I'm looking to migrating my functions to the newly minted across.
A function I have searches several key words across several columns using filter_at.
However, I am struggling to replicate this using across as shown below:
library(tidyverse)
raw_df <- tibble::tribble(
~cust_name, ~other_desc, ~trans, ~val,
"Cisco", "nothing", "a", 100L,
"bad_cs", "cisCo", "s", 101L,
"Ibm", "nothing", "d", 102L,
"bad_ib", "ibM", "f", 102L,
"oraCle", "Oracle", "g", 103L,
"mSft", "nothing", "k", 103L,
"noth", "Msft", "j", 104L,
"noth", "oracle", "l", 104L
)
search_string = c("ibm", "cisco")
# Done using `filter_at`
raw_df %>%
filter_at(.vars = vars(cust_name, other_desc),
.vars_predicate = any_vars(str_detect(., regex(paste(search_string, collapse = "|"), ignore_case = TRUE)))
) %>% unique()
# Not able to replicate result with `across`
raw_df %>%
filter(across(
.cols = c(cust_name, other_desc),
.fns = ~str_detect(.), regex(paste(search_string, collapse = "|"), ignore_case = TRUE)))
raw_df %>%
filter(str_detect,
across(any_of(cust_name, other_desc),
regex(paste(search_string, collapse = "|"), ignore_case = TRUE)))
Combine across with Reduce to select rows which has any occurrence of the pattern.
library(dplyr)
library(stringr)
pat <- paste(search_string, collapse = "|")
raw_df %>%
filter(Reduce(`|`, across(c(cust_name, other_desc),
~str_detect(., regex(pat, ignore_case = TRUE)))))
However, I think using if_any is more suitable here as it was build to handle such cases -
raw_df %>%
filter(if_any(c(cust_name, other_desc),
~str_detect(., regex(pat, ignore_case = TRUE))))
# cust_name other_desc trans val
# <chr> <chr> <chr> <int>
#1 Cisco nothing a 100
#2 bad_cs cisCo s 101
#3 Ibm nothing d 102
#4 bad_ib ibM f 102