .getOrCreate()

    # $example on$
    # Load and parse the data file, converting it to a DataFrame.
--- a/examples/src/main/python/ml/index_to_string_example.py
+++ b/examples/src/main/python/ml/index_to_string_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import IndexToString, StringIndexer
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("IndexToStringExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("IndexToStringExample")\
+        .getOrCreate()

    # $example on$
    df = spark.createDataFrame(
--- a/examples/src/main/python/ml/kmeans_example.py
+++ b/examples/src/main/python/ml/kmeans_example.py
@ -49,7 +49,10 @@ if __name__ == "__main__":
    path = sys.argv[1]
    k = sys.argv[2]

-    spark = SparkSession.builder.appName("PythonKMeansExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("PythonKMeansExample")\
+        .getOrCreate()

    lines = spark.read.text(path).rdd
    data = lines.map(parseVector)
--- a/examples/src/main/python/ml/linear_regression_with_elastic_net.py
+++ b/examples/src/main/python/ml/linear_regression_with_elastic_net.py
@ -23,7 +23,10 @@ from pyspark.ml.regression import LinearRegression
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("LinearRegressionWithElasticNet").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("LinearRegressionWithElasticNet")\
+        .getOrCreate()

    # $example on$
    # Load training data
--- a/examples/src/main/python/ml/logistic_regression_with_elastic_net.py
+++ b/examples/src/main/python/ml/logistic_regression_with_elastic_net.py
@ -23,7 +23,10 @@ from pyspark.ml.classification import LogisticRegression
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("LogisticRegressionWithElasticNet").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("LogisticRegressionWithElasticNet")\
+        .getOrCreate()

    # $example on$
    # Load training data
--- a/examples/src/main/python/ml/max_abs_scaler_example.py
+++ b/examples/src/main/python/ml/max_abs_scaler_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import MaxAbsScaler
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("MaxAbsScalerExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("MaxAbsScalerExample")\
+        .getOrCreate()

    # $example on$
    dataFrame = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
--- a/examples/src/main/python/ml/min_max_scaler_example.py
+++ b/examples/src/main/python/ml/min_max_scaler_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import MinMaxScaler
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("MinMaxScalerExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("MinMaxScalerExample")\
+        .getOrCreate()

    # $example on$
    dataFrame = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
--- a/examples/src/main/python/ml/n_gram_example.py
+++ b/examples/src/main/python/ml/n_gram_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import NGram
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("NGramExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("NGramExample")\
+        .getOrCreate()

    # $example on$
    wordDataFrame = spark.createDataFrame([
--- a/examples/src/main/python/ml/naive_bayes_example.py
+++ b/examples/src/main/python/ml/naive_bayes_example.py
@ -24,7 +24,10 @@ from pyspark.ml.evaluation import MulticlassClassificationEvaluator
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("naive_bayes_example").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("naive_bayes_example")\
+        .getOrCreate()

    # $example on$
    # Load training data
--- a/examples/src/main/python/ml/normalizer_example.py
+++ b/examples/src/main/python/ml/normalizer_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import Normalizer
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("NormalizerExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("NormalizerExample")\
+        .getOrCreate()

    # $example on$
    dataFrame = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
--- a/examples/src/main/python/ml/onehot_encoder_example.py
+++ b/examples/src/main/python/ml/onehot_encoder_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import OneHotEncoder, StringIndexer
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("OneHotEncoderExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("OneHotEncoderExample")\
+        .getOrCreate()

    # $example on$
    df = spark.createDataFrame([
--- a/examples/src/main/python/ml/pca_example.py
+++ b/examples/src/main/python/ml/pca_example.py
@ -24,7 +24,10 @@ from pyspark.mllib.linalg import Vectors
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("PCAExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("PCAExample")\
+        .getOrCreate()

    # $example on$
    data = [(Vectors.sparse(5, [(1, 1.0), (3, 7.0)]),),
--- a/examples/src/main/python/ml/pipeline_example.py
+++ b/examples/src/main/python/ml/pipeline_example.py
@ -27,7 +27,10 @@ from pyspark.ml.feature import HashingTF, Tokenizer
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("PipelineExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("PipelineExample")\
+        .getOrCreate()

