Building models programmatically
Now that we have imported the data, we will start building models programmatically. We will look at building the most basic models, then explore how to extract and visualize feature impact, before evaluating the performance of our models. Then, we will create more complex projects. Specifically, we will build one versus all multiclass classification models and model factories.
To create a DataRobot project, we must use the DataRobot Project.start method. The basic format for this is importing the necessary libraries (DataRobot, in the following case). Thereafter, the access credentials are presented, as described in the previous section. It is at the point that the Project method is called. project_name, sourcedata, and target are the minimal parameters that are required by the Project method for projects to be created. The project_name parameter tells DataRobot the name to give the created project. sourcedata provides information regarding the location...
