@Test public void runRidgeRegressionUsingStaticMethods() { int numExamples = 50; int numFeatures = 20; List<LabeledPoint> data = generateRidgeData(2 * numExamples, numFeatures, 10.0); JavaRDD<LabeledPoint> testRDD = jsc.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); model = RidgeRegressionWithSGD.train(testRDD.rdd(), 200, 1.0, 0.1); double regularizedErr = predictionError(validationData, model); Assert.assertTrue(regularizedErr < unRegularizedErr); } }
@Test public void runRidgeRegressionUsingStaticMethods() { int numExamples = 50; int numFeatures = 20; List<LabeledPoint> data = generateRidgeData(2 * numExamples, numFeatures, 10.0); JavaRDD<LabeledPoint> testRDD = jsc.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); model = RidgeRegressionWithSGD.train(testRDD.rdd(), 200, 1.0, 0.1); double regularizedErr = predictionError(validationData, model); Assert.assertTrue(regularizedErr < unRegularizedErr); } }
@Test public void runRidgeRegressionUsingStaticMethods() { int numExamples = 50; int numFeatures = 20; List<LabeledPoint> data = generateRidgeData(2 * numExamples, numFeatures, 10.0); JavaRDD<LabeledPoint> testRDD = jsc.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); model = RidgeRegressionWithSGD.train(testRDD.rdd(), 200, 1.0, 0.1); double regularizedErr = predictionError(validationData, model); Assert.assertTrue(regularizedErr < unRegularizedErr); } }
@Test public void runRidgeRegressionUsingConstructor() { int numExamples = 50; int numFeatures = 20; List<LabeledPoint> data = generateRidgeData(2 * numExamples, numFeatures, 10.0); JavaRDD<LabeledPoint> testRDD = jsc.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); RidgeRegressionModel model = ridgeSGDImpl.run(testRDD.rdd()); double unRegularizedErr = predictionError(validationData, model); ridgeSGDImpl.optimizer().setRegParam(0.1); model = ridgeSGDImpl.run(testRDD.rdd()); double regularizedErr = predictionError(validationData, model); Assert.assertTrue(regularizedErr < unRegularizedErr); }
@Test public void runRidgeRegressionUsingConstructor() { int numExamples = 50; int numFeatures = 20; List<LabeledPoint> data = generateRidgeData(2 * numExamples, numFeatures, 10.0); JavaRDD<LabeledPoint> testRDD = jsc.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); RidgeRegressionModel model = ridgeSGDImpl.run(testRDD.rdd()); double unRegularizedErr = predictionError(validationData, model); ridgeSGDImpl.optimizer().setRegParam(0.1); model = ridgeSGDImpl.run(testRDD.rdd()); double regularizedErr = predictionError(validationData, model); Assert.assertTrue(regularizedErr < unRegularizedErr); }
@Test public void runRidgeRegressionUsingConstructor() { int numExamples = 50; int numFeatures = 20; List<LabeledPoint> data = generateRidgeData(2 * numExamples, numFeatures, 10.0); JavaRDD<LabeledPoint> testRDD = jsc.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); RidgeRegressionModel model = ridgeSGDImpl.run(testRDD.rdd()); double unRegularizedErr = predictionError(validationData, model); ridgeSGDImpl.optimizer().setRegParam(0.1); model = ridgeSGDImpl.run(testRDD.rdd()); double regularizedErr = predictionError(validationData, model); Assert.assertTrue(regularizedErr < unRegularizedErr); }