nrkarthikeyan
nrkarthikeyan
This can be implemented for the "classic": https://github.com/Trusted-AI/AIF360/blob/master/aif360/metrics/classification_metric.py as well as the sklearn-compatible: https://github.com/Trusted-AI/AIF360/blob/master/aif360/sklearn/metrics/metrics.py versions
What version of the metric are you using? There are two versions - one is sklearn compatible and one is not. https://github.com/Trusted-AI/AIF360/blob/faa75ee0cfffb57ecb921b8ea36970e0bda669f5/aif360/sklearn/metrics/metrics.py#L352 https://github.com/Trusted-AI/AIF360/blob/faa75ee0cfffb57ecb921b8ea36970e0bda669f5/aif360/metrics/classification_metric.py#L838
related to #74 and #85?
@monindersingh , can you take a look and see what if any can be done and provide your thoughts? @psortos you are also welcome to provide your thoughts on how...
@monindersingh - FYI, this may address some of the questions you had.
`numpy.nonzero` returns both row and column indices and we want only row indices. Was your dataset labels a 2D array?
@FrieseWoudloper please provide more details. @gdequeiroz ^^^
@pronics2004 ^^^. If we agree that this is a genuine issue, may be @giandos200 - you can open a PR.
From my tests, this partially fixes the issue (reduces memory usage by about half), so we have some more way to go.
@hoffmansc and I will work on this.