EDA

As you saw in the previous section, DataRobot automatically performed an initial analysis of the dataset. Let's see how we will review this data and gain insights from it. If you scroll down the page, you will see a table of features and an overview of their characteristics, as shown in the following screenshot:

Figure 5.3 – Data analysis overview

You can see that in this table, DataRobot has computed and listed any data quality concerns regarding a feature, what type of variable it is, how many unique values are in the dataset, and how many values are missing. These are all very important characteristics, and you need to review all of them to make sure that you understand what they are telling you.

For example, is the variable type selected by DataRobot what you expected? If you look at num_of_doors, you will notice that this is categorical. Even though this is correct because the data contained is in the form of text, you know that this...