# SPARK Autotuning

## Structure

+ docker: Contains the container used to run Spark applications on the cluster. Currently Spark v3.0 is used with Hadoop v2.7 and Scala v2.12
+ kube: Contains the necessary ```YAML``` files to deploy Sparkbench on a kubernetes cluster. Modification might be needed to suit your cluster.
+ src: 


## 1. Generating the Spark configurations
Please see ```src/python/README.md``` for instructions.