Create readr column specification using regular expression matching

Allows to define a regular expression per desired column specification object matching the respective column names.

Usage

cols_regex(..., .col_names, .default = readr::col_character())

Arguments

...: Named arguments where the names are (Perl-compatible) regular expressions and the values are column objects created by col_*(), or their abbreviated character names (as described in the col_types parameter of readr::read_delim()). Dynamic dots are supported.
.col_names: Column names which should be matched by ....
.default: Any named columns not matched by any of the regular expressions in ... will be read with this column type.

Value

A column specification.

Examples

library(magrittr)

# for some hypothetical CSV data column names like these...
col_names <- c("VAR1_Text",
               "VAR2_Text",
               "VAR3_Text_Other",
               "VAR1_Code_R1",
               "VAR2_Code_R2",
               "HAS_R1_Lag",
               "HAS_R2_Lag",
               "GARBAGEX67",
               "GARBAGEY09")

# ...a column spec could be created concisely as follows:
col_regex <- list("_Text(_|$)" = "c",
                  "_Code(_|$)" = "i",
                  "^GARBAGE"  = readr::col_skip())

pal::cols_regex(.col_names = col_names,
                !!!col_regex,
                .default     = "l")
#> cols(
#>   .default = col_logical(),
#>   VAR1_Text = col_character(),
#>   VAR2_Text = col_character(),
#>   VAR3_Text_Other = col_character(),
#>   VAR1_Code_R1 = col_integer(),
#>   VAR2_Code_R2 = col_integer(),
#>   GARBAGEX67 = col_skip(),
#>   GARBAGEY09 = col_skip()
#> )

# we can parse some real data:
raw_data <-
  httr::GET(paste0("http://www.web.statistik.zh.ch/ogd/data/",
                   "KANTON_ZUERICH_nrw_2019_listen_ergebnisse_gemeinde.csv")) |>
  httr::content(as = "text",
                encoding = "UTF-8")

readr::read_csv(file = raw_data,
                col_types = pal::cols_regex("^(Gemeindenamen|Partei)$" = "c",
                                            "(?i)anteil" = "d",
                                            .default = "i",
                                            .col_names = pal::dsv_colnames(raw_data)))
#> Warning: One or more parsing issues, call `problems()` on your data frame for details, e.g.:
#>   dat <- vroom(...)
#>   problems(dat)
#> # A tibble: 6 × 1
#>   `<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML 2.0//EN">`
#>                                                  <int>
#> 1                                                   NA
#> 2                                                   NA
#> 3                                                   NA
#> 4                                                   NA
#> 5                                                   NA
#> 6                                                   NA

# an alternative way to process the same data using `readr::type_convert()`:
readr::read_csv(file = raw_data,
                col_types = list(.default = "c")) %>%
  readr::type_convert(col_types = pal::cols_regex("^(Gemeindenamen|Partei)$" = "c",
                                                  "(?i)anteil" = "d",
                                                  .default = "i",
                                                  .col_names = colnames(.)))
#> Warning: [0, 1]: expected no trailing characters, but got '<html><head>'
#> Warning: [1, 1]: expected no trailing characters, but got '<title>404 Not Found</title>'
#> Warning: [2, 1]: expected no trailing characters, but got '</head><body>'
#> Warning: [3, 1]: expected no trailing characters, but got '<h1>Not Found</h1>'
#> Warning: [4, 1]: expected no trailing characters, but got '<p>The requested URL was not found on this server.</p>'
#> Warning: [5, 1]: expected no trailing characters, but got '</body></html>'
#> # A tibble: 6 × 1
#>   `<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML 2.0//EN">`
#>                                                  <int>
#> 1                                                   NA
#> 2                                                   NA
#> 3                                                   NA
#> 4                                                   NA
#> 5                                                   NA
#> 6                                                   NA