We will be leveraging our Python Databricks notebook, but we will include the following Scala cell. At the top level here's the flow of the code:
%scalapackage d3aimport org.apache.spark.sql._import com.databricks.backend.daemon.driver.EnhancedRDDFunctions.displayHTMLcase class Edge(src: String, dest: String, count: Long)case class Node(name: String)case class Link(source: Int, target: Int, value: Long)case class Graph(nodes: Seq[Node], links: Seq[Link])object graphs {val sqlContext = SQLContext.getOrCreate(org.apache.spark.SparkContext.getOrCreate())import sqlContext.implicits._def force(clicks: Dataset[Edge], height: Int = 100, width: Int = 960): Unit = { val data = clicks.collect() val nodes = (data.map(_.src) ++ data.map(_.dest)).map(_.replaceAll("_", ...