    # $example on$
    # Prepare training documents from a list of (id, text, label) tuples.
--- a/examples/src/main/python/ml/polynomial_expansion_example.py
+++ b/examples/src/main/python/ml/polynomial_expansion_example.py
@ -24,7 +24,10 @@ from pyspark.mllib.linalg import Vectors
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("PolynomialExpansionExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("PolynomialExpansionExample")\
+        .getOrCreate()

    # $example on$
    df = spark\
--- a/examples/src/main/python/ml/random_forest_classifier_example.py
+++ b/examples/src/main/python/ml/random_forest_classifier_example.py
@ -29,7 +29,10 @@ from pyspark.ml.evaluation import MulticlassClassificationEvaluator
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("random_forest_classifier_example").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("random_forest_classifier_example")\
+        .getOrCreate()

    # $example on$
    # Load and parse the data file, converting it to a DataFrame.
--- a/examples/src/main/python/ml/random_forest_regressor_example.py
+++ b/examples/src/main/python/ml/random_forest_regressor_example.py
@ -29,7 +29,10 @@ from pyspark.ml.evaluation import RegressionEvaluator
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("random_forest_regressor_example").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("random_forest_regressor_example")\
+        .getOrCreate()

    # $example on$
    # Load and parse the data file, converting it to a DataFrame.
--- a/examples/src/main/python/ml/rformula_example.py
+++ b/examples/src/main/python/ml/rformula_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import RFormula
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("RFormulaExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("RFormulaExample")\
+        .getOrCreate()

    # $example on$
    dataset = spark.createDataFrame(
--- a/examples/src/main/python/ml/simple_text_classification_pipeline.py
+++ b/examples/src/main/python/ml/simple_text_classification_pipeline.py
@ -33,7 +33,10 @@ pipeline in Python. Run with:


 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("SimpleTextClassificationPipeline").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("SimpleTextClassificationPipeline")\
+        .getOrCreate()

    # Prepare training documents, which are labeled.
    training = spark.createDataFrame([
--- a/examples/src/main/python/ml/sql_transformer.py
+++ b/examples/src/main/python/ml/sql_transformer.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import SQLTransformer
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("SQLTransformerExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("SQLTransformerExample")\
+        .getOrCreate()

    # $example on$
    df = spark.createDataFrame([
--- a/examples/src/main/python/ml/standard_scaler_example.py
+++ b/examples/src/main/python/ml/standard_scaler_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import StandardScaler
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("StandardScalerExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("StandardScalerExample")\
+        .getOrCreate()

    # $example on$
    dataFrame = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
--- a/examples/src/main/python/ml/stopwords_remover_example.py
+++ b/examples/src/main/python/ml/stopwords_remover_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import StopWordsRemover
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("StopWordsRemoverExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("StopWordsRemoverExample")\
+        .getOrCreate()

    # $example on$
    sentenceData = spark.createDataFrame([
--- a/examples/src/main/python/ml/string_indexer_example.py
+++ b/examples/src/main/python/ml/string_indexer_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import StringIndexer
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("StringIndexerExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("StringIndexerExample")\
+        .getOrCreate()

    # $example on$
    df = spark.createDataFrame(
--- a/examples/src/main/python/ml/tf_idf_example.py
+++ b/examples/src/main/python/ml/tf_idf_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import HashingTF, IDF, Tokenizer
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("TfIdfExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("TfIdfExample")\
+        .getOrCreate()

    # $example on$
    sentenceData = spark.createDataFrame([
--- a/examples/src/main/python/ml/tokenizer_example.py
+++ b/examples/src/main/python/ml/tokenizer_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import Tokenizer, RegexTokenizer
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("TokenizerExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("TokenizerExample")\
+        .getOrCreate()

    # $example on$
    sentenceDataFrame = spark.createDataFrame([
--- a/examples/src/main/python/ml/train_validation_split.py
+++ b/examples/src/main/python/ml/train_validation_split.py
@ -31,7 +31,10 @@ Run with:
 """

