[SPARK-15296][MLLIB] Refactor All Java Tests that use SparkSession

## What changes were proposed in this pull request?
Refactor All Java Tests that use SparkSession, to extend SharedSparkSesion

## How was this patch tested?
Existing Tests

Author: Sandeep Singh <[email protected]>

Closes apache#13101 from techaddict/SPARK-15296.

Author: techaddict

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

@@ -37,7 +37,7 @@ public class JavaGaussianMixtureExample {
 
   public static void main(String[] args) {
 
-    // Creates a SparkSession 
+    // Creates a SparkSession
     SparkSession spark = SparkSession
             .builder()
             .appName("JavaGaussianMixtureExample")

mllib/src/test/java/org/apache/spark/SharedSparkSession.java

@@ -0,0 +1,48 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark;
+
+import java.io.IOException;
+import java.io.Serializable;
+
+import org.junit.After;
+import org.junit.Before;
+
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.SparkSession;
+
+public abstract class SharedSparkSession implements Serializable {
+
+  protected transient SparkSession spark;
+  protected transient JavaSparkContext jsc;
+
+  @Before
+  public void setUp() throws IOException {
+    spark = SparkSession.builder()
+      .master("local[2]")
+      .appName(getClass().getSimpleName())
+      .getOrCreate();
+    jsc = new JavaSparkContext(spark.sparkContext());
+  }
+
+  @After
+  public void tearDown() {
+    spark.stop();
+    spark = null;
+  }
+}

mllib/src/test/java/org/apache/spark/ml/JavaPipelineSuite.java

@@ -17,47 +17,34 @@
 
 package org.apache.spark.ml;
 
-import org.junit.After;
-import org.junit.Before;
+import java.io.IOException;
+
 import org.junit.Test;
 
+import org.apache.spark.SharedSparkSession;
 import org.apache.spark.api.java.JavaRDD;
-import org.apache.spark.api.java.JavaSparkContext;
 import org.apache.spark.ml.classification.LogisticRegression;
 import static org.apache.spark.ml.classification.LogisticRegressionSuite.generateLogisticInputAsList;
 import org.apache.spark.ml.feature.LabeledPoint;
 import org.apache.spark.ml.feature.StandardScaler;
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.Row;
-import org.apache.spark.sql.SparkSession;
 
 /**
  * Test Pipeline construction and fitting in Java.
  */
-public class JavaPipelineSuite {
+public class JavaPipelineSuite extends SharedSparkSession {
 
-  private transient SparkSession spark;
-  private transient JavaSparkContext jsc;
   private transient Dataset<Row> dataset;
 
-  @Before
-  public void setUp() {
-    spark = SparkSession.builder()
-      .master("local")
-      .appName("JavaPipelineSuite")
-      .getOrCreate();
-    jsc = new JavaSparkContext(spark.sparkContext());
+  @Override
+  public void setUp() throws IOException {
+    super.setUp();
     JavaRDD<LabeledPoint> points =
       jsc.parallelize(generateLogisticInputAsList(1.0, 1.0, 100, 42), 2);
     dataset = spark.createDataFrame(points, LabeledPoint.class);
   }
 
-  @After
-  public void tearDown() {
-    spark.stop();
-    spark = null;
-  }
-
   @Test
   public void pipeline() {
     StandardScaler scaler = new StandardScaler()

mllib/src/test/java/org/apache/spark/ml/classification/JavaDecisionTreeClassifierSuite.java

@@ -17,42 +17,19 @@
 
 package org.apache.spark.ml.classification;
 
-import java.io.Serializable;
 import java.util.HashMap;
 import java.util.Map;
 
-import org.junit.After;
-import org.junit.Before;
 import org.junit.Test;
 
+import org.apache.spark.SharedSparkSession;
 import org.apache.spark.api.java.JavaRDD;
-import org.apache.spark.api.java.JavaSparkContext;
-import org.apache.spark.ml.classification.LogisticRegressionSuite;
 import org.apache.spark.ml.feature.LabeledPoint;
 import org.apache.spark.ml.tree.impl.TreeTests;
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.Row;
-import org.apache.spark.sql.SparkSession;
 
-public class JavaDecisionTreeClassifierSuite implements Serializable {
-
-  private transient SparkSession spark;
-  private transient JavaSparkContext jsc;
-
-  @Before
-  public void setUp() {
-    spark = SparkSession.builder()
-      .master("local")
-      .appName("JavaDecisionTreeClassifierSuite")
-      .getOrCreate();
-    jsc = new JavaSparkContext(spark.sparkContext());
-  }
-
-  @After
-  public void tearDown() {
-    spark.stop();
-    spark = null;
-  }
+public class JavaDecisionTreeClassifierSuite extends SharedSparkSession {
 
   @Test
   public void runDT() {

mllib/src/test/java/org/apache/spark/ml/classification/JavaGBTClassifierSuite.java

@@ -17,43 +17,19 @@
 
 package org.apache.spark.ml.classification;
 
-import java.io.Serializable;
 import java.util.HashMap;
 import java.util.Map;
 
-import org.junit.After;
-import org.junit.Before;
 import org.junit.Test;
 
+import org.apache.spark.SharedSparkSession;
 import org.apache.spark.api.java.JavaRDD;
-import org.apache.spark.api.java.JavaSparkContext;
-import org.apache.spark.ml.classification.LogisticRegressionSuite;
 import org.apache.spark.ml.feature.LabeledPoint;
 import org.apache.spark.ml.tree.impl.TreeTests;
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.Row;
-import org.apache.spark.sql.SparkSession;
 
