Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/5697#discussion_r29105224
--- Diff: mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala
---
@@ -63,20 +63,27 @@ sealed trait Vector extends Serializable {
Vectors.equals(0 until d1.size, d1.values, s1.indices,
s1.values)
case (_, _) => util.Arrays.equals(this.toArray, v2.toArray)
}
- }
case _ => false
}
}
+ /**
+ * Returns a hash code value for the vector. The hash code is based on
its size and its nonzeros
+ * in the first 16 entries, using a hash algorithm similar to
[[java.util.Arrays.hashCode]].
+ */
override def hashCode(): Int = {
- var result: Int = size + 31
- this.foreachActive { case (index, value) =>
- // ignore explict 0 for comparison between sparse and dense
- if (value != 0) {
- result = 31 * result + index
- // refer to {@link java.util.Arrays.equals} for hash algorithm
- val bits = java.lang.Double.doubleToLongBits(value)
- result = 31 * result + (bits ^ (bits >>> 32)).toInt
+ // This is a reference implementation. It calls return in
foreachActive, which is slow.
+ var result: Int = 31 + size
+ this.foreachActive { (index, value) =>
+ if (index < 16) {
+ // ignore explict 0 for comparison between sparse and dense
--- End diff --
typo: "explicit"
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
