Ctgan

Dependency upgrades to ensure compatibility with the rest of the SDV ecosystem.

In this release, the way in which the loss function of the TVAE model was computed has been fixed.
In addition, the default value of the `discriminator_decay` has been changed to a more optimal
value. Also some improvements to the tests were added.

Issues closed

* `TVAE`: loss function - Issue [143](https://github.com/sdv-dev/CTGAN/issues/143) by fealho and DingfanChen
* Set `discriminator_decay` to `1e-6` - Pull request [145](https://github.com/sdv-dev/CTGAN/pull/145/) by fealho
* Adds unit tests - Pull requests [140](https://github.com/sdv-dev/CTGAN/pull/140) by fealho

This release exposes all the hyperparameters which the user may find useful for both `CTGAN`
and `TVAE`. Also `TVAE` can now be fitted on datasets that are shorter than the batch
size and drops the last batch only if the data size is not divisible by the batch size.

Issues closed

* `TVAE`: Adapt `batch_size` to data size - Issue [135](https://github.com/sdv-dev/CTGAN/issues/135) by fealho and csala
* `ValueError` from `validate_discre_columns` with `uniqueCombinationConstraint` - Issue [133](https://github.com/sdv-dev/CTGAN/issues/133) by fealho and MLjungg

Maintenance relese to upgrade dependencies to ensure compatibility with the rest
of the SDV libraries.

Also add a validation on the CTGAN `condition_column` and `condition_value` inputs.

Improvements

* Validate condition_column and condition_value - Issue [124](https://github.com/sdv-dev/CTGAN/issues/124) by fealho

Improvements

* Check discrete_columns valid before fitting - [Issue 35](https://github.com/sdv-dev/CTGAN/issues/35) by fealho

Bugs fixed

* ValueError: max() arg is an empty sequence - [Issue 115](https://github.com/sdv-dev/CTGAN/issues/115) by fealho

In this release we add a new TVAE model which was presented in the original CTGAN paper.
It also exposes more hyperparameters and moves epochs and log_frequency from fit to the constructor.

A new verbose argument has been added to optionally disable unnecessary printing, and a new hyperparameter
called `discriminator_steps` has been added to CTGAN to control the number of optimization steps performed
in the discriminator for each generator epoch.

The code has also been reorganized and cleaned up for better readability and interpretability.

Special thanks to Baukebrenninkmeijer fealho leix28 csala for the contributions!

Improvements

* Add TVAE - [Issue 111](https://github.com/sdv-dev/CTGAN/issues/111) by fealho
* Move `log_frequency` to `__init__` - [Issue 102](https://github.com/sdv-dev/CTGAN/issues/102) by fealho
* Add discriminator steps hyperparameter - [Issue 101](https://github.com/sdv-dev/CTGAN/issues/101) by Baukebrenninkmeijer
* Code cleanup / Expose hyperparameters - [Issue 59](https://github.com/sdv-dev/CTGAN/issues/59) by fealho and leix28
* Publish to conda repo - [Issue 54](https://github.com/sdv-dev/CTGAN/issues/54) by fealho

Bugs fixed

* Fixed NaN != NaN counting bug. - [Issue 100](https://github.com/sdv-dev/CTGAN/issues/100) by fealho
* Update dependencies and testing - [Issue 90](https://github.com/sdv-dev/CTGAN/issues/90) by csala