The dataset we will use in our example is available in the GitHub repository at https://github.com/PacktPublishing/Machine-Learning-with-the-Elastic-Stack/tree/master/example_data. This dataset, once downloaded, can be easily imported into your Kibana via ML's Data Visualizer (only in versions 6.5+). To upload the data, go to ML's Data Visualizer tab and select the Upload file button:

Choose the forecast_example.json file from your local machine. The Data Visualizer will then display the first 1000 lines of the file to give you a preview of what the file contains, as well as a breakdown of the different fields:

In this specific case, we do not need to override any of the settings that the Data Visualizer has made automatically, so we can proceed by clicking on the Import button. We can supply a name for the destination index (we can use forecast_example for this exercise):

Clicking on the Import button now will complete the import process:

We can now create a new ML job so that we can do some forecasting on this dataset.