Hi all,
May I know how many nodes are required to process 9 million records in approximately 8 hours on a local Spark cluster with 8 cores and 256 GB RAM?
Can Someone please help here.
Performance is subject to the matches in the dataset, fields, match types, how well you trained etc. It is also a core problem we solve by learning through the provided labels. The docs share some numbers which I hope are useful Suriya S.