What Is It?
Smart Mapping is an AI-driven visualization routine that helps you instantly understand the key driving features in your data.
Why Is This Important?
Smart Mapping is especially useful in minimizing time to insight when working with a large number of features in your data. Using this routine, you can uncover hidden relationships within your data. For example, you can discover that Variance and Region are the largest driving factors for 3yr Return in an Exchange Traded Fund (ETF) dataset. Or, for example, you can discover the specific drug regimens that are linked to desirable health outcomes.
Smart Mapping works right out of the box in Explore. Smart Mapping is a supervised machine learning routine that takes as input a target and a set of additional features to be compared, then outputs the additional features sorted by their relative importance to the target.
The routine also creates several AI-suggested visualizations for you to interpret the results.
Steps for running Smart Mapping:
- Open the Smart Mapping panel by clicking the icon in the toolbar or selecting Smart Mapping from the Data Analytics menu.
- Drag and drop the target feature from the Features panel into the Target textbox.
- Tip: Continuous and discrete numerical and categorical features all work well as the Smart Mapping target.
- Add other features by dragging and dropping them into the Add Features area or using the Input All button.
- Tip: Input All will not input an already selected target feature
- (Optional) Remove unwanted features by hovering over the feature and clicking the "x" button.
- Tip: Remove features used to calculate the target and sparse features (with many missing values). Click the red pound sign to remove sparse features.
- Click the "Run" Button.
Smart Mapping typically suggests several visualizations in addition to the initial plot displayed. The suggested mappings consider the relative importance of the features and any correlations existing between them, taking features like Longitude and Latitude into account to suggest geospatial plots as well.
If the target is a numerical feature it will be applied to the color dimension and split into quartiles. You can change the bin options by accessing the Color Settings in the Mapping panel. If a categorical feature is within the first eight ranked features, it will be applied to Playback. The top binary categorical feature will also be mapped to Shape.
Linear and non-linear relationships are explored and leveraged in determining the rank of the features impact on the target feature.