This function calculates ignition points for all clusters.
Arguments
- lon
Numeric. A vector of longitude values.
- lat
Numeric. A vector of latitude values.
- obsTime
Date/Datetime/Numeric. A vector of observed time.
- timeUnit
Character. One of "s" (seconds), "m"(minutes), "h"(hours), "d"(days) and "n"(numeric).
- timeID
Integer (>=1). A vector of time indexes.
- membership
Integer. A vector of membership labels.
- ignitionCenter
Character. Method of calculating ignition points, one of "mean" and "median".
Value
A data frame of ignition points
membership: Membership labels.lon: Longitude of ignition points.lat: Latitude of ignition points.obsTime: Observed time of ignition points.timeID: Time indexes.obsInCluster: Number of observations in the cluster.clusterTimeLen: Length of time of the cluster.clusterTimeLenUnit: Unit of length of time of the cluster.
Details
For more details about the clustering algorithm and the argument
timeUnit, timeID and ignitionCenter,
please check the documentation of hotspot_cluster().
This function performs the step 5 of the clustering algorithm. It
calculates ignition points.
For a cluster, when there are multiple earliest hot spots, if
ignitionCenter is "mean", the centroid of these hot spots will be used
as the ignition point. If ignitionCenter is "median", median longitude
and median latitude of these hot spots will be used.
Examples
# Define lon, lat, obsTime, timeID and membership for 10 observations
lon <- c(141.1, 141.14, 141.12, 141.14, 141.16, 141.12, 141.14,
141.16, 141.12, 141.14)
lat <- c(-37.10, -37.10, -37.12, -37.12, -37.12, -37.14, -37.14,
-37.14, -37.16, -37.16)
obsTime <- c(rep(1, 5), rep(26, 5))
timeUnit <- "n"
timeID <- c(rep(1, 5), rep(26, 5))
membership <- c(1, 1, 1, 1, 1, 2, 2, 2, 2, 2)
# Calculate the ignition points using different methods
ignition_point(lon, lat, obsTime, timeUnit, timeID, membership, "mean")
#>
#> ── ignitionCenter = "mean"
#> ✔ Compute ignition points for clusters
#> ℹ average hot spots : 5
#> ℹ average duration : 0 numeric
#> membership lon lat obsTime timeID obsInCluster clusterTimeLen
#> 1 1 141.132 -37.112 1 1 5 0
#> 2 2 141.136 -37.148 26 26 5 0
#> clusterTimeLenUnit
#> 1 n
#> 2 n
ignition_point(lon, lat, obsTime, timeUnit, timeID, membership, "median")
#>
#> ── ignitionCenter = "median"
#> ✔ Compute ignition points for clusters
#> ℹ average hot spots : 5
#> ℹ average duration : 0 numeric
#> membership lon lat obsTime timeID obsInCluster clusterTimeLen
#> 1 1 141.14 -37.12 1 1 5 0
#> 2 2 141.14 -37.14 26 26 5 0
#> clusterTimeLenUnit
#> 1 n
#> 2 n