diff options
Diffstat (limited to 'mllib/src/test/java/org')
5 files changed, 29 insertions, 35 deletions
diff --git a/mllib/src/test/java/org/apache/spark/mllib/classification/JavaNaiveBayesSuite.java b/mllib/src/test/java/org/apache/spark/mllib/classification/JavaNaiveBayesSuite.java index 073ded6f36..c80b1134ed 100644 --- a/mllib/src/test/java/org/apache/spark/mllib/classification/JavaNaiveBayesSuite.java +++ b/mllib/src/test/java/org/apache/spark/mllib/classification/JavaNaiveBayesSuite.java @@ -19,6 +19,7 @@ package org.apache.spark.mllib.classification; 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 class JavaNaiveBayesSuite implements Serializable { } 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) { diff --git a/mllib/src/test/java/org/apache/spark/mllib/classification/JavaSVMSuite.java b/mllib/src/test/java/org/apache/spark/mllib/classification/JavaSVMSuite.java index 117e5eaa8b..4701a5e545 100644 --- a/mllib/src/test/java/org/apache/spark/mllib/classification/JavaSVMSuite.java +++ b/mllib/src/test/java/org/apache/spark/mllib/classification/JavaSVMSuite.java @@ -17,7 +17,6 @@ package org.apache.spark.mllib.classification; - import java.io.Serializable; import java.util.List; @@ -28,7 +27,6 @@ import org.junit.Test; import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaSparkContext; - import org.apache.spark.mllib.regression.LabeledPoint; public class JavaSVMSuite implements Serializable { @@ -94,5 +92,4 @@ public class JavaSVMSuite implements Serializable { int numAccurate = validatePrediction(validationData, model); Assert.assertTrue(numAccurate > nPoints * 4.0 / 5.0); } - } diff --git a/mllib/src/test/java/org/apache/spark/mllib/linalg/JavaVectorsSuite.java b/mllib/src/test/java/org/apache/spark/mllib/linalg/JavaVectorsSuite.java index 2c4d795f96..c6d8425ffc 100644 --- a/mllib/src/test/java/org/apache/spark/mllib/linalg/JavaVectorsSuite.java +++ b/mllib/src/test/java/org/apache/spark/mllib/linalg/JavaVectorsSuite.java @@ -19,10 +19,10 @@ package org.apache.spark.mllib.linalg; 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 class JavaVectorsSuite implements Serializable { @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); diff --git a/mllib/src/test/java/org/apache/spark/mllib/regression/JavaLassoSuite.java b/mllib/src/test/java/org/apache/spark/mllib/regression/JavaLassoSuite.java index f44b25cd44..f725924a2d 100644 --- a/mllib/src/test/java/org/apache/spark/mllib/regression/JavaLassoSuite.java +++ b/mllib/src/test/java/org/apache/spark/mllib/regression/JavaLassoSuite.java @@ -59,7 +59,7 @@ public class JavaLassoSuite implements Serializable { @Test public void runLassoUsingConstructor() { int nPoints = 10000; - double A = 2.0; + double A = 0.0; double[] weights = {-1.5, 1.0e-2}; JavaRDD<LabeledPoint> testRDD = sc.parallelize(LinearDataGenerator.generateLinearInputAsList(A, @@ -80,7 +80,7 @@ public class JavaLassoSuite implements Serializable { @Test public void runLassoUsingStaticMethods() { int nPoints = 10000; - double A = 2.0; + double A = 0.0; double[] weights = {-1.5, 1.0e-2}; JavaRDD<LabeledPoint> testRDD = sc.parallelize(LinearDataGenerator.generateLinearInputAsList(A, diff --git a/mllib/src/test/java/org/apache/spark/mllib/regression/JavaRidgeRegressionSuite.java b/mllib/src/test/java/org/apache/spark/mllib/regression/JavaRidgeRegressionSuite.java index 2fdd5fc8fd..03714ae7e4 100644 --- a/mllib/src/test/java/org/apache/spark/mllib/regression/JavaRidgeRegressionSuite.java +++ b/mllib/src/test/java/org/apache/spark/mllib/regression/JavaRidgeRegressionSuite.java @@ -55,30 +55,27 @@ public class JavaRidgeRegressionSuite implements Serializable { return errorSum / validationData.size(); } - List<LabeledPoint> generateRidgeData(int numPoints, int nfeatures, double eps) { + List<LabeledPoint> generateRidgeData(int numPoints, int numFeatures, double std) { org.jblas.util.Random.seed(42); // Pick weights as random values distributed uniformly in [-0.5, 0.5] - DoubleMatrix w = DoubleMatrix.rand(nfeatures, 1).subi(0.5); - // Set first two weights to eps - w.put(0, 0, eps); - w.put(1, 0, eps); - return LinearDataGenerator.generateLinearInputAsList(0.0, w.data, numPoints, 42, eps); + DoubleMatrix w = DoubleMatrix.rand(numFeatures, 1).subi(0.5); + return LinearDataGenerator.generateLinearInputAsList(0.0, w.data, numPoints, 42, std); } @Test public void runRidgeRegressionUsingConstructor() { - int nexamples = 200; - int nfeatures = 20; - double eps = 10.0; - List<LabeledPoint> data = generateRidgeData(2*nexamples, nfeatures, eps); + int numExamples = 50; + int numFeatures = 20; + List<LabeledPoint> data = generateRidgeData(2*numExamples, numFeatures, 10.0); - JavaRDD<LabeledPoint> testRDD = sc.parallelize(data.subList(0, nexamples)); - List<LabeledPoint> validationData = data.subList(nexamples, 2*nexamples); + JavaRDD<LabeledPoint> testRDD = sc.parallelize(data.subList(0, numExamples)); + List<LabeledPoint> validationData = data.subList(numExamples, 2 * numExamples); RidgeRegressionWithSGD ridgeSGDImpl = new RidgeRegressionWithSGD(); - ridgeSGDImpl.optimizer().setStepSize(1.0) - .setRegParam(0.0) - .setNumIterations(200); + ridgeSGDImpl.optimizer() + .setStepSize(1.0) + .setRegParam(0.0) + .setNumIterations(200); RidgeRegressionModel model = ridgeSGDImpl.run(testRDD.rdd()); double unRegularizedErr = predictionError(validationData, model); @@ -91,13 +88,12 @@ public class JavaRidgeRegressionSuite implements Serializable { @Test public void runRidgeRegressionUsingStaticMethods() { - int nexamples = 200; - int nfeatures = 20; - double eps = 10.0; - List<LabeledPoint> data = generateRidgeData(2*nexamples, nfeatures, eps); + int numExamples = 50; + int numFeatures = 20; + List<LabeledPoint> data = generateRidgeData(2 * numExamples, numFeatures, 10.0); - JavaRDD<LabeledPoint> testRDD = sc.parallelize(data.subList(0, nexamples)); - List<LabeledPoint> validationData = data.subList(nexamples, 2*nexamples); + JavaRDD<LabeledPoint> testRDD = sc.parallelize(data.subList(0, numExamples)); + List<LabeledPoint> validationData = data.subList(numExamples, 2 * numExamples); RidgeRegressionModel model = RidgeRegressionWithSGD.train(testRDD.rdd(), 200, 1.0, 0.0); double unRegularizedErr = predictionError(validationData, model); |