Apache Spark Machine Learning Blueprints

Chapter 11. Modeling Open Data on Spark

Following what we did in Chapter 10, Learning Telco Data on Spark, in this chapter, we will further extend our Apache Spark machine learning to a project of learning from open data. In Chapter 9, City Analytics on Spark, we already applied machine learning to open data, where we built models to predict service requests. Here, we will further move up into a new level where we will explore machine learning approaches of turning more open data into useful insights, as well as building models to score school districts or schools for academic achievements, technologies, and others. After that, we will build predictive models to explain what impacts the ranking and scoring of these districts.

To follow the good ...