An implementation of the Random Cut Forest data structure for sketching streaming data, with support for anomaly detection, density estimation, imputation, and more.
RCFs can produce the expected value while scoring an anomaly -- however that expected value computation requires more data than is required to determine anomaly/non-anomaly. In addition, some anomalies will always be detected late. Currently, if there is a late anomaly detected within the first 100 points then the past values are not set. While this can be fixed in the code invoking RCF, it may be simpler to have it solved inside RCF.
RCFs can produce the expected value while scoring an anomaly -- however that expected value computation requires more data than is required to determine anomaly/non-anomaly. In addition, some anomalies will always be detected late. Currently, if there is a late anomaly detected within the first 100 points then the past values are not set. While this can be fixed in the code invoking RCF, it may be simpler to have it solved inside RCF.