Synthesizers don't validate constraints during validate()

[amontanez24]

Environment Details

Please indicate the following details about the environment in which you found the bug:

• SDV version: 1.0.*
• Python version: Any
• Operating System: Any

Error Description

When running synthesizer.validate(data) on data that doesn't meet constraints already set in the synthesizer, we should raise errors for those constraints.

Steps to reproduce

from sdv.datasets.demo import download_demo

real_data, metadata = download_demo(
    modality='single_table',
    dataset_name='fake_hotel_guests'
)
real_data['checkin_date'][0] = real_data['checkout_date'][1] # make constraint fail
from sdv.single_table import GaussianCopulaSynthesizer

gc = GaussianCopulaSynthesizer(metadata)

checkin_lessthan_checkout = {
    'constraint_class': 'Inequality',
    'constraint_parameters': {
        'low_column_name': 'checkin_date',
        'high_column_name': 'checkout_date'
    }
}
gc.add_constraints([
    checkin_lessthan_checkout
])
gc.validate() # Should raise error for constraint