[SPARK-10254] [ML] Removes Guava dependencies in spark.ml.feature JavaTests

* Replaces `com.google.common` dependencies with `java.util.Arrays`
* Small clean up in `JavaNormalizerSuite`

Author: Feynman Liang <fliang@databricks.com>

Closes #8445 from feynmanliang/SPARK-10254.

mllib/src/test/java/org/apache/spark/ml/feature/JavaBucketizerSuite.java

@@ -17,7 +17,8 @@
 
 package org.apache.spark.ml.feature;
 
-import com.google.common.collect.Lists;
+import java.util.Arrays;
+
 import org.junit.After;
 import org.junit.Assert;
 import org.junit.Before;
@@ -54,7 +55,7 @@ public class JavaBucketizerSuite {
   public void bucketizerTest() {
     double[] splits = {-0.5, 0.0, 0.5};
 
-    JavaRDD<Row> data = jsc.parallelize(Lists.newArrayList(
+    JavaRDD<Row> data = jsc.parallelize(Arrays.asList(
       RowFactory.create(-0.5),
       RowFactory.create(-0.3),
       RowFactory.create(0.0),

mllib/src/test/java/org/apache/spark/ml/feature/JavaDCTSuite.java

@@ -17,7 +17,8 @@
 
 package org.apache.spark.ml.feature;
 
-import com.google.common.collect.Lists;
+import java.util.Arrays;
+
 import edu.emory.mathcs.jtransforms.dct.DoubleDCT_1D;
 import org.junit.After;
 import org.junit.Assert;
@@ -56,7 +57,7 @@ public class JavaDCTSuite {
   @Test
   public void javaCompatibilityTest() {
     double[] input = new double[] {1D, 2D, 3D, 4D};
-    JavaRDD<Row> data = jsc.parallelize(Lists.newArrayList(
+    JavaRDD<Row> data = jsc.parallelize(Arrays.asList(
       RowFactory.create(Vectors.dense(input))
     ));
     DataFrame dataset = jsql.createDataFrame(data, new StructType(new StructField[]{

mllib/src/test/java/org/apache/spark/ml/feature/JavaHashingTFSuite.java

@@ -17,7 +17,8 @@
 
 package org.apache.spark.ml.feature;
 
-import com.google.common.collect.Lists;
+import java.util.Arrays;
+
 import org.junit.After;
 import org.junit.Assert;
 import org.junit.Before;
@@ -54,7 +55,7 @@ public class JavaHashingTFSuite {
 
   @Test
   public void hashingTF() {
-    JavaRDD<Row> jrdd = jsc.parallelize(Lists.newArrayList(
+    JavaRDD<Row> jrdd = jsc.parallelize(Arrays.asList(
       RowFactory.create(0.0, "Hi I heard about Spark"),
       RowFactory.create(0.0, "I wish Java could use case classes"),
       RowFactory.create(1.0, "Logistic regression models are neat")

mllib/src/test/java/org/apache/spark/ml/feature/JavaNormalizerSuite.java

@@ -17,15 +17,15 @@
 
 package org.apache.spark.ml.feature;
 
-import java.util.List;
+import java.util.Arrays;
 
-import com.google.common.collect.Lists;
 import org.junit.After;
 import org.junit.Before;
 import org.junit.Test;
 
 import org.apache.spark.api.java.JavaSparkContext;
 import org.apache.spark.mllib.linalg.Vectors;
+import org.apache.spark.api.java.JavaRDD;
 import org.apache.spark.sql.DataFrame;
 import org.apache.spark.sql.SQLContext;
 
