Run nan_to_num on quantiles

[jlashner]

Replaces nans and +- inf in bias step quantile functions.

Description

This should fix the issue with infs getting passed to session.data reported here: #645

Motivation and Context

Resolves #645, which has been occasionally crashing the schedule.

How Has This Been Tested?

I've tested running the line w/ fake data to make sure there are no typos.

Types of changes

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)

Checklist:

• My code follows the code style of this project.
• My change requires a change to the documentation.
• I have updated the documentation accordingly.

[BrianJKoopman]

Looks good, thanks @jlashner!