Match addr_street vectors

A single addr_street in y is chosen for each addr_street in x. If exact matches (using as.character) are not found, candidate matches are chosen by fuzzy matching on street name (using phonetic street key and street name) and exact matching on the enabled street components. Ordinal street names use restricted phonetic candidates: an ordinal phonetic key like #0007 may fuzzy match only to plausible ordinal neighbors such as digit shifts (#0070, #0700, #7000) or same-width substitutions (#0008, #0009), not arbitrary OSA-distance-one ordinal keys such as #0017 or #0077. If multiple candidates remain after fuzzy matching, the first candidate in y is returned.

addr_street objects with missing or empty @name are not matched and returned as missing instead.

Usage

match_addr_street(
  x,
  y,
  name_phonetic_dist = 1L,
  name_fuzzy_dist = 2L,
  match_street_predirectional = TRUE,
  match_street_posttype = TRUE,
  match_street_pretype = TRUE,
  match_street_postdirectional = FALSE
)

Arguments

x, y

addr_street vectors to match

name_phonetic_dist

integer; maximum optimized string alignment distance between phonetic_street_key() of x and y to consider a possible match

name_fuzzy_dist

integer; maximum optimized string alignment distance between @name of x and y to consider a possible match

match_street_predirectional

logical; require street predirectional to match when selecting street candidates?

match_street_posttype

logical; require street posttype to match when selecting street candidates?

match_street_pretype

logical; require street pretype to match when selecting street candidates?

match_street_postdirectional

logical; require street postdirectional to match when selecting street candidates?

Value

An addr_street vector, the same length as x, containing the selected match in y for each element of x. Unmatched elements are returned as missing addr_street() values.

Examples

my_streets <- addr_street(
   predirectional = "",
   premodifier = "",
   pretype = "",
   name = c("Beechview", "Vivian", "Springfield", "Round Bottom", "Pfeiffer", "Beachview",
            "Vevan", "Srpingfield", "Square Top", "Pfeffer", "Wuhlper", ""),
  posttype = c("Cir", "Pl", "Pike", "Rd", "Rd", "Cir", "Pl", "Pike", "Rd", "Rd", "Ave", ""),
  postdirectional = ""
 )
the_streets <- nad_example_data()$nad_addr@street
match_addr_street(my_streets, the_streets)
#> <addr_street> function ()  
#>  @ predirectional : chr [1:12] "" "" "" "" "" "" "" "" NA "" "" NA
#>  @ premodifier    : chr [1:12] "" "" "" "" "" "" "" "" NA "" "" NA
#>  @ pretype        : chr [1:12] "" "" "" "" "" "" "" "" NA "" "" NA
#>  @ name           : chr [1:12] "BEECHVIEW" "VIVIAN" "SPRINGFIELD" "ROUND BOTTOM" ...
#>  @ posttype       : chr [1:12] "Cir" "Pl" "Pike" "Rd" "Rd" "Cir" "Pl" "Pike" NA "Rd" ...
#>  @ postdirectional: chr [1:12] "" "" "" "" "" "" "" "" NA "" "" NA

toggle_y <- addr_street(
  predirectional = c("E", "", "", "E"),
  premodifier = "",
  pretype = c("", "", "US Hwy", "US Hwy"),
  name = c("14th", "Oak", "Main", "Main"),
  posttype = c("St", "Rd", "Rd", "Rd"),
  postdirectional = c("", "", "", "E"),
  map_pretype = FALSE,
  map_posttype = FALSE,
  map_directional = FALSE,
  map_ordinal = FALSE
)

# predirectional is required by default, so blank "14th St" stays unmatched
format(match_addr_street(
  addr_street(
    predirectional = "",
    premodifier = "",
    pretype = "",
    name = "14th",
    posttype = "St",
    postdirectional = "",
    map_pretype = FALSE,
    map_posttype = FALSE,
    map_directional = FALSE,
    map_ordinal = FALSE
  ),
  toggle_y
))
#> [1] ""
format(match_addr_street(
  addr_street(
    predirectional = "",
    premodifier = "",
    pretype = "",
    name = "14th",
    posttype = "St",
    postdirectional = "",
    map_pretype = FALSE,
    map_posttype = FALSE,
    map_directional = FALSE,
    map_ordinal = FALSE
  ),
  toggle_y,
  match_street_predirectional = FALSE
))
#> [1] "E 14th St"

# posttype can also be made optional during fuzzy street-name matching
format(match_addr_street(
  addr_street(
    predirectional = "",
    premodifier = "",
    pretype = "",
    name = "Oka",
    posttype = "Ave",
    postdirectional = "",
    map_pretype = FALSE,
    map_posttype = FALSE,
    map_directional = FALSE,
    map_ordinal = FALSE
  ),
  toggle_y,
  name_fuzzy_dist = 1L
))
#> [1] ""
format(match_addr_street(
  addr_street(
    predirectional = "",
    premodifier = "",
    pretype = "",
    name = "Oka",
    posttype = "Ave",
    postdirectional = "",
    map_pretype = FALSE,
    map_posttype = FALSE,
    map_directional = FALSE,
    map_ordinal = FALSE
  ),
  toggle_y,
  name_fuzzy_dist = 1L,
  match_street_posttype = FALSE
))
#> [1] "Oak Rd"

# pretype is required by default; postdirectional can also be required
format(match_addr_street(
  addr_street(
    predirectional = "E",
    premodifier = "",
    pretype = "US Hwy",
    name = "Mian",
    posttype = "Rd",
    postdirectional = "E",
    map_pretype = FALSE,
    map_posttype = FALSE,
    map_directional = FALSE,
    map_ordinal = FALSE
  ),
  toggle_y,
  match_street_pretype = FALSE,
  name_fuzzy_dist = 1L
))
#> [1] "E US Hwy Main Rd E"
format(match_addr_street(
  addr_street(
    predirectional = "E",
    premodifier = "",
    pretype = "US Hwy",
    name = "Mian",
    posttype = "Rd",
    postdirectional = "E",
    map_pretype = FALSE,
    map_posttype = FALSE,
    map_directional = FALSE,
    map_ordinal = FALSE
  ),
  toggle_y,
  name_fuzzy_dist = 1L
))
#> [1] "E US Hwy Main Rd E"
format(match_addr_street(
  addr_street(
    predirectional = "E",
    premodifier = "",
    pretype = "US Hwy",
    name = "Mian",
    posttype = "Rd",
    postdirectional = "E",
    map_pretype = FALSE,
    map_posttype = FALSE,
    map_directional = FALSE,
    map_ordinal = FALSE
  ),
  toggle_y,
  name_fuzzy_dist = 1L,
  match_street_pretype = TRUE,
  match_street_postdirectional = TRUE
))
#> [1] "E US Hwy Main Rd E"