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("TrainValidationSplit").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("TrainValidationSplit")\
+        .getOrCreate()
    # $example on$
    # Prepare training and test data.
    data = spark.read.format("libsvm")\
--- a/examples/src/main/python/ml/vector_assembler_example.py
+++ b/examples/src/main/python/ml/vector_assembler_example.py
@ -24,7 +24,10 @@ from pyspark.ml.feature import VectorAssembler
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("VectorAssemblerExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("VectorAssemblerExample")\
+        .getOrCreate()

    # $example on$
    dataset = spark.createDataFrame(
--- a/examples/src/main/python/ml/vector_indexer_example.py
+++ b/examples/src/main/python/ml/vector_indexer_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import VectorIndexer
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("VectorIndexerExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("VectorIndexerExample")\
+        .getOrCreate()

    # $example on$
    data = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
--- a/examples/src/main/python/ml/vector_slicer_example.py
+++ b/examples/src/main/python/ml/vector_slicer_example.py
@ -25,7 +25,10 @@ from pyspark.sql.types import Row
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("VectorSlicerExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("VectorSlicerExample")\
+        .getOrCreate()

    # $example on$
    df = spark.createDataFrame([
--- a/examples/src/main/python/ml/word2vec_example.py
+++ b/examples/src/main/python/ml/word2vec_example.py
@ -23,7 +23,10 @@ from pyspark.ml.feature import Word2Vec
 from pyspark.sql import SparkSession

 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("Word2VecExample").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("Word2VecExample")\
+        .getOrCreate()

    # $example on$
    # Input data: Each row is a bag of words from a sentence or document.
--- a/examples/src/main/python/mllib/binary_classification_metrics_example.py
+++ b/examples/src/main/python/mllib/binary_classification_metrics_example.py
@ -18,20 +18,25 @@
 Binary Classification Metrics Example.
 """
 from __future__ import print_function
-from pyspark import SparkContext
+from pyspark.sql import SparkSession
 # $example on$
 from pyspark.mllib.classification import LogisticRegressionWithLBFGS
 from pyspark.mllib.evaluation import BinaryClassificationMetrics
-from pyspark.mllib.util import MLUtils
+from pyspark.mllib.regression import LabeledPoint
 # $example off$

 if __name__ == "__main__":
-    sc = SparkContext(appName="BinaryClassificationMetricsExample")
+    spark = SparkSession\
+        .builder\
+        .appName("BinaryClassificationMetricsExample")\
+        .getOrCreate()

    # $example on$
    # Several of the methods available in scala are currently missing from pyspark
    # Load training data in LIBSVM format
-    data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_binary_classification_data.txt")
+    data = spark\
+        .read.format("libsvm").load("data/mllib/sample_binary_classification_data.txt")\
+        .rdd.map(lambda row: LabeledPoint(row[0], row[1]))

    # Split data into training (60%) and test (40%)
    training, test = data.randomSplit([0.6, 0.4], seed=11L)
@ -53,4 +58,4 @@ if __name__ == "__main__":
    print("Area under ROC = %s" % metrics.areaUnderROC)
    # $example off$

-    sc.stop()
+    spark.stop()
--- a/examples/src/main/python/sql.py
+++ b/examples/src/main/python/sql.py
@ -25,7 +25,10 @@ from pyspark.sql.types import Row, StructField, StructType, StringType, IntegerT


 if __name__ == "__main__":
-    spark = SparkSession.builder.appName("PythonSQL").getOrCreate()
+    spark = SparkSession\
+        .builder\
+        .appName("PythonSQL")\
+        .getOrCreate()

    # A list of Rows. Infer schema from the first row, create a DataFrame and print the schema
    rows = [Row(name="John", age=19), Row(name="Smith", age=23), Row(name="Sarah", age=18)]
--- a/examples/src/main/python/streaming/sql_network_wordcount.py
+++ b/examples/src/main/python/streaming/sql_network_wordcount.py
@ -38,8 +38,10 @@ from pyspark.sql import Row, SparkSession

 def getSparkSessionInstance(sparkConf):
    if ('sparkSessionSingletonInstance' not in globals()):
-        globals()['sparkSessionSingletonInstance'] =\
-            SparkSession.builder.config(conf=sparkConf).getOrCreate()
+        globals()['sparkSessionSingletonInstance'] = SparkSession\
+            .builder\
+            .config(conf=sparkConf)\
+            .getOrCreate()
    return globals()['sparkSessionSingletonInstance']


