sensAI
sensAI copied to clipboard
aai-institute
The Python library for sensible AI.
The current class [TorchModel](https://github.com/aai-institute/sensAI/blob/develop/src/sensai/torch/torch_base.py#L97) has the following init: ```python class TorchModel(ABC, ToStringMixin): """ sensAI abstraction for torch models, which supports one-line training, allows for convenient model application, has basic mechanisms...
Right now, we cannot deal with this when using categorical default rules, as they will render the categorical features _unsupported_ rather than _ignored_. While I am not aware of models...
The `ColumnGeneratorCachedByIndex` is recommended for new cached column generators, but it can be significantly slower than the not-recommended way of first creating a ColumnGenerator and then adding cache by wrapping...
I'm not sure how many breaking changes this would cause. One thing I found is that `IndexCachedColumnGenerator` is broken since [iteritems is no longer supported on Series](https://stackoverflow.com/questions/76200452/error-while-iterating-over-dataframe-columns-entries-attributeerror-series) 
persist several types of models via the v0-legacy branch and add tests that load and apply them: torch models and sk learn models alike, classification and regression
1. Update the notebooks that are still relevant to use sensAI v1 and re-enable the respective tests in `test_notebooks.py`. 2. Include the notebooks that provide useful documentation in `index.rst` (most...
various combinations, e.g. classification with and without probabilities
See https://github.com/jambit/sensAI/runs/2884663556?check_suite_focus=true RuntimeError: Kernel died before replying to kernel_info zmq.error.ZMQError: Address already in use @MischaPanch, are you familiar with such errors? Could this be related to the newly introduced caching...
This will include new metrics (like intersection over union, stuctural similarity indices and so on) and also new visualization methods for the special case of 2-dim. data.