bom4v / ti-spark-data-generation 0.0.1-spark2.3

GitHub

Generation of a few sample data sets. For instance, feature set derived from CDR

Scala versions: 2.11

Generation of Data Sets

References

This GitHub repository is a component of the BOM4V project, aiming at demonstrating end-to-end Spark-based examples of Machine Learning (ML) pipelines, for instance churn detection in telecoms and transport industries.
Central Maven repository with BOM4V Jar artefacts
Docker cloud with ready-to-use images

Telecoms

Generation of CDR: https://github.com/RealImpactAnalytics/cdr-generator/tree/master/src/main/scala/Model

Installation

Short version

Just add the dependency on ti-spark-data-generation in the SBT project configuration (typically, build.sbt in the project root directory):

libraryDependencies += "org.bom4v.ti" %% "ti-spark-data-generation" % "0.0.1-spark2.3"