--- a/examples/src/main/scala/org/apache/spark/examples/ml/AFTSurvivalRegressionExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/AFTSurvivalRegressionExample.scala
@ -30,7 +30,10 @@ import org.apache.spark.sql.SparkSession
 object AFTSurvivalRegressionExample {

  def main(args: Array[String]): Unit = {
-    val spark = SparkSession.builder.appName("AFTSurvivalRegressionExample").getOrCreate()
+    val spark = SparkSession
+      .builder
+      .appName("AFTSurvivalRegressionExample")
+      .getOrCreate()

    // $example on$
    val training = spark.createDataFrame(Seq(
--- a/examples/src/main/scala/org/apache/spark/examples/ml/ALSExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/ALSExample.scala
@ -42,7 +42,10 @@ object ALSExample {
  // $example off$

  def main(args: Array[String]) {
-    val spark = SparkSession.builder.appName("ALSExample").getOrCreate()
+    val spark = SparkSession
+      .builder
+      .appName("ALSExample")
+      .getOrCreate()
    import spark.implicits._

    // $example on$
--- a/examples/src/main/scala/org/apache/spark/examples/ml/BinarizerExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/BinarizerExample.scala
@ -25,7 +25,10 @@ import org.apache.spark.sql.{DataFrame, SparkSession}

 object BinarizerExample {
  def main(args: Array[String]): Unit = {
-    val spark = SparkSession.builder.appName("BinarizerExample").getOrCreate()
+    val spark = SparkSession
+      .builder
+      .appName("BinarizerExample")
+      .getOrCreate()
    // $example on$
    val data = Array((0, 0.1), (1, 0.8), (2, 0.2))
    val dataFrame: DataFrame = spark.createDataFrame(data).toDF("label", "feature")
--- a/examples/src/main/scala/org/apache/spark/examples/ml/BucketizerExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/BucketizerExample.scala
@ -25,7 +25,10 @@ import org.apache.spark.sql.SparkSession

 object BucketizerExample {
  def main(args: Array[String]): Unit = {
-    val spark = SparkSession.builder.appName("BucketizerExample").getOrCreate()
+    val spark = SparkSession
+      .builder
+      .appName("BucketizerExample")
+      .getOrCreate()

    // $example on$
    val splits = Array(Double.NegativeInfinity, -0.5, 0.0, 0.5, Double.PositiveInfinity)
--- a/examples/src/main/scala/org/apache/spark/examples/ml/ChiSqSelectorExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/ChiSqSelectorExample.scala
@ -26,7 +26,10 @@ import org.apache.spark.sql.SparkSession

 object ChiSqSelectorExample {
  def main(args: Array[String]) {
-    val spark = SparkSession.builder.appName("ChiSqSelectorExample").getOrCreate()
+    val spark = SparkSession
+      .builder
+      .appName("ChiSqSelectorExample")
+      .getOrCreate()
    import spark.implicits._

    // $example on$
--- a/examples/src/main/scala/org/apache/spark/examples/ml/CountVectorizerExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/CountVectorizerExample.scala
@ -25,7 +25,10 @@ import org.apache.spark.sql.SparkSession

 object CountVectorizerExample {
  def main(args: Array[String]) {
-    val spark = SparkSession.builder.appName("CounterVectorizerExample").getOrCreate()
+    val spark = SparkSession
+      .builder
+      .appName("CounterVectorizerExample")
+      .getOrCreate()

    // $example on$
    val df = spark.createDataFrame(Seq(
--- a/examples/src/main/scala/org/apache/spark/examples/ml/DCTExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/DCTExample.scala
@ -26,7 +26,10 @@ import org.apache.spark.sql.SparkSession

 object DCTExample {
  def main(args: Array[String]): Unit = {
-    val spark = SparkSession.builder.appName("DCTExample").getOrCreate()
+    val spark = SparkSession
+      .builder
+      .appName("DCTExample")
+      .getOrCreate()

    // $example on$
    val data = Seq(
--- a/examples/src/main/scala/org/apache/spark/examples/ml/DataFrameExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/DataFrameExample.scala
@ -61,7 +61,10 @@ object DataFrameExample {
  }

  def run(params: Params) {
-    val spark = SparkSession.builder.appName(s"DataFrameExample with $params").getOrCreate()
+    val spark = SparkSession
+      .builder
+      .appName(s"DataFrameExample with $params")
+      .getOrCreate()

