passed test compile

Author: mengxr

mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala

@@ -54,6 +54,12 @@ trait Vector extends Serializable {
    * Converts the instance to a breeze vector.
    */
   private[mllib] def toBreeze: BV[Double]
+
+  /**
+   * Gets the value of the ith element.
+   * @param i index
+   */
+  private[mllib] def apply(i: Int): Double = toBreeze(i)
 }
 
 /**

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

@@ -19,6 +19,7 @@
 
 import org.apache.spark.api.java.JavaRDD;
 import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.mllib.linalg.Vectors;
 import org.apache.spark.mllib.regression.LabeledPoint;
 import org.junit.After;
 import org.junit.Assert;
@@ -45,12 +46,12 @@ public void tearDown() {
   }
 
   private static final List<LabeledPoint> POINTS = Arrays.asList(
-    new LabeledPoint(0, new double[] {1.0, 0.0, 0.0}),
-    new LabeledPoint(0, new double[] {2.0, 0.0, 0.0}),
-    new LabeledPoint(1, new double[] {0.0, 1.0, 0.0}),
-    new LabeledPoint(1, new double[] {0.0, 2.0, 0.0}),
-    new LabeledPoint(2, new double[] {0.0, 0.0, 1.0}),
-    new LabeledPoint(2, new double[] {0.0, 0.0, 2.0})
+    new LabeledPoint(0, Vectors.dense(1.0, 0.0, 0.0)),
+    new LabeledPoint(0, Vectors.dense(2.0, 0.0, 0.0)),
+    new LabeledPoint(1, Vectors.dense(0.0, 1.0, 0.0)),
+    new LabeledPoint(1, Vectors.dense(0.0, 2.0, 0.0)),
+    new LabeledPoint(2, Vectors.dense(0.0, 0.0, 1.0)),
+    new LabeledPoint(2, Vectors.dense(0.0, 0.0, 2.0))
   );
 
   private int validatePrediction(List<LabeledPoint> points, NaiveBayesModel model) {

mllib/src/test/java/org/apache/spark/mllib/linalg/JavaVectorsSuite.java

@@ -19,10 +19,10 @@
 
 import java.io.Serializable;
 
-import com.google.common.collect.Lists;
-
 import scala.Tuple2;
 
+import com.google.common.collect.Lists;
+
 import org.junit.Test;
 import static org.junit.Assert.*;
 
@@ -36,7 +36,7 @@ public void denseArrayConstruction() {
 
   @Test
   public void sparseArrayConstruction() {
-    Vector v = Vectors.sparse(3, Lists.newArrayList(
+    Vector v = Vectors.sparse(3, Lists.<Tuple2<Integer, Double>>newArrayList(
         new Tuple2<Integer, Double>(0, 2.0),
         new Tuple2<Integer, Double>(2, 3.0)));
     assertArrayEquals(new double[]{2.0, 0.0, 3.0}, v.toArray(), 0.0);

mllib/src/test/scala/org/apache/spark/mllib/classification/LogisticRegressionSuite.scala

@@ -112,7 +112,7 @@ class LogisticRegressionSuite extends FunSuite with LocalSparkContext with Shoul
     val testData = LogisticRegressionSuite.generateLogisticInput(A, B, nPoints, 42)
 
     val initialB = -1.0
-    val initialWeights = Array(initialB)
+    val initialWeights = Vectors.dense(initialB)
 
     val testRDD = sc.parallelize(testData, 2)
     testRDD.cache()

mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala

@@ -19,11 +19,11 @@ package org.apache.spark.mllib.classification
 
 import scala.util.Random
 
-import org.scalatest.BeforeAndAfterAll
 import org.scalatest.FunSuite
 
 import org.apache.spark.mllib.regression.LabeledPoint
 import org.apache.spark.mllib.util.LocalSparkContext
+import org.apache.spark.mllib.linalg.Vectors
 
 object NaiveBayesSuite {
 
@@ -54,7 +54,7 @@ object NaiveBayesSuite {
         if (rnd.nextDouble() < _theta(y)(j)) 1 else 0
       }
 
