Github user gatorsmile commented on a diff in the pull request: https://github.com/apache/spark/pull/20959#discussion_r179934764 --- Diff: sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala --- @@ -1279,4 +1279,45 @@ class CSVSuite extends QueryTest with SharedSQLContext with SQLTestUtils { Row("0,2013-111-11 12:13:14") :: Row(null) :: Nil ) } + + test("SPARK-23846: schema inferring touches less data if samplingRation < 1.0") { + val predefinedSample = Set[Int](2, 8, 15, 27, 30, 34, 35, 37, 44, 46, + 57, 62, 68, 72) --- End diff -- `val predefinedSample = Set[Int](2, 8, 15, 27, 30, 34, 35, 37, 44, 46)` is enough.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org