Contributions on kmeans implementation in Spark using Scala. More specifically, an implementation of Silhouette Coefficient and the implementation of initialization of centers in k-means.
This is a University Project, for the MSc of the Department of Informatics (AUTh). The report existing on the repository is in Greek and is analysing the theory behind the project and some results.
Dependencies:
- Apache Spark: spark-1.6.1-bin-hadoop2.6.tgz
- Scala v.2.10.4