Carles Sala

Rename Score to Severity

2

Currently, the `analyze` method returns a column called `score`, which indicates the severity of the anomaly. This name is also in the Database Schema, currently as part a field of...

### Problem Description Currently (and even after #135) is resolved, the last batch from the dataset loader is dropped if it is shorter than the batch size, potentially resulting in...

PAR model cannot fit if sequence index is type `date` instead of `datetime`

1

### Environment Details Please indicate the following details about the environment in which you found the bug: * SDV version: 0.10.0 ### Error Description A Sequence index of type `date`...

### Problem Description Current SDV implementation only supports individual column keys of type `integer` and `string`. We should extend this to support other options such as key values of other...

Add `random_state` arguments wherever relevant

1

There have been a few questions, such as #515 and #299 about how to set a random state for the models. External workarounds exist, like the one shared in those...

Add methods to explore the modeled parameters after modeling. SDV should have a `visualize` or `explain` or `view` method to obtain details about the parameters learned during the modeling. When...

Issue #348 was resolved including unit tests that certify that individual errors are added to a list. Integration should be added/extended to test metadata validation with multiple errors, asserting that...

### Error Description When HMA1 is used with a non-parametrical model the message that informs the user about the model not being parametric is being wrongly caught on this `try/except`...

PRs #334 and #277 introduced new CTGAN hyperparameters that are not properly exposed in the `CopulaGAN` class, either because they are just not there, like `pac`, or because they are...

Drop Python 3.5 support and start supporting Python 3.9

2

On September 13th 2020 Python 3.5 reached its end of life, so we can stop explicitly supporting it. On the other side, on October 5th, Python 3.9 was released, so...