An implementation of the Random Cut Forest data structure for sketching streaming data, with support for anomaly detection, density estimation, imputation, and more.
Description of changes: Floating point operations are non-commutative and even if addition and subtraction (of single precision numbers) are performed in double precision over large enough dimensions, the floating points may conspire for an anomalous scenario (a reproducible test is provided). That scenario is explicitly ruled out in this change and debug statements are added for future.
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.
Issue #, if available: 374
Description of changes: Floating point operations are non-commutative and even if addition and subtraction (of single precision numbers) are performed in double precision over large enough dimensions, the floating points may conspire for an anomalous scenario (a reproducible test is provided). That scenario is explicitly ruled out in this change and debug statements are added for future.
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.