-      LabeledPoint(y, xi)
+      LabeledPoint(y, Vectors.dense(xi))
     }
   }
 }

mllib/src/test/scala/org/apache/spark/mllib/classification/SVMSuite.scala

@@ -20,14 +20,14 @@ package org.apache.spark.mllib.classification
 import scala.util.Random
 import scala.collection.JavaConversions._
 
-import org.scalatest.BeforeAndAfterAll
 import org.scalatest.FunSuite
 
 import org.jblas.DoubleMatrix
 
 import org.apache.spark.SparkException
 import org.apache.spark.mllib.regression._
 import org.apache.spark.mllib.util.LocalSparkContext
+import org.apache.spark.mllib.linalg.Vectors
 
 object SVMSuite {
 
@@ -54,7 +54,7 @@ object SVMSuite {
         intercept + 0.01 * rnd.nextGaussian()
       if (yD < 0) 0.0 else 1.0
     }
-    y.zip(x).map(p => LabeledPoint(p._1, p._2))
+    y.zip(x).map(p => LabeledPoint(p._1, Vectors.dense(p._2)))
   }
 
 }
@@ -110,7 +110,7 @@ class SVMSuite extends FunSuite with LocalSparkContext {
 
     val initialB = -1.0
     val initialC = -1.0
-    val initialWeights = Array(initialB,initialC)
+    val initialWeights = Vectors.dense(initialB, initialC)
 
     val testRDD = sc.parallelize(testData, 2)
     testRDD.cache()

mllib/src/test/scala/org/apache/spark/mllib/optimization/GradientDescentSuite.scala

@@ -20,13 +20,12 @@ package org.apache.spark.mllib.optimization
 import scala.util.Random
 import scala.collection.JavaConversions._
 
-import org.scalatest.BeforeAndAfterAll
 import org.scalatest.FunSuite
 import org.scalatest.matchers.ShouldMatchers
 
-import org.apache.spark.SparkContext
 import org.apache.spark.mllib.regression._
 import org.apache.spark.mllib.util.LocalSparkContext
+import org.apache.spark.mllib.linalg.Vectors
 
 object GradientDescentSuite {
 
@@ -58,7 +57,7 @@ object GradientDescentSuite {
       if (yVal > 0) 1 else 0
     }
 
-    val testData = (0 until nPoints).map(i => LabeledPoint(y(i), Array(x1(i))))
+    val testData = (0 until nPoints).map(i => LabeledPoint(y(i), Vectors.dense(Array(x1(i)))))
     testData
   }
 }
@@ -83,11 +82,11 @@ class GradientDescentSuite extends FunSuite with LocalSparkContext with ShouldMa
     // Add a extra variable consisting of all 1.0's for the intercept.
     val testData = GradientDescentSuite.generateGDInput(A, B, nPoints, 42)
     val data = testData.map { case LabeledPoint(label, features) =>
-      label -> Array(1.0, features: _*)
+      label -> Vectors.dense(1.0, features.toArray: _*)
     }
 
     val dataRDD = sc.parallelize(data, 2).cache()
-    val initialWeightsWithIntercept = Array(1.0, initialWeights: _*)
+    val initialWeightsWithIntercept = Vectors.dense(0.0, initialWeights: _*)
 
     val (_, loss) = GradientDescent.runMiniBatchSGD(
       dataRDD,
@@ -113,13 +112,13 @@ class GradientDescentSuite extends FunSuite with LocalSparkContext with ShouldMa
     // Add a extra variable consisting of all 1.0's for the intercept.
     val testData = GradientDescentSuite.generateGDInput(2.0, -1.5, 10000, 42)
     val data = testData.map { case LabeledPoint(label, features) =>
-      label -> Array(1.0, features: _*)
+      label -> Vectors.dense(1.0, features.toArray: _*)
     }
 
     val dataRDD = sc.parallelize(data, 2).cache()
 
