Machine Learning with Spark - Second Edition

Creating a streaming regression model

In the next step in our example, we will create a streaming regression program. The basic layout and setup is the same as our previous streaming analytics examples:

/**   * A simple streaming linear regression that prints out predicted      value for each batch  */ object SimpleStreamingModel {   def main(args: Array[String]) {   val ssc = new StreamingContext("local[2]", "First Streaming           App", Seconds(10))   val stream = ssc.socketTextStream("localhost", 9999)

Here, we will set up the number of features to match the records in our input data stream. We will then create a zero vector to use as the initial weight vector of our streaming regression model. Finally, we will select the number of iterations and ...