8  Data import

Prerequisites

library(tidyverse)
#> ── Attaching core tidyverse packages ───────────────────── tidyverse 2.0.0 ──
#> ✔ dplyr     1.1.2     ✔ readr     2.1.4
#> ✔ forcats   1.0.0     ✔ stringr   1.5.0
#> ✔ ggplot2   3.4.2     ✔ tibble    3.2.1
#> ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
#> ✔ purrr     1.0.1     
#> ── Conflicts ─────────────────────────────────────── tidyverse_conflicts() ──
#> ✖ dplyr::filter() masks stats::filter()
#> ✖ dplyr::lag()    masks stats::lag()
#> ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

8.2.4 Exercises

  1. For reading a file delimited with |, use read_delim() with argument delim = "|".

  2. All other arguments are common among the two functions.

  3. col_positions is an important argument since it defines the beginning and end of columns.

  4. We need to specify the quote argument.

    read_csv("x,y\n1,'a,b'", quote = "\'")
#> Rows: 1 Columns: 2
#> ── Column specification ─────────────────────────────────────────────────────
#> Delimiter: ","
#> chr (1): y
#> dbl (1): x
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> # A tibble: 1 × 2
#>       x y    
#>   <dbl> <chr>
#> 1     1 a,b

  5. Problems with each read_csv() statement is shown below:\

    • There are only two column headers but three values in each row, so the last two get merged:

      read_csv("a,b\n1,2,3\n4,5,6")
#> Warning: One or more parsing issues, call `problems()` on your data frame for
#> details, e.g.:
#>   dat <- vroom(...)
#>   problems(dat)
#> Rows: 2 Columns: 2
#> ── Column specification ─────────────────────────────────────────────────────
#> Delimiter: ","
#> dbl (1): a
#> num (1): b
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> # A tibble: 2 × 2
#>       a     b
#>   <dbl> <dbl>
#> 1     1    23
#> 2     4    56

    • There are only three column headers, first row is missing a value in the last column so gets an NA there, the second row has four values so the last two get merged:

      read_csv("a,b,c\n1,2\n1,2,3,4")
#> Warning: One or more parsing issues, call `problems()` on your data frame for
#> details, e.g.:
#>   dat <- vroom(...)
#>   problems(dat)
#> Rows: 2 Columns: 3
#> ── Column specification ─────────────────────────────────────────────────────
#> Delimiter: ","
#> dbl (2): a, b
#> num (1): c
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> # A tibble: 2 × 3
#>       a     b     c
#>   <dbl> <dbl> <dbl>
#> 1     1     2    NA
#> 2     1     2    34

    • No rows are read in:

      read_csv("a,b\n\"1")
#> Rows: 0 Columns: 2
#> ── Column specification ─────────────────────────────────────────────────────
#> Delimiter: ","
#> chr (2): a, b
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> # A tibble: 0 × 2
#> # ℹ 2 variables: a <chr>, b <chr>

    • Each column has a numerical and a character value, so the column type is coerced to character:

      read_csv("a,b\n1,2\na,b")
#> Rows: 2 Columns: 2
#> ── Column specification ─────────────────────────────────────────────────────
#> Delimiter: ","
#> chr (2): a, b
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> # A tibble: 2 × 2
#>   a     b    
#>   <chr> <chr>
#> 1 1     2    
#> 2 a     b

    • The delimiter is ; but it’s not specified, therefore this is read in as a single-column data frame with a single observation:

      read_csv("a;b\n1;3")
#> Rows: 1 Columns: 1
#> ── Column specification ─────────────────────────────────────────────────────
#> Delimiter: ","
#> chr (1): a;b
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> # A tibble: 1 × 1
#>   `a;b`
#>   <chr>
#> 1 1;3

  6. The non-syntactic names can be read in as follows.

    annoying <- tibble(
  `1` = 1:10,
  `2` = `1` * 2 + rnorm(length(`1`))
)
    1. Extracting the variable called 1:
    annoying |>
  select(`1`)
#> # A tibble: 10 × 1
#>     `1`
#>   <int>
#> 1     1
#> 2     2
#> 3     3
#> 4     4
#> 5     5
#> 6     6
#> # ℹ 4 more rows
    1. Plotting a scatterplot of 1 vs. 2:
    ggplot(annoying, aes(x = `2`, y = `1`)) +
  geom_point()

    1. Creating a new column called 3, which is 2 divided by 1:
    annoying |>
  mutate(`3` = `2` / `1`)
#> # A tibble: 10 × 3
#>     `1`    `2`   `3`
#>   <int>  <dbl> <dbl>
#> 1     1  0.600 0.600
#> 2     2  4.26  2.13 
#> 3     3  3.56  1.19 
#> 4     4  7.99  2.00 
#> 5     5 10.6   2.12 
#> 6     6 13.1   2.19 
#> # ℹ 4 more rows
    1. Renaming the columns to one, two, and three:
    annoying |>
  mutate(`3` = `2` / `1`) |>
  rename(
    "one" = `1`,
    "two" = `2`,
    "three" = `3`
  )
#> # A tibble: 10 × 3
#>     one    two three
#>   <int>  <dbl> <dbl>
#> 1     1  0.600 0.600
#> 2     2  4.26  2.13 
#> 3     3  3.56  1.19 
#> 4     4  7.99  2.00 
#> 5     5 10.6   2.12 
#> 6     6 13.1   2.19 
#> # ℹ 4 more rows