Repository: spark Updated Branches: refs/heads/branch-2.3 c647f918b -> 0cde5212a
[SPARK-23091][ML] Incorrect unit test for approxQuantile ## What changes were proposed in this pull request? Narrow bound on approx quantile test to epsilon from 2*epsilon to match paper ## How was this patch tested? Existing tests. Author: Sean Owen <so...@cloudera.com> Closes #20324 from srowen/SPARK-23091. (cherry picked from commit 396cdfbea45232bacbc03bfaf8be4ea85d47d3fd) Signed-off-by: gatorsmile <gatorsm...@gmail.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/0cde5212 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/0cde5212 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/0cde5212 Branch: refs/heads/branch-2.3 Commit: 0cde5212a80b5572bfe53b06ed557e6c2ec8c903 Parents: c647f91 Author: Sean Owen <so...@cloudera.com> Authored: Fri Jan 19 22:46:34 2018 -0800 Committer: gatorsmile <gatorsm...@gmail.com> Committed: Fri Jan 19 22:46:47 2018 -0800 ---------------------------------------------------------------------- .../apache/spark/sql/DataFrameStatSuite.scala | 24 ++++++++++---------- 1 file changed, 12 insertions(+), 12 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/0cde5212/sql/core/src/test/scala/org/apache/spark/sql/DataFrameStatSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameStatSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameStatSuite.scala index 5169d2b..8eae353 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameStatSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameStatSuite.scala @@ -154,24 +154,24 @@ class DataFrameStatSuite extends QueryTest with SharedSQLContext { val Array(d1, d2) = df.stat.approxQuantile("doubles", Array(q1, q2), epsilon) val Array(s1, s2) = df.stat.approxQuantile("singles", Array(q1, q2), epsilon) - val error_single = 2 * 1000 * epsilon - val error_double = 2 * 2000 * epsilon + val errorSingle = 1000 * epsilon + val errorDouble = 2.0 * errorSingle - assert(math.abs(single1 - q1 * n) < error_single) - assert(math.abs(double2 - 2 * q2 * n) < error_double) - assert(math.abs(s1 - q1 * n) < error_single) - assert(math.abs(s2 - q2 * n) < error_single) - assert(math.abs(d1 - 2 * q1 * n) < error_double) - assert(math.abs(d2 - 2 * q2 * n) < error_double) + assert(math.abs(single1 - q1 * n) <= errorSingle) + assert(math.abs(double2 - 2 * q2 * n) <= errorDouble) + assert(math.abs(s1 - q1 * n) <= errorSingle) + assert(math.abs(s2 - q2 * n) <= errorSingle) + assert(math.abs(d1 - 2 * q1 * n) <= errorDouble) + assert(math.abs(d2 - 2 * q2 * n) <= errorDouble) // Multiple columns val Array(Array(ms1, ms2), Array(md1, md2)) = df.stat.approxQuantile(Array("singles", "doubles"), Array(q1, q2), epsilon) - assert(math.abs(ms1 - q1 * n) < error_single) - assert(math.abs(ms2 - q2 * n) < error_single) - assert(math.abs(md1 - 2 * q1 * n) < error_double) - assert(math.abs(md2 - 2 * q2 * n) < error_double) + assert(math.abs(ms1 - q1 * n) <= errorSingle) + assert(math.abs(ms2 - q2 * n) <= errorSingle) + assert(math.abs(md1 - 2 * q1 * n) <= errorDouble) + assert(math.abs(md2 - 2 * q2 * n) <= errorDouble) } // quantile should be in the range [0.0, 1.0] --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