-
-public class JavaGBTClassifierSuite implements Serializable {
-
-  private transient SparkSession spark;
-  private transient JavaSparkContext jsc;
-
-  @Before
-  public void setUp() {
-    spark = SparkSession.builder()
-      .master("local")
-      .appName("JavaGBTClassifierSuite")
-      .getOrCreate();
-    jsc = new JavaSparkContext(spark.sparkContext());
-  }
-
-  @After
-  public void tearDown() {
-    spark.stop();
-    spark = null;
-  }
+public class JavaGBTClassifierSuite extends SharedSparkSession {
 
   @Test
   public void runDT() {

mllib/src/test/java/org/apache/spark/ml/classification/JavaLogisticRegressionSuite.java

@@ -17,52 +17,36 @@
 
 package org.apache.spark.ml.classification;
 
-import java.io.Serializable;
+import java.io.IOException;
 import java.util.List;
 
-import org.junit.After;
 import org.junit.Assert;
-import org.junit.Before;
 import org.junit.Test;
 
+import org.apache.spark.SharedSparkSession;
 import org.apache.spark.api.java.JavaRDD;
-import org.apache.spark.api.java.JavaSparkContext;
 import static org.apache.spark.ml.classification.LogisticRegressionSuite.generateLogisticInputAsList;
 import org.apache.spark.ml.feature.LabeledPoint;
 import org.apache.spark.ml.linalg.Vector;
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.Row;
-import org.apache.spark.sql.SparkSession;
 
-public class JavaLogisticRegressionSuite implements Serializable {
+public class JavaLogisticRegressionSuite extends SharedSparkSession {
 
-  private transient SparkSession spark;
-  private transient JavaSparkContext jsc;
   private transient Dataset<Row> dataset;
 
   private transient JavaRDD<LabeledPoint> datasetRDD;
   private double eps = 1e-5;
 
-  @Before
-  public void setUp() {
-    spark = SparkSession.builder()
-      .master("local")
-      .appName("JavaLogisticRegressionSuite")
-      .getOrCreate();
-    jsc = new JavaSparkContext(spark.sparkContext());
-
+  @Override
+  public void setUp() throws IOException {
+    super.setUp();
     List<LabeledPoint> points = generateLogisticInputAsList(1.0, 1.0, 100, 42);
     datasetRDD = jsc.parallelize(points, 2);
     dataset = spark.createDataFrame(datasetRDD, LabeledPoint.class);
     dataset.createOrReplaceTempView("dataset");
   }
 
-  @After
-  public void tearDown() {
-    spark.stop();
-    spark = null;
-  }
-
   @Test
   public void logisticRegressionDefaultParams() {
     LogisticRegression lr = new LogisticRegression();

mllib/src/test/java/org/apache/spark/ml/classification/JavaMultilayerPerceptronClassifierSuite.java

@@ -17,38 +17,19 @@
 
 package org.apache.spark.ml.classification;
 
-import java.io.Serializable;
 import java.util.Arrays;
 import java.util.List;
 
-import org.junit.After;
 import org.junit.Assert;
-import org.junit.Before;
 import org.junit.Test;
 
+import org.apache.spark.SharedSparkSession;
 import org.apache.spark.ml.feature.LabeledPoint;
 import org.apache.spark.ml.linalg.Vectors;
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.Row;
-import org.apache.spark.sql.SparkSession;
 
-public class JavaMultilayerPerceptronClassifierSuite implements Serializable {
-
-  private transient SparkSession spark;
-
-  @Before
-  public void setUp() {
-    spark = SparkSession.builder()
-      .master("local")
-      .appName("JavaLogisticRegressionSuite")
-      .getOrCreate();
-  }
-
-  @After
-  public void tearDown() {
-    spark.stop();
-    spark = null;
-  }
+public class JavaMultilayerPerceptronClassifierSuite extends SharedSparkSession {
 
   @Test
   public void testMLPC() {

mllib/src/test/java/org/apache/spark/ml/classification/JavaNaiveBayesSuite.java

@@ -17,43 +17,24 @@
 
 package org.apache.spark.ml.classification;
 
-import java.io.Serializable;
 import java.util.Arrays;
 import java.util.List;
 
-import org.junit.After;
-import org.junit.Before;
 import org.junit.Test;
 import static org.junit.Assert.assertEquals;
 
+import org.apache.spark.SharedSparkSession;
 import org.apache.spark.ml.linalg.VectorUDT;
 import org.apache.spark.ml.linalg.Vectors;
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.Row;
 import org.apache.spark.sql.RowFactory;
-import org.apache.spark.sql.SparkSession;
 import org.apache.spark.sql.types.DataTypes;
 import org.apache.spark.sql.types.Metadata;
 import org.apache.spark.sql.types.StructField;
 import org.apache.spark.sql.types.StructType;
 
-public class JavaNaiveBayesSuite implements Serializable {
-
-  private transient SparkSession spark;
-
-  @Before
-  public void setUp() {
-    spark = SparkSession.builder()
-      .master("local")
-      .appName("JavaLogisticRegressionSuite")
-      .getOrCreate();
-  }
-
-  @After
-  public void tearDown() {
-    spark.stop();
-    spark = null;
-  }
+public class JavaNaiveBayesSuite extends SharedSparkSession {
 
   public void validatePrediction(Dataset<Row> predictionAndLabels) {
     for (Row r : predictionAndLabels.collectAsList()) {