As part of preprocessing, Watson Studio gives you the ability to refine data. Refining data is described in the online documentation as the cleansing and shaping of data.

As you manipulate data within Watson Studio using the refinery feature, you build what is referred to as a customized data refinery flow. We can try out some of the features and functions offered by the data refinery by going through the following steps (starting with some setup):

1. To create a project, you click on New project on the right side of the Watson Studio My Projects page, as shown in the following screenshot:

2. Next, choose a project starter. We'll choose Data Engineering, as shown in the following screenshot (you may need to select or provision the required services at this step, depending upon what you selected; for our selection, no additional services are needed):

3. On the New project screen, you can add a name and description for the project, as shown in the following screenshot:

At this point, you need to choose whether to restrict who you can add as collaborators (we'll use the default settings in this example), and you might be prompted to add services as you add assets that require them (in this example, no additional services will be needed, but as an FYI, you can also add other services after you create a project using the Settings page).

4. Next, click on Create, as shown in the following screenshot:

After clicking on Create, Watson Studio will prepare the project for you, displaying the dialog shown in the following screenshot:

And finally (typically, it only takes a minute or two), your new project will open, ready to go, and you can start having fun developing it!