5.2 REDCAP

Regionalization with dynamically constrained agglomerative clustering and partitioning (REDCAP) is developed by D. Guo (2008). Like SKATER, REDCAP starts from building a spanning tree in 4 different approaches (single-linkage, average-linkage, complete-linkage, and wards-linkage). Then, REDCAP provides 2 different approaches (first‐order and full-order constraining) to prune the tree to find clusters. The REDCAP with first-order approach using a minimum spanning tree is exactly the same as SKATER. For more information, please read https://geodacenter.github.io/workbook/9c_spatial3/lab9c.html#redcap

redcap()

redcap() is a PostgreSQL WINDOW function. Please call it with an OVER clause.

Synopsis

Short version 1:

integer redcap(integer k, anyarray vals, bytea weights, 
    character varying method
)

Short version 2:

integer skater(integer k, anyarray vals,  bytea weights, 
    character varying method, integer min_region_size
)

Short version 3:

integer redcap(integer k, anyarray vals,  bytea weights, 
    character varying method, numeric bound_vas, float min_bound
)

Full version 1:

integer redcap(integer k, anyarray vals,  bytea weights, 
    character varying method, integer min_region_size,
    character varying scale_method,
    character varying distance_type,
    integer seed,
    integer cpu_threads)

Full version 2:

integer redcap(integer k, anyarray vals,  bytea weights, 
    character varying method, numeric bound_val, float min_bound,
    character varying scale_method,
    character varying distance_type,
    integer seed,
    integer cpu_threads)

Arguments

Name	Type	Description
k	integer	the number of clusters
vals	anyarray	an array of the numeric columns that contains the values for skater
weights	bytea	a bytea column that stores the spatial weights information
method	character varying	the redcap method. Options are {"firstorder-singlelinkage", "fullorder-completelinkage", "fullorder-averagelinkage","fullorder-singlelinkage", "fullorder-wardlinkage"}
bound_val	numeric	the numeric column of a bound variable
min_bound	float	the minimum bound value that applies to all clusters
scale_method	character varying	the scaling method applies to vals. Options are {'raw', 'standardize', 'demean', 'mad', 'range_standardize', 'range_adjust'}. Default: 'standardize'
distance_method	character varying	the distance metric used to measure the distance in attribute space of input vals. Options are {'euclidean', 'manhattan'. Default: 'euclidean'.
seed	integer	the seed for random number generator used in LISA statistics. Default: 123456789.
cpu_threads	integer	the number of CPU threads used for parallel LISA computation. Default: 6.

Return

Type	Description
integer	the cluster indicator

Examples

Apply redcap (fullorder-completelinkage) to create 10 spatially constrained clusters using variable ["hr60", "ue60", "dv60"] (homicide, unemployment, divorce rate 1960 in natregimes dataset) and queen contiguity weights "queen_w":

Please see chapter 'Contiguity Based Weights' for how to create a Queen contiguity weights.

SELECT redcap(10, ARRAY[hr60, ue60, dv60], queen_w, 'fullorder-completelinkage') OVER() FROM natregimes;

 redcap 
--------
      2
      2
      1
      2
      1
      3
      2
 ...