I was answering these two questions and got an adequate solution, but I had trouble passing arguments using fuzzy_join
into the match_fun that I extracted from fuzzyjoin::stringdist_join
. In this case, I'm using a mix of multiple match_fun's, including this customized match_fun_stringdist
and also ==
and <=
for exact and criteria matching.
The error message I'm getting is:
# Error in mf(rep(u_x, n_y), rep(u_y, each = n_x), ...): object 'ignore_case' not found
# Data:
library(data.table, quietly = TRUE)
Address1 <- c("786, GALI NO 5, XYZ","rambo, 45, strret 4, atlast, pqr","23/4, 23RD FLOOR, STREET 2, ABC-E, PQR","45-B, GALI NO5, XYZ","HECTIC, 99 STREET, PQR")
AREACODE <- c('10','10','14','20','30')
Year1 <- c(2001:2005)
Address2 <- c("abc, pqr, xyz","786, GALI NO 4 XYZ","45B, GALI NO 5, XYZ","del, 546, strret2, towards east, pqr","23/4, STREET 2, PQR","abc, pqr, xyz","786, GALI NO 4 XYZ","45B, GALI NO 5, XYZ","del, 546, strret2, towards east, pqr","23/4, STREET 2, PQR")
Year2 <- c(2001:2010)
AREA_CODE <- c('10','10','10','20','30','40','50','61','64', '99')
data1 <- data.table(Address1, Year1, AREACODE)
data2 <- data.table(Address2, Year2, AREA_CODE)
data2[, unique_id := sprintf("%06d", 1:nrow(data2))]
# Solution:
library(fuzzyjoin, quietly = TRUE); library(dplyr, quietly = TRUE)
# First, need to define match_fun_stringdist
# Code from stringdist_join from https://github.com/dgrtwo/fuzzyjoin/blob/master/R/stringdist_join.R
match_fun_stringdist <- function(v1, v2, ...) {
if (ignore_case) {
v1 <- stringr::str_to_lower(v1)
v2 <- stringr::str_to_lower(v2)
}
dists <- stringdist::stringdist(v1, v2, method = method, ...)
ret <- dplyr::data_frame(include = (dists <= max_dist))
if (!is.null(distance_col)) {
ret[[distance_col]] <- dists
}
ret
}
# Call fuzzy_join
fuzzy_join(data1, data2,
by = list(x = c("Address1", "AREACODE", "Year1"), y = c("Address2", "AREA_CODE", "Year2")),
match_fun = list(match_fun_stringdist, `==`, `<=`),
mode = "left",
ignore_case = FALSE,
method = "dl",
max_dist = 99,
distance_col = "dist"
) %>%
group_by(Address1, Year1, AREACODE) %>%
top_n(1, -Address1.dist) %>%
top_n(1, Year2) %>%
select(unique_id, Address1.dist, everything())
#> Error in mf(rep(u_x, n_y), rep(u_y, each = n_x), ...): object 'ignore_case' not found