DynamicNormalizer: Dinamyc normalizer

In alaineiturria/otsad: Online Time Series Anomaly Detectors

Dinamyc normalizer

Description

R6 class that implements the unsupervised dynamic z-score standardization proposed by Bollegala. This method allows normalizing the data sets in an online manner, by z-score standardization, dynamically updating the mean and the variance whenever a new data arrives.

Methods

Public methods

• DynamicNormalizer$new()

• DynamicNormalizer$normalize()

• DynamicNormalizer$denormalize()

---

Method new()

Create a new DynamicNormalizer object.

Usage

DynamicNormalizer$new()

Returns

A new DynamicNormalizer object.

---

Method normalize()

Normalizes the current data value.

Usage

DynamicNormalizer$normalize(x)

Arguments

x

Current data value to be normalized.

Returns

If return_point = FALSE then normalized current window is returned, else, normalized current data point is returned.

---

Method denormalize()

Denormalizes the current data value.

Usage

DynamicNormalizer$denormalize(y)

Arguments

y

Current data value to be denormalized.

Returns

Denormalized current data point.

References

D. Bollegala, Dynamic feature scaling for online learning of binary classifiers, Knowledge-Based Syst., vol. 129, pp. 97–105, 2017.

Examples

normalizer <- DynamicNormalizer$new()

normalizer$normalize(10)
normalizer$normalize(15)
normalizer$normalize(20)
normalizer$normalize(10)
normalizer$normalize(30)
normalizer$normalize(15)

normalizer$denormalize(-0.2214036)

alaineiturria/otsad documentation built on Jan. 12, 2023, 12:26 p.m.