Sweep polygon Moran's I across (category x year)

Loops morie_tps_polygon_morans_i over a grid of value-column prefixes and years, returning the resulting matrix of Moran's I values for downstream visualisation as a heatmap.

Usage

morie_tps_moran_sweep_heatmap(
  polygons,
  category_prefixes = NULL,
  years = NULL,
  k_neighbours = 5L,
  ds_name = "NeighbourhoodCrimeRates",
  centroid_lat_col = "lat",
  centroid_lon_col = "lon"
)

Arguments

polygons

An sf object or data.frame with centroid columns and per-year value columns.

category_prefixes

Character vector of column prefixes. Defaults to the 9 published TPS rate categories.

years

Integer vector of years. Defaults to 2014:2024.

k_neighbours

k for the k-NN weights graph passed down.

ds_name

Tag for the result title.

centroid_lat_col, centroid_lon_col

Centroid column names forwarded to morie_tps_polygon_morans_i.

Value

A named list with the (category x year) Moran's I matrix.

Details

Column names are constructed as paste0(prefix, "_", year).

Examples

set.seed(2026)
polys <- data.frame(
  HOOD_ID = letters[1:16],
  lat = rep(43.6 + (0:3) * 0.02, 4),
  lon = rep(-79.4 + (0:3) * 0.02, each = 4),
  ASSAULT_RATE_2023 = rpois(16, 30),
  ASSAULT_RATE_2024 = rpois(16, 32),
  HOMICIDE_RATE_2023 = rpois(16, 2),
  HOMICIDE_RATE_2024 = rpois(16, 2)
)
morie_tps_moran_sweep_heatmap(polys,
  category_prefixes = c("ASSAULT_RATE", "HOMICIDE_RATE"),
  years = c(2023L, 2024L),
  centroid_lat_col = "lat", centroid_lon_col = "lon")
#> Moran's I sweep -- 2 categories x 2 years
#> =========================================
#> Call: morie_tps_moran_sweep_heatmap(cats=2, years=2) 
#> 
#>   Categories  2
#>   Years       2023-2024
#>   Min I       -0.13028
#>   Max I       0.090545
#> 
#> Swept polygon Moran's I across 2 category prefix(es) and 2 year(s) (2023-2024). Min I = -0.130, max I = +0.091; positive values indicate spatial autocorrelation in the corresponding crime rate across neighbourhoods.