How it works...

This section explains the transformations needed on the data to be used in the model.

  1. One of the first steps to building a model is splitting the data into a training and test dataset for model evaluation purposes. Our goal is to use all of the stock quotes from 2000 through 2016 to predict stock trends in 2017-2018. We know from previous sections that we have a total of 4,610 days of stock quotes, but we don't know exactly how many fall in each year. We can use the groupBy() function within the dataframe to get a unique count of stock quotes per year, as can be seen in the following screenshot:
  1. 2016 and 2017's combined ...

Get Apache Spark Deep Learning Cookbook 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.

Start your free trial