@@ -48,13 +48,12 @@ public class JavaNormalizerSuite {
   @Test
   public void normalizer() {
     // The tests are to check Java compatibility.
-    List<VectorIndexerSuite.FeatureData> points = Lists.newArrayList(
+    JavaRDD<VectorIndexerSuite.FeatureData> points = jsc.parallelize(Arrays.asList(
       new VectorIndexerSuite.FeatureData(Vectors.dense(0.0, -2.0)),
       new VectorIndexerSuite.FeatureData(Vectors.dense(1.0, 3.0)),
       new VectorIndexerSuite.FeatureData(Vectors.dense(1.0, 4.0))
-    );
-    DataFrame dataFrame = jsql.createDataFrame(jsc.parallelize(points, 2),
-      VectorIndexerSuite.FeatureData.class);
+    ));
+    DataFrame dataFrame = jsql.createDataFrame(points, VectorIndexerSuite.FeatureData.class);
     Normalizer normalizer = new Normalizer()
       .setInputCol("features")
       .setOutputCol("normFeatures");

mllib/src/test/java/org/apache/spark/ml/feature/JavaPCASuite.java

@@ -18,11 +18,11 @@
 package org.apache.spark.ml.feature;
 
 import java.io.Serializable;
+import java.util.Arrays;
 import java.util.List;
 
 import scala.Tuple2;
 
-import com.google.common.collect.Lists;
 import org.junit.After;
 import org.junit.Assert;
 import org.junit.Before;
@@ -78,7 +78,7 @@ public class JavaPCASuite implements Serializable {
 
   @Test
   public void testPCA() {
-    List<Vector> points = Lists.newArrayList(
+    List<Vector> points = Arrays.asList(
       Vectors.sparse(5, new int[]{1, 3}, new double[]{1.0, 7.0}),
       Vectors.dense(2.0, 0.0, 3.0, 4.0, 5.0),
       Vectors.dense(4.0, 0.0, 0.0, 6.0, 7.0)

mllib/src/test/java/org/apache/spark/ml/feature/JavaPolynomialExpansionSuite.java

@@ -17,7 +17,8 @@
 
 package org.apache.spark.ml.feature;
 
-import com.google.common.collect.Lists;
+import java.util.Arrays;
+
 import org.junit.After;
 import org.junit.Assert;
 import org.junit.Before;
@@ -59,7 +60,7 @@ public class JavaPolynomialExpansionSuite {
       .setOutputCol("polyFeatures")
       .setDegree(3);
 
-    JavaRDD<Row> data = jsc.parallelize(Lists.newArrayList(
+    JavaRDD<Row> data = jsc.parallelize(Arrays.asList(
       RowFactory.create(
         Vectors.dense(-2.0, 2.3),
         Vectors.dense(-2.0, 4.0, -8.0, 2.3, -4.6, 9.2, 5.29, -10.58, 12.17)

mllib/src/test/java/org/apache/spark/ml/feature/JavaStandardScalerSuite.java

@@ -17,9 +17,9 @@
 
 package org.apache.spark.ml.feature;
 
+import java.util.Arrays;
 import java.util.List;
 
-import com.google.common.collect.Lists;
 import org.junit.After;
 import org.junit.Before;
 import org.junit.Test;
@@ -48,7 +48,7 @@ public class JavaStandardScalerSuite {
   @Test
   public void standardScaler() {
     // The tests are to check Java compatibility.
-    List<VectorIndexerSuite.FeatureData> points = Lists.newArrayList(
+    List<VectorIndexerSuite.FeatureData> points = Arrays.asList(
       new VectorIndexerSuite.FeatureData(Vectors.dense(0.0, -2.0)),
       new VectorIndexerSuite.FeatureData(Vectors.dense(1.0, 3.0)),
       new VectorIndexerSuite.FeatureData(Vectors.dense(1.0, 4.0))

mllib/src/test/java/org/apache/spark/ml/feature/JavaTokenizerSuite.java

@@ -17,7 +17,8 @@
 
 package org.apache.spark.ml.feature;
 
-import com.google.common.collect.Lists;
+import java.util.Arrays;
+
 import org.junit.After;
 import org.junit.Assert;
 import org.junit.Before;
@@ -54,7 +55,8 @@ public class JavaTokenizerSuite {
       .setGaps(true)
       .setMinTokenLength(3);
 
