diff options
Diffstat (limited to 'core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala')
| -rw-r--r-- | core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala index 2306c9736b..9ca971c8a4 100644 --- a/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala @@ -52,7 +52,7 @@ class DoubleRDDFunctions(self: RDD[Double]) extends Logging with Serializable { /** Compute the standard deviation of this RDD's elements. */ def stdev(): Double = stats().stdev - /** + /** * Compute the sample standard deviation of this RDD's elements (which corrects for bias in * estimating the standard deviation by dividing by N-1 instead of N). */ @@ -123,13 +123,13 @@ class DoubleRDDFunctions(self: RDD[Double]) extends Logging with Serializable { * e.g. for the array * [1, 10, 20, 50] the buckets are [1, 10) [10, 20) [20, 50] * e.g 1<=x<10 , 10<=x<20, 20<=x<50 - * And on the input of 1 and 50 we would have a histogram of 1, 0, 0 - * + * And on the input of 1 and 50 we would have a histogram of 1, 0, 0 + * * Note: if your histogram is evenly spaced (e.g. [0, 10, 20, 30]) this can be switched * from an O(log n) inseration to O(1) per element. (where n = # buckets) if you set evenBuckets * to true. * buckets must be sorted and not contain any duplicates. - * buckets array must be at least two elements + * buckets array must be at least two elements * All NaN entries are treated the same. If you have a NaN bucket it must be * the maximum value of the last position and all NaN entries will be counted * in that bucket. |