I'm a SAS user, and have a task to run clustering algorithm on a SAS server but ran out of memory. The dataset is 500G, i know i can sampling it down to fit into memory, but if I want to run the model on the entire data, would ORE help with my problem?
Other related questions regarding ORE and ORCH:
1. Does the Oracle R Package include any clustering algorithms? Is there a list of available Oracle R packages?
2. Will I also run into memory issue if I run the kmeans algorithm (R CRAN package) in Oracle R Enterprise?
3. Is there any R clustering package available in BDA that is written to run on distributed Hadoop clusters?
Thanks in advance!