-    JavaRDD<TokenizerTestData> rdd = jsc.parallelize(Lists.newArrayList(
+
+    JavaRDD<TokenizerTestData> rdd = jsc.parallelize(Arrays.asList(
       new TokenizerTestData("Test of tok.", new String[] {"Test", "tok."}),
       new TokenizerTestData("Te,st.  punct", new String[] {"Te,st.", "punct"})
     ));

mllib/src/test/java/org/apache/spark/ml/feature/JavaVectorIndexerSuite.java

@@ -18,6 +18,7 @@
 package org.apache.spark.ml.feature;
 
 import java.io.Serializable;
+import java.util.Arrays;
 import java.util.List;
 import java.util.Map;
 
@@ -26,8 +27,6 @@ import org.junit.Assert;
 import org.junit.Before;
 import org.junit.Test;
 
-import com.google.common.collect.Lists;
-
 import org.apache.spark.api.java.JavaSparkContext;
 import org.apache.spark.ml.feature.VectorIndexerSuite.FeatureData;
 import org.apache.spark.mllib.linalg.Vectors;
@@ -52,7 +51,7 @@ public class JavaVectorIndexerSuite implements Serializable {
   @Test
   public void vectorIndexerAPI() {
     // The tests are to check Java compatibility.
-    List<FeatureData> points = Lists.newArrayList(
+    List<FeatureData> points = Arrays.asList(
       new FeatureData(Vectors.dense(0.0, -2.0)),
       new FeatureData(Vectors.dense(1.0, 3.0)),
       new FeatureData(Vectors.dense(1.0, 4.0))

mllib/src/test/java/org/apache/spark/ml/feature/JavaVectorSlicerSuite.java

@@ -17,7 +17,7 @@
 
 package org.apache.spark.ml.feature;
 
-import com.google.common.collect.Lists;
+import java.util.Arrays;
 
 import org.junit.After;
 import org.junit.Assert;
@@ -63,7 +63,7 @@ public class JavaVectorSlicerSuite {
     };
     AttributeGroup group = new AttributeGroup("userFeatures", attrs);
 
-    JavaRDD<Row> jrdd = jsc.parallelize(Lists.newArrayList(
+    JavaRDD<Row> jrdd = jsc.parallelize(Arrays.asList(
       RowFactory.create(Vectors.sparse(3, new int[]{0, 1}, new double[]{-2.0, 2.3})),
       RowFactory.create(Vectors.dense(-2.0, 2.3, 0.0))
     ));

mllib/src/test/java/org/apache/spark/ml/feature/JavaWord2VecSuite.java

@@ -17,7 +17,8 @@
 
 package org.apache.spark.ml.feature;
 
-import com.google.common.collect.Lists;
+import java.util.Arrays;
+
 import org.junit.After;
 import org.junit.Assert;
 import org.junit.Before;
@@ -50,10 +51,10 @@ public class JavaWord2VecSuite {
 
   @Test
   public void testJavaWord2Vec() {
-    JavaRDD<Row> jrdd = jsc.parallelize(Lists.newArrayList(
-      RowFactory.create(Lists.newArrayList("Hi I heard about Spark".split(" "))),
-      RowFactory.create(Lists.newArrayList("I wish Java could use case classes".split(" "))),
-      RowFactory.create(Lists.newArrayList("Logistic regression models are neat".split(" ")))
+    JavaRDD<Row> jrdd = jsc.parallelize(Arrays.asList(
+      RowFactory.create(Arrays.asList("Hi I heard about Spark".split(" "))),
+      RowFactory.create(Arrays.asList("I wish Java could use case classes".split(" "))),
+      RowFactory.create(Arrays.asList("Logistic regression models are neat".split(" ")))
     ));
     StructType schema = new StructType(new StructField[]{
       new StructField("text", new ArrayType(DataTypes.StringType, true), false, Metadata.empty())