diff options
| -rw-r--r-- | core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala | 6 |
1 files changed, 3 insertions, 3 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 9ca971c8a4..f233544d12 100644 --- a/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala @@ -119,11 +119,11 @@ class DoubleRDDFunctions(self: RDD[Double]) extends Logging with Serializable { /** * Compute a histogram using the provided buckets. The buckets are all open - * to the left except for the last which is closed + * to the right except for the last which is closed * 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 + * 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, 1 * * 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 |