alibi-detect

alibi-detect copied to clipboard

Review data_type in meta

1

> Not isolated to this PR, but noting that we seem to be a little inconsistent across the new and old outlier detectors wrt to when `data_type` is hard-coded, and...

mauicv

Update torch requirement from <1.14.0,>=1.7.0 to >=1.7.0,<3.0.0

7

Updates the requirements on [torch](https://github.com/pytorch/pytorch) to permit the latest version. Release notes Sourced from torch's releases. PyTorch 2.0: Our next generation release that is faster, more Pythonic and Dynamic as...

dependabot[bot]

- [ ] Outlier detector arguments should be in a consistent order across all outlier detectors - [ ] Outlier detector args and docstrings arg descriptions should be in correct...

mauicv

Issue: Feature-level p-values are not generated by the Spot-the-diff algorithm

2

**Description:** Feature-level p-values are not generated by the Spot-the-diff algorithm during drift detection, despite proper implementation. No specific parameters or options were found to control the generation of feature-level p-values

Gaurav-Sahu-TA

`gmm` and `svm` set defaults in multiple locations for the fit method call. Once in the fit method itself and then again in `format_fit_kwargs`. Ideally, these should only be set...

mauicv

This issue is to track tests that we skip currently because the Gaussian kernel is not torch scriptable. - [test 1](https://github.com/SeldonIO/alibi-detect/blob/df48c949520ad5821f9f7aa991c0da8ef2f3b474/alibi_detect/od/tests/test__knn/test__knn_backend.py#L118) - [test 2](https://github.com/SeldonIO/alibi-detect/blob/5e69f4bd71ed9a1cc640df0faa725a8c1c1ca28f/alibi_detect/od/tests/test__lof/test__lof_backend.py#L118)

mauicv

> In a few places `outlying` is used e.g. https://github.com/SeldonIO/alibi-detect/blob/21ca540f5b0ff8f2ee312e7a30ace0d27c238435/alibi_detect/od/_mahalanobis.py#L96 > whereas in the `score` docstring (and for `_pca`, `_gmm`, `_knn`, `mahalanobis`) `anomalous` is used. Worth picking one or the...

mauicv

see [this](https://github.com/SeldonIO/alibi-detect/pull/746#discussion_r1206730082) comment. This should be done for both LOF and KNN.

mauicv

An error occurred in the _configure_kernel_centers function in the LSDDOnlineDrift class

3

Hi, When I run drift detection with LSDDOnlineDrift class, the following error occurred. [Error Message] InvalidArgumentError: cannot compute AddV2 as input #1(zero-based) was expected to be a double tensor but...

KevinRyu

Drift Detection Methods -> Learned Kernel -> Dataset format incompatible

4

**I am facing a format incompatibility issue. I have tried to follow the structure here (https://docs.seldon.io/projects/alibi-detect/en/stable/cd/methods/learnedkerneldrift.html). I could not understand properly the (imput) file format required/needed. Could someone help me,...

righelcpm