AnomalyDetectorFunction
represents a function generated by AnomalyDetection for detecting whether data is anomalous or not.
Details and Options
- AnomalyDetectorFunction works like Function.
- AnomalyDetectorFunction[…][data] returns True if it considers data to be anomalous, and False otherwise.
- AnomalyDetectorFunction[…][{data1,data2,…}] tests all the datai.
- AnomalyDetectorFunction[…][data,prop] gives the specified property of the anomaly detection associated with data.
- Possible properties include:
-
"Decision" whether the data is anomalous or not (default) "RarerProbability" probability to generate a sample with lower PDF than data - The following options can be given:
-
AcceptanceThreshold 0.001 RarerProbability threshold to consider an example anomalous PerformanceGoal Automatic aspects of performance to optimize - Possible settings for PerformanceGoal include:
-
"Quality" maximize the quality of the detection "Speed" maximize speed of the detection Automatic automatic tradeoff between speed and quality - AnomalyDetectorFunction[…] can also be used with FindAnomalies to detect anomalous examples.
Examples
open allclose allBasic Examples (2)Summary of the most common use cases
Train a detector function on a numeric dataset:
https://wolfram.com/xid/0vvb49ddnlhru66n8z2-5hhlm7
Use the trained detector to find examples that are considered anomalous:
https://wolfram.com/xid/0vvb49ddnlhru66n8z2-38oizs
Find rarer probabilities of new examples:
https://wolfram.com/xid/0vvb49ddnlhru66n8z2-zf8jkp
Train an AnomalyDetectorFunction on a two-dimensional array of pseudorandom real numbers:
https://wolfram.com/xid/0vvb49ddnlhru66n8z2-euyqat
Use the trained AnomalyDetectorFunction to find anomalies in new examples with FindAnomalies:
https://wolfram.com/xid/0vvb49ddnlhru66n8z2-rh2y4d
Find anomalies and their corresponding positions:
https://wolfram.com/xid/0vvb49ddnlhru66n8z2-uraw86
Scope (1)Survey of the scope of standard use cases
Train an AnomalyDetectorFunction on a list of colors:
https://wolfram.com/xid/0vvb49ddnlhru66n8z2-yygqof
Attempt to find outliers in a list of colors using the trained anomaly detector:
https://wolfram.com/xid/0vvb49ddnlhru66n8z2-wbj35k
Obtain information on the trained anomaly detector:
https://wolfram.com/xid/0vvb49ddnlhru66n8z2-6jmxzt
Obtain information on training time:
https://wolfram.com/xid/0vvb49ddnlhru66n8z2-uqhe6z
https://wolfram.com/xid/0vvb49ddnlhru66n8z2-2pd8cv
Options (1)Common values & functionality for each option
AcceptanceThreshold (1)
Create a dataset sampled from two different distributions:
https://wolfram.com/xid/0vvb49ddnlhru66n8z2-lrvca8
Train an anomaly detector function:
https://wolfram.com/xid/0vvb49ddnlhru66n8z2-dagdzy
Find anomalous/non-anomalous examples by specifying the AcceptanceThreshold:
https://wolfram.com/xid/0vvb49ddnlhru66n8z2-bjdt1k
Wolfram Research (2019), AnomalyDetectorFunction, Wolfram Language function, https://reference.wolfram.com/language/ref/AnomalyDetectorFunction.html.
Text
Wolfram Research (2019), AnomalyDetectorFunction, Wolfram Language function, https://reference.wolfram.com/language/ref/AnomalyDetectorFunction.html.
Wolfram Research (2019), AnomalyDetectorFunction, Wolfram Language function, https://reference.wolfram.com/language/ref/AnomalyDetectorFunction.html.
CMS
Wolfram Language. 2019. "AnomalyDetectorFunction." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/AnomalyDetectorFunction.html.
Wolfram Language. 2019. "AnomalyDetectorFunction." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/AnomalyDetectorFunction.html.
APA
Wolfram Language. (2019). AnomalyDetectorFunction. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/AnomalyDetectorFunction.html
Wolfram Language. (2019). AnomalyDetectorFunction. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/AnomalyDetectorFunction.html
BibTeX
@misc{reference.wolfram_2024_anomalydetectorfunction, author="Wolfram Research", title="{AnomalyDetectorFunction}", year="2019", howpublished="\url{https://reference.wolfram.com/language/ref/AnomalyDetectorFunction.html}", note=[Accessed: 10-January-2025
]}
BibLaTeX
@online{reference.wolfram_2024_anomalydetectorfunction, organization={Wolfram Research}, title={AnomalyDetectorFunction}, year={2019}, url={https://reference.wolfram.com/language/ref/AnomalyDetectorFunction.html}, note=[Accessed: 10-January-2025
]}