Add validate to PARSynthesizer

[amontanez24]

Problem Description

As a user, it would be helpful if there was a way to see if my sequential data is correct according to my metadata.

Acceptance criteria

• Add a method called validate to the PARSynthesizer
• This method should make the same checks as the BaseSynthesizer.validate plus the following one
  • Context columns (stored in the model's parameters) should be fixed for each sequence – ie if you group by sequence key, the context columns should not vary
    Error: Context column 'patient_address' is changing inside sequence ('Patient_ID'='ID_004').

Expected behavior

synthesizer.validate(data)
InvalidDataError: The provided data does not match the metadata

Error: Context column 'patient_address' is changing inside sequence ('Patient_ID'='ID_004').

Additional context

• The PARSynthesizer does not inherit from the BaseSynthesizer class. This is mostly because the sampling methods for these classes are different. It might be worth investigating ways to refactor the code so that there isn't too much repetition. One option could be mixins. We could have a mixin for most of the repeated functionality that both PARSynthesizer and BaseSynthesizer inherit from.