    // Load input data
    println(s"Loading LIBSVM file with UDT from ${params.input}.")
--- a/examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeClassificationExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeClassificationExample.scala
@ -29,7 +29,10 @@ import org.apache.spark.sql.SparkSession

 object DecisionTreeClassificationExample {
  def main(args: Array[String]): Unit = {
-    val spark = SparkSession.builder.appName("DecisionTreeClassificationExample").getOrCreate()
+    val spark = SparkSession
+      .builder
+      .appName("DecisionTreeClassificationExample")
+      .getOrCreate()
    // $example on$
    // Load the data stored in LIBSVM format as a DataFrame.
    val data = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
--- a/examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeExample.scala
@ -167,7 +167,9 @@ object DecisionTreeExample {
      testInput: String,
      algo: String,
      fracTest: Double): (DataFrame, DataFrame) = {
-    val spark = SparkSession.builder.getOrCreate()
+    val spark = SparkSession
+      .builder
+      .getOrCreate()

    // Load training data
    val origExamples: DataFrame = loadData(spark, input, dataFormat)
--- a/examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeRegressionExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeRegressionExample.scala
@ -29,7 +29,10 @@ import org.apache.spark.sql.SparkSession

 object DecisionTreeRegressionExample {
  def main(args: Array[String]): Unit = {
-    val spark = SparkSession.builder.appName("DecisionTreeRegressionExample").getOrCreate()
+    val spark = SparkSession
+      .builder
+      .appName("DecisionTreeRegressionExample")
+      .getOrCreate()

    // $example on$
    // Load the data stored in LIBSVM format as a DataFrame.
--- a/examples/src/main/scala/org/apache/spark/examples/ml/DeveloperApiExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/DeveloperApiExample.scala
@ -37,7 +37,10 @@ import org.apache.spark.sql.{Dataset, Row, SparkSession}
 object DeveloperApiExample {

  def main(args: Array[String]) {
-    val spark = SparkSession.builder.appName("DeveloperApiExample").getOrCreate()
+    val spark = SparkSession
+      .builder
+      .appName("DeveloperApiExample")
+      .getOrCreate()
    import spark.implicits._

    // Prepare training data.
--- a/examples/src/main/scala/org/apache/spark/examples/ml/ElementwiseProductExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/ElementwiseProductExample.scala
@ -26,7 +26,10 @@ import org.apache.spark.sql.SparkSession

 object ElementwiseProductExample {
  def main(args: Array[String]): Unit = {
-    val spark = SparkSession.builder.appName("ElementwiseProductExample").getOrCreate()
+    val spark = SparkSession
+      .builder
+      .appName("ElementwiseProductExample")
+      .getOrCreate()

    // $example on$
    // Create some vector data; also works for sparse vectors
--- a/examples/src/main/scala/org/apache/spark/examples/ml/EstimatorTransformerParamExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/EstimatorTransformerParamExample.scala
@ -29,7 +29,10 @@ import org.apache.spark.sql.SparkSession
 object EstimatorTransformerParamExample {

  def main(args: Array[String]): Unit = {
-    val spark = SparkSession.builder.appName("EstimatorTransformerParamExample").getOrCreate()
+    val spark = SparkSession
+      .builder
+      .appName("EstimatorTransformerParamExample")
+      .getOrCreate()

    // $example on$
    // Prepare training data from a list of (label, features) tuples.
--- a/examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeClassifierExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeClassifierExample.scala
@ -28,7 +28,10 @@ import org.apache.spark.sql.SparkSession

 object GradientBoostedTreeClassifierExample {
  def main(args: Array[String]): Unit = {
-    val spark = SparkSession.builder.appName("GradientBoostedTreeClassifierExample").getOrCreate()
+    val spark = SparkSession
+      .builder
+      .appName("GradientBoostedTreeClassifierExample")
+      .getOrCreate()

    // $example on$
    // Load and parse the data file, converting it to a DataFrame.
--- a/Show more
+++ b/Show more