specifying categorical features in Python Outlier Detection (PyOD)

[shivasheeshyadav]

How to specify the categorical features in PyOD when using Histogram-based Outlier Detection (HBOS) for anomaly detection ? I've read that HBOS can be used for anomaly detection when there are categorical features involved. I found it's Python implementation here: https://pyod.readthedocs.io/en/latest/pyod.models.html#module-pyod.models.hbos But I can't figure out how should I pass the position or list of names of categorical features of my dataset while training the model. The code I've tried:

clf = HBOS(n_bins=10, alpha=0.1, tol=0.5, contamination=0.1)
clf.fit(train_df)
train_pred = clf.labels_

There is no parameter to mention categorical features while training.

[yzhao062]

Hi there, Sorry for responding late. Unfortunately, this function has not been implemented. One temporary workaround is to turn your categorical into numerical (not a good idea though). Will update you once have this func in place.

[shivasheeshyadav]

@yzhao062 Thanks. What do you suggest then, Label encoding or OneHot encoding of the categorical features ?

[2994186010]

@yzhao062 @shivasheeshyadav , my dataset contains categorical features. Can pyod process categorical features in pyod now? What do you suggest to do with the categorical features?

[Stevod]

Any update on this essential feature for categorical anomaly detection?

[alik604]

@Stevod do you have any ideas on how you will handle this. I've been using this library for the last 3 months, and am now realizing the accuracy could be higher, since all the features I'm working with are categorical.