Now that we know a bit more about our data, we can skip to the next step: preparing our data for the modeling activity. This main objective involves a lot of tasks that usually go under the names of data cleaning, data validation, data munging, and data wrangling. The reason behind the need for these activities is quite simple: the modeling techniques we are going to apply to our data will have specific requirements, which could include, for instance, the absence of null values or a specific type of variable as an input (categorical, numerical, and many more). It is, therefore, critical to prepare our data in a way that is suitable for our models. Moreover, we may need to perform basic transformation activities on our raw data, such as merging or appending tables. Finally, we may even need to draw a sample from our data, for instance, to address a matter of resource constraints.
We are going to look closer at how to perform these tasks with R in Chapters 5, How to Address...
