search

linkedin / isolation-forest

A Spark/Scala implementation of the isolation forest unsupervised outlier detection algorithm with support for exporting in ONNX format.
Other
223 stars 47 forks source link

PySpark support #25

Closed bgreenwell closed 3 years ago

bgreenwell commented 3 years ago

First off, thank you for making this available. I’m wondering if anyone has had success in interfacing with this via Python/pyspark (or sparkR for that matter)? If not, is it possible? Given my limited experience with PySpark, it seems very possible.

jverbus commented 3 years ago

This isolation forest library is leveraged by Microsoft's MMLSpark to provide isolation forest functionality in the latter. MMLSpark automatically provides python and R bindings.

You can try it out here: https://github.com/Azure/mmlspark

jverbus commented 3 years ago

Closing this. Please let me know if you have success with the MMLSpark recommendation above for python / R bindings.