From b35467388612167f0bc3d17142c21a406f6c620d Mon Sep 17 00:00:00 2001 From: sethah Date: Thu, 11 Feb 2016 16:42:44 -0800 Subject: [SPARK-13047][PYSPARK][ML] Pyspark Params.hasParam should not throw an error Pyspark Params class has a method `hasParam(paramName)` which returns `True` if the class has a parameter by that name, but throws an `AttributeError` otherwise. There is not currently a way of getting a Boolean to indicate if a class has a parameter. With Spark 2.0 we could modify the existing behavior of `hasParam` or add an additional method with this functionality. In Python: ```python from pyspark.ml.classification import NaiveBayes nb = NaiveBayes() print nb.hasParam("smoothing") print nb.hasParam("notAParam") ``` produces: > True > AttributeError: 'NaiveBayes' object has no attribute 'notAParam' However, in Scala: ```scala import org.apache.spark.ml.classification.NaiveBayes val nb = new NaiveBayes() nb.hasParam("smoothing") nb.hasParam("notAParam") ``` produces: > true > false cc holdenk Author: sethah Closes #10962 from sethah/SPARK-13047. --- python/pyspark/ml/tests.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'python/pyspark/ml/tests.py') diff --git a/python/pyspark/ml/tests.py b/python/pyspark/ml/tests.py index e93a4e157b..5fcfa9e61f 100644 --- a/python/pyspark/ml/tests.py +++ b/python/pyspark/ml/tests.py @@ -209,6 +209,11 @@ class ParamTests(PySparkTestCase): self.assertEqual(maxIter.doc, "max number of iterations (>= 0).") self.assertTrue(maxIter.parent == testParams.uid) + def test_hasparam(self): + testParams = TestParams() + self.assertTrue(all([testParams.hasParam(p.name) for p in testParams.params])) + self.assertFalse(testParams.hasParam("notAParameter")) + def test_params(self): testParams = TestParams() maxIter = testParams.maxIter @@ -218,7 +223,7 @@ class ParamTests(PySparkTestCase): params = testParams.params self.assertEqual(params, [inputCol, maxIter, seed]) - self.assertTrue(testParams.hasParam(maxIter)) + self.assertTrue(testParams.hasParam(maxIter.name)) self.assertTrue(testParams.hasDefault(maxIter)) self.assertFalse(testParams.isSet(maxIter)) self.assertTrue(testParams.isDefined(maxIter)) @@ -227,7 +232,7 @@ class ParamTests(PySparkTestCase): self.assertTrue(testParams.isSet(maxIter)) self.assertEqual(testParams.getMaxIter(), 100) - self.assertTrue(testParams.hasParam(inputCol)) + self.assertTrue(testParams.hasParam(inputCol.name)) self.assertFalse(testParams.hasDefault(inputCol)) self.assertFalse(testParams.isSet(inputCol)) self.assertFalse(testParams.isDefined(inputCol)) -- cgit v1.2.3