User validation for reverse_transform

[npatki]

Problem Description

When a user uses reverse_transform, we should validate their input & throw appropriate warnings/errors.

Expected behavior

Perform the following 3 validation checks:

1. Reverse transforming data before fitting it

Note: This also applies if the HyperTransformer was previously fit but the config has changed since then.

ht = HyperTransformer()
ht.detect_initial_config(data)
ht.reverse_transform(reversed_data)
Error: The HyperTransformer is not ready to use. Please fit your data first using 'fit' or 'fit_transform'.

2. Transforming the data before setting a config

ht = HyperTransformer()
ht.reverse_transform(reversed_data)
Error: No config detected. Set the config using 'set_config' or pre-populate it automatically from your data using 'detect_initial_config' prior to fitting your data.

3. The data does not have the exact same column names as the config (& fit data)

ht = HyperTransformer()
ht.detect_initial_config(data)
ht.fit(data)
ht.reverse_transform(bad_data)
Error: There are unexpected columns in the data you are trying to transform. You must provide a transformed dataset with all the columns from the original data.