Normalization

Normalization transforms the points along a dimension so that you can better see their distribution. It spreads out a tightly clustered group of points so that the differences are clearer in your visualization. It is often used to adjust values measured on different scales to a common scale.

Applying Normalization

Normalization can be set in four ways:

  • The Normalization button in the toolbar, which allows you to apply the same normalization to all three axes at once
  • Normalization dropdown in the dimension settings by clicking on each dimension icon in the Mapping panel
  • You can create a new normalized feature by right-clicking a numerical feature and selecting an option from the Normalize section

Normalization Types

VIP supports the following different types of normalization:

  • Log10 – A common normalization type, log transformation changes the feature from linear to logarithmic. Cannot be used on features that contain a value of 0 or less.
  • IHST – Inverse hyperbolic¬†sine transformation. Similar to Softmax, but can provide slightly more space between points for certain features.
  • Softmax – Useful for normalizing features that contain values of 0 or less, making this a robust choice.
  • CDF – Cumulative distribution function.