Setting the target feature and correlation analysis

By the time you reach this stage, you should already have a pretty good idea of the problem you are trying to solve and what should be the target feature. It is not unusual to use different features as targets for different use cases. Also, sometimes you will set a transformed feature as a target (for example, log of a feature). For the Automobile dataset, we want to predict the price of cars. Once you select the target feature, as shown in the following screenshot, it will analyze that feature and provide some recommendations:

Figure 5.11 – Setting target feature

You can see from the preceding screenshot that it is showing how the price is distributed. DataRobot also cautions that some of the target values are missing. Ideally, we would filter out the rows with missing target values before uploading the dataset. You will also notice that DataRobot has characterized this as a regression problem. Another...