cpcp_df: Couplet and relaxed couplet county assignments.
In davidsovich/usgeogr: An R package for U.S. geographic data.

Description Usage Format Source

A dataset that assigns each county to a unique cluster using the "couplet" algorithm. Couplet clusters are defined as cross-border county pairs in which each constituent county does not appear in any other cross-border county pairs. Because each border county may belong to several cross-border county pairs, the "couplet" algorithm is needed to partition the space with the goal of maximizing the total number of couplet clusters. Couplet clusters are identified by cpcp_id; some counties are excluded from any couplet clusters by the algorithm. To resolve the issue of non-assignment of some border counties, the relaxed_cpcp_id identifier assigns non-matched border counties to the couplet their cross-borde neighbor. Metadata includes: (1) 499 unique couplet clusters mapped to 998 border counties, (2) 186 border counties without a matched couplet cluster, (3) 499 unique relaxed couplet clusters mapped to 1,183 border counties, (4) 1 border county without a matched relaxed couplet cluster.

cpcp_df

A data frame with 1,184 rows and 6 variables:

fips_code: County FIPS code, in original string format. Unique identifier.
county_state: State postal code corresponding to FIPS code.
cpcp_id: Couplet cluster pair identifier.
relaxed_cpcp_id: Relaxed couplet cluster pair identifier.
cpcp_remove_flag: Binary flag equal to one if a county is unmatched to a couplet cluster.
relaxed_cpcp_remove_flag: Binary flag equal to one if a county is unmatched to a relaxed couplet cluster.