Github user MechCoder commented on a diff in the pull request: https://github.com/apache/spark/pull/6112#discussion_r31382216 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala --- @@ -717,6 +719,49 @@ class SparseVector( new SparseVector(size, ii, vv) } } + + override def argmax: Int = { + if (size == 0) { + -1 + } else { + + var maxIdx = 0 + var maxValue = if(indices(0) != 0) 0.0 else values(0) + + foreachActive { (i, v) => + if (v > maxValue) { + maxIdx = i + maxValue = v + } + } + + // look for inactive values incase all active node values are negative + if(size != values.size && maxValue < 0){ + maxIdx = calcInactiveIdx(indices(0)) + maxValue = 0 + } + maxIdx + } + } + + /** + * Calculates the first instance of an inactive node in a sparse vector and returns the Idx + * of the element. + * @param idx starting index of computation + * @return index of first inactive node or -1 if it cannot find one + */ + private[SparseVector] def calcInactiveIdx(idx: Int): Int ={ --- End diff -- I'm still not sure about the best way. cc @mengxr
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org