GetNumTrainingValues: Get Number of Training Values

In otsad: Online Time Series Anomaly Detectors

Description

GetNumTrainingValues Calculates the number of values to be used as a training set.

Usage

GetNumTrainingValues(n.row, prob.percent = 0.15)

Arguments

n.row	Number of rows of the all dataset with training and test values.
prob.percent	Percentage of training values

Details

the number of values to be used as a training set is calculated as a minimum between 15% of the number of rows in the dataset and 15% of 5000.

Value

Number of training values.

References

A. Lavin and S. Ahmad, “Evaluating Real-time Anomaly Detection Algorithms – the Numenta Anomaly Benchmark,” in 14th International Conference on Machine Learning and Applications (IEEE ICMLA’15), 2015.

Examples

## Generate data
set.seed(100)
n <- 180
x <- sample(1:100, n, replace = TRUE)
x[70:90] <- sample(110:115, 21, replace = TRUE)
x[25] <- 200
x[150] <- 170
df <- data.frame(timestamp = 1:n, value = x)

# Get number of instances to train phase
GetNumTrainingValues(nrow(df))

otsad documentation built on Sept. 6, 2019, 5:02 p.m.