     // Prepare non-zero weights
-    val initialWeightsWithIntercept = Array(1.0, 0.5)
+    val initialWeightsWithIntercept = Vectors.dense(1.0, 0.5)
 
     val regParam0 = 0
     val (newWeights0, loss0) = GradientDescent.runMiniBatchSGD(

mllib/src/test/scala/org/apache/spark/mllib/regression/LassoSuite.scala

@@ -17,11 +17,9 @@
 
 package org.apache.spark.mllib.regression
 
-
-import org.scalatest.BeforeAndAfterAll
 import org.scalatest.FunSuite
 
-import org.apache.spark.SparkContext
+import org.apache.spark.mllib.linalg.Vectors
 import org.apache.spark.mllib.util.{LinearDataGenerator, LocalSparkContext}
 
 class LassoSuite extends FunSuite with LocalSparkContext {
@@ -51,7 +49,6 @@ class LassoSuite extends FunSuite with LocalSparkContext {
     ls.optimizer.setStepSize(1.0).setRegParam(0.01).setNumIterations(20)
 
     val model = ls.run(testRDD)
-
     val weight0 = model.weights(0)
     val weight1 = model.weights(1)
     assert(model.intercept >= 1.9 && model.intercept <= 2.1, model.intercept + " not in [1.9, 2.1]")
@@ -79,7 +76,7 @@ class LassoSuite extends FunSuite with LocalSparkContext {
 
     val initialB = -1.0
     val initialC = -1.0
-    val initialWeights = Array(initialB,initialC)
+    val initialWeights = Vectors.dense(Array(initialB, initialC))
 
     val testRDD = sc.parallelize(testData, 2)
     testRDD.cache()
@@ -88,7 +85,6 @@ class LassoSuite extends FunSuite with LocalSparkContext {
     ls.optimizer.setStepSize(1.0).setRegParam(0.01).setNumIterations(20)
 
     val model = ls.run(testRDD, initialWeights)
-
     val weight0 = model.weights(0)
     val weight1 = model.weights(1)
     assert(model.intercept >= 1.9 && model.intercept <= 2.1, model.intercept + " not in [1.9, 2.1]")

mllib/src/test/scala/org/apache/spark/mllib/regression/LinearRegressionSuite.scala

@@ -40,11 +40,12 @@ class LinearRegressionSuite extends FunSuite with LocalSparkContext {
     linReg.optimizer.setNumIterations(1000).setStepSize(1.0)
 
     val model = linReg.run(testRDD)
-
     assert(model.intercept >= 2.5 && model.intercept <= 3.5)
-    assert(model.weights.length === 2)
-    assert(model.weights(0) >= 9.0 && model.weights(0) <= 11.0)
-    assert(model.weights(1) >= 9.0 && model.weights(1) <= 11.0)
+
+    val weights = model.weights
+    assert(weights.size === 2)
+    assert(weights(0) >= 9.0 && weights(0) <= 11.0)
+    assert(weights(1) >= 9.0 && weights(1) <= 11.0)
 
     val validationData = LinearDataGenerator.generateLinearInput(
       3.0, Array(10.0, 10.0), 100, 17)
@@ -67,9 +68,11 @@ class LinearRegressionSuite extends FunSuite with LocalSparkContext {
     val model = linReg.run(testRDD)
 
     assert(model.intercept === 0.0)
-    assert(model.weights.length === 2)
-    assert(model.weights(0) >= 9.0 && model.weights(0) <= 11.0)
-    assert(model.weights(1) >= 9.0 && model.weights(1) <= 11.0)
+
+    val weights = model.weights
+    assert(weights.size === 2)
+    assert(weights(0) >= 9.0 && weights(0) <= 11.0)
+    assert(weights(1) >= 9.0 && weights(1) <= 11.0)
 
     val validationData = LinearDataGenerator.generateLinearInput(
       0.0, Array(10.0, 10.0), 100, 17)