将参数传递给R fuzzyjoin::fuzzy_join中的多个fuzzyjoin：：fuzzy_join函数

Question

我回答了这些two questions，得到了一个适当的解决方案，但是我很难将使用fuzzy_join的参数传递到从fuzzyjoin::stringdist_join提取的match_fun中。在本例中，我使用了多个match_ of的组合，包括这个定制的match_fun_stringdist，以及用于精确匹配和标准匹配的==和<=。

我得到的错误消息是：

# 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

Answer 1

我认为这个错误是因为传递给多个match_fun的每个参数都搞砸了它，即不能将额外的参数(最初只用于ignore_case string_dist match_fun )传递给match_fun of >=

解决方案是用固定的参数为参数定义我自己的match_ my。请参见下面使用固定参数定义自己的match_fun_stringdist的位置。我在这里还在另一个问答https://stackoverflow.com/a/44383103/4663008中实现了它。

# First, need to define match_fun_stringdist 
# Code from stringdist_join from https://github.com/dgrtwo/fuzzyjoin
match_fun_stringdist <- function(v1, v2) {

  # Can't pass these parameters in from fuzzy_join because of multiple incompatible match_funs, so I set them here.
  ignore_case = FALSE
  method = "dl"
  max_dist = 99
  distance_col = "dist"

  if (ignore_case) {
    v1 <- stringr::str_to_lower(v1)
    v2 <- stringr::str_to_lower(v2)
  }

  # shortcut for Levenshtein-like methods: if the difference in
  # string length is greater than the maximum string distance, the
  # edit distance must be at least that large

  # length is much faster to compute than string distance
  if (method %in% c("osa", "lv", "dl")) {
    length_diff <- abs(stringr::str_length(v1) - stringr::str_length(v2))
    include <- length_diff <= max_dist

    dists <- rep(NA, length(v1))

    dists[include] <- stringdist::stringdist(v1[include], v2[include], method = method)
  } else {
    # have to compute them all
    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
}

打电话给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")