API to identify colinearity (high-correlation between attributes/features/input-variables)

Related to model explainability features and feature or input variable selection in general, if would be good to have any API to identify colinearity (high correlation between attributes/features/input-variables).

Colinearity in the input variables can make choosing the correct attributes/input-variables to use more difficult, especially in linear models.

This issue is also related to the more general issue: https://github.com/dotnet/machinelearning/issues/749
But this issue focuses on a particular feature which is "colinearity detection".

In short, collinearity:

- Can make choosing the correct predictors to include more difficult.
- Interferes in determining the precise effect of each predictor, but...
- BUT, it doesn’t affect the overall fit of the model or produce bad predictions.

Depending on your goals, multicollinearity isn’t always a problem. However, because of the difficulty in choosing the correct model when severe multicollinearity is present, it’s always worth exploring.

This feature is not critical for our current major release (v1.0) that we are currently stabilizing, but should be taken into account for future releases.