Running the Model on Hadoop
We have used BigML for creating the classification tree with the help of historical campaign response data. This model is available in the form of Java code. We can now run this model on Hadoop by using it inside a MapReduce job.
We will need a MapReduce program, which you are already familiar with from the previous chapters of this book. This program is supplied with this book in the directory /hbp/chapt4 as a file named ResponsePrediction.java. This file contains the code for a mapper, reducer, and driver in a single file. The following classes are included in this file:
public class ResponsePrediction {...} public static void main(String[] args) throws Exception { JobConf conf = new JobConf(ResponsePrediction.class); ...Get Hadoop Blueprints now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
