Hi all,I want to implement a basic K-nearest neighbors search in Spark, but I am totally new to Scala so don't know where to start with.My data consists of millions of points. For each point, I need to compute its Euclidean distance to the other points, and return the top-K points that are closest to it. The data.txt is with the comma-separated format like this:ID, X, Y1, 68, 932, 12, 903, 45, 76........1000000, 86, 54 Could you please tell me what data structure I should use, and how to implement this algorithm in Scala (*some sample code are greatly appreciated*).Thank you very much.Regards,Carter
-- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/K-nearest-neighbors-search-in-Spark-tp6393.html Sent from the Apache Spark User List mailing list archive at Nabble.com.
