tune_cpdbee_2D: Tunes 2D event detection using labeled data

In eventstream: Streaming Events and their Early Classification

Tunes 2D event detection using labeled data

Description

This function finds best parameters for 2D event detection using labeled data.

Usage

tune_cpdbee_2D(
  x,
  cl,
  alpha_min = 0.95,
  alpha_max = 0.98,
  alpha_step = 0.01,
  epsilon_min = 2,
  epsilon_max = 12,
  epsilon_step = 2,
  minPts_min = 4,
  minPts_max = 12,
  minPts_step = 2
)

Arguments

x	The data in an mxn matrix or dataframe.
cl	The actual locations of the events.
alpha_min	The minimum threshold value.
alpha_max	The maximum threshold value.
alpha_step	The incremental step size for alpha.
epsilon_min	The minimum epsilon value for DBSCAN clustering.
epsilon_max	The maximum epsilon value for DBSCAN clustering.
epsilon_step	The incremental step size for epsilon for DBSCAN clustering.
minPts_min	The minimum minPts value for for DBSCAN clustering.
minPts_max	The maximum minPts value for for DBSCAN clustering.
minPts_step	The incremental step size for minPts for DBSCAN clustering.

Value

A list with following components

best	The best threshold, epsilon and MinPts for 2D event detection and the associated Jaccard Index.
all	All parameter values used and the associated Jaccard Index values.

Examples

## Not run: 
out <- gen_stream(1, sd=15)
zz <- as.matrix(out$data)
clst <- get_clusters(zz, filename = NULL, thres = 0.95, 
                    vis = TRUE, epsilon = 5, miniPts = 10, 
                    rolling = FALSE)
clst_loc <- clst$data[ ,1:2]
out <- tune_cpdbee_2D(zz, clst_loc)
out$best

## End(Not run)

eventstream documentation built on May 16, 2022, 9:06 a.m.