diff options
| -rw-r--r-- | core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala | 6 | ||||
| -rw-r--r-- | core/src/main/scala/org/apache/spark/rdd/RDD.scala | 2 |
2 files changed, 4 insertions, 4 deletions
diff --git a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala index f34593f0b6..d778692f45 100644 --- a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala @@ -211,7 +211,7 @@ class PairRDDFunctions[K: ClassManifest, V: ClassManifest](self: RDD[(K, V)]) /** * Return approximate number of distinct values for each key in this RDD. - * The accuracy of approximation can be controlled through the relative standard diviation + * The accuracy of approximation can be controlled through the relative standard deviation * (relativeSD) parameter, which also controls the amount of memory used. Lower values result in * more accurate counts but increase the memory footprint and vise versa. Uses the provided * Partitioner to partition the output RDD. @@ -235,7 +235,7 @@ class PairRDDFunctions[K: ClassManifest, V: ClassManifest](self: RDD[(K, V)]) /** * Return approximate number of distinct values for each key in this RDD. - * The accuracy of approximation can be controlled through the relative standard diviation + * The accuracy of approximation can be controlled through the relative standard deviation * (relativeSD) parameter, which also controls the amount of memory used. Lower values result in * more accurate counts but increase the memory footprint and vise versa. HashPartitions the * output RDD into numPartitions. @@ -247,7 +247,7 @@ class PairRDDFunctions[K: ClassManifest, V: ClassManifest](self: RDD[(K, V)]) /** * Return approximate number of distinct values for each key this RDD. - * The accuracy of approximation can be controlled through the relative standard diviation + * The accuracy of approximation can be controlled through the relative standard deviation * (relativeSD) parameter, which also controls the amount of memory used. Lower values result in * more accurate counts but increase the memory footprint and vise versa. The default value of * relativeSD is 0.05. Hash-partitions the output RDD using the existing partitioner/parallelism diff --git a/core/src/main/scala/org/apache/spark/rdd/RDD.scala b/core/src/main/scala/org/apache/spark/rdd/RDD.scala index 09932db5ea..38fa96fd6d 100644 --- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala @@ -769,7 +769,7 @@ abstract class RDD[T: ClassManifest]( /** * Return approximate number of distinct elements in the RDD. * - * The accuracy of approximation can be controlled through the relative standard diviation + * The accuracy of approximation can be controlled through the relative standard deviation * (relativeSD) parameter, which also controls the amount of memory used. Lower values result in * more accurate counts but increase the memory footprint and vise versa. The default value of * relativeSD is 0.05. |