Is this a new feature, an improvement, or a change to existing functionality?

Improvement

How would you describe the priority of this feature request

Medium

Please provide a clear description of problem this feature solves

Currently, the AutoEncoder class utilizes pandas to perform much of the pre-processing necessary before converting the DataFrames to pytorch tensors needed for training. This is much slower and requires converting from cudf -> pandas -> GPU tensor, which is very inefficient.

Describe your ideal solution

Where possible, replace all uses of pandas with cuDF. This would require:

• Remove all uses of apply() by using alternate cuDF functions (where possible). We should strive to never use apply()
• Replace all uses of pandas with cudf
• Ensure all tests continue to pass without changes

Describe any alternatives you have considered

No response

Additional context

No response

Code of Conduct

• I agree to follow this project's Code of Conduct
• I have searched the open feature requests and have found no duplicates for this feature request