Repository: spark Updated Branches: refs/heads/branch-1.3 035d6d70c -> 25203d9d0
[SPARK-10973] [ML] [PYTHON] Fix IndexError exception on SparseVector when asked for index after the last non-zero entry See https://github.com/apache/spark/pull/9009 for details. Author: zero323 <[email protected]> Closes #9062 from zero323/SPARK-10973_1.3. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/25203d9d Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/25203d9d Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/25203d9d Branch: refs/heads/branch-1.3 Commit: 25203d9d0b7c345a1ede2194d5cb7acdd5ca674a Parents: 035d6d7 Author: zero323 <[email protected]> Authored: Mon Oct 12 17:23:37 2015 -0700 Committer: Joseph K. Bradley <[email protected]> Committed: Mon Oct 12 17:23:37 2015 -0700 ---------------------------------------------------------------------- python/pyspark/mllib/linalg.py | 3 +++ python/pyspark/mllib/tests.py | 20 +++++++++++--------- 2 files changed, 14 insertions(+), 9 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/25203d9d/python/pyspark/mllib/linalg.py ---------------------------------------------------------------------- diff --git a/python/pyspark/mllib/linalg.py b/python/pyspark/mllib/linalg.py index 3db06d4..2416357 100644 --- a/python/pyspark/mllib/linalg.py +++ b/python/pyspark/mllib/linalg.py @@ -561,6 +561,9 @@ class SparseVector(Vector): raise ValueError("Index %d out of bounds." % index) insert_index = np.searchsorted(inds, index) + if insert_index >= inds.size: + return 0. + row_ind = inds[insert_index] if row_ind == index: return vals[insert_index] http://git-wip-us.apache.org/repos/asf/spark/blob/25203d9d/python/pyspark/mllib/tests.py ---------------------------------------------------------------------- diff --git a/python/pyspark/mllib/tests.py b/python/pyspark/mllib/tests.py index 113f216..ea2ceaf 100644 --- a/python/pyspark/mllib/tests.py +++ b/python/pyspark/mllib/tests.py @@ -124,15 +124,17 @@ class VectorTests(PySparkTestCase): self.assertTrue(dv.array.dtype == 'float64') def test_sparse_vector_indexing(self): - sv = SparseVector(4, {1: 1, 3: 2}) - self.assertEquals(sv[0], 0.) - self.assertEquals(sv[3], 2.) - self.assertEquals(sv[1], 1.) - self.assertEquals(sv[2], 0.) - self.assertEquals(sv[-1], 2) - self.assertEquals(sv[-2], 0) - self.assertEquals(sv[-4], 0) - for ind in [4, -5, 7.8]: + sv = SparseVector(5, {1: 1, 3: 2}) + self.assertEqual(sv[0], 0.) + self.assertEqual(sv[3], 2.) + self.assertEqual(sv[1], 1.) + self.assertEqual(sv[2], 0.) + self.assertEqual(sv[4], 0.) + self.assertEqual(sv[-1], 0.) + self.assertEqual(sv[-2], 2.) + self.assertEqual(sv[-3], 0.) + self.assertEqual(sv[-5], 0.) + for ind in [5, -6, 7.8]: self.assertRaises(ValueError, sv.__getitem__, ind) --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
