TIL20230124

read_csv

They are typically much faster (~10x) than their base equivalents.
- https://r4ds.had.co.nz/data-import.html#getting-started

data source https://archive.ics.uci.edu/ml/machine-learning-databases/credit-screening/crx.data

b,30.83,0,u,g,w,v,1.25,t,t,01,f,g,00202,0,+
a,58.67,4.46,u,g,q,h,3.04,t,t,06,f,g,00043,560,+
a,24.50,0.5,u,g,q,h,1.5,t,f,0,f,g,00280,824,+
b,27.83,1.54,u,g,w,v,3.75,t,t,05,t,g,00100,3,+
b,20.17,5.625,u,g,w,v,1.71,t,f,0,f,s,00120,0,+

url <- "https://archive.ics.uci.edu/ml/machine-learning-databases/credit-screening/crx.data"
data_raw <- read_csv(file = url,
                     col_names = paste0("A", seq(1:16)),
                     na = "?")
head(data_raw)

## # A tibble: 6 x 16
##   A1       A2    A3 A4    A5    A6    A7       A8 A9    A10   A11   A12   A13  
##   <chr> <dbl> <dbl> <chr> <chr> <chr> <chr> <dbl> <lgl> <lgl> <chr> <lgl> <chr>
## 1 b      30.8  0    u     g     w     v      1.25 TRUE  TRUE  01    FALSE g    
## 2 a      58.7  4.46 u     g     q     h      3.04 TRUE  TRUE  06    FALSE g    
## 3 a      24.5  0.5  u     g     q     h      1.5  TRUE  FALSE 0     FALSE g    
## 4 b      27.8  1.54 u     g     w     v      3.75 TRUE  TRUE  05    TRUE  g    
## 5 b      20.2  5.62 u     g     w     v      1.71 TRUE  FALSE 0     FALSE s    
## 6 b      32.1  4    u     g     m     v      2.5  TRUE  FALSE 0     TRUE  g    
## # ... with 3 more variables: A14 <chr>, A15 <dbl>, A16 <chr>

data <- data_raw %>% 
  filter(if_any(everything(), ~is.na(.)))
data %>% head

## # A tibble: 6 x 16
##   A1       A2    A3 A4    A5    A6    A7        A8 A9    A10   A11   A12   A13  
##   <chr> <dbl> <dbl> <chr> <chr> <chr> <chr>  <dbl> <lgl> <lgl> <chr> <lgl> <chr>
## 1 b      34.8 4     u     g     d     bb    12.5   TRUE  FALSE 0     TRUE  g    
## 2 a      NA   3.5   u     g     d     v      3     TRUE  FALSE 0     TRUE  g    
## 3 b      NA   0.375 u     g     d     v      0.875 TRUE  FALSE 0     TRUE  s    
## 4 b      NA   5     y     p     aa    v      8.5   TRUE  FALSE 0     FALSE g    
## 5 b      NA   0.5   u     g     c     bb     0.835 TRUE  FALSE 0     TRUE  s    
## 6 b      24.8 2.75  u     g     c     v      2.25  TRUE  TRUE  06    FALSE g    
## # ... with 3 more variables: A14 <chr>, A15 <dbl>, A16 <chr>

read_csv("
a,b,c
1,2,3
4,5,6
")

## # A tibble: 2 x 3
##       a     b     c
##   <dbl> <dbl> <dbl>
## 1     1     2     3
## 2     4     5     6

read_delim("
a;b;c
1;2;3
4;5;6
", delim = ";")

## # A tibble: 2 x 3
##       a     b     c
##   <dbl> <dbl> <dbl>
## 1     1     2     3
## 2     4     5     6

read_csv("1,2,3\n4,5,6", col_names = c("x", "y", "z"))

## # A tibble: 2 x 3
##       x     y     z
##   <dbl> <dbl> <dbl>
## 1     1     2     3
## 2     4     5     6

read_csv("a,b\n 1,2,3\n 4,5,6")

## # A tibble: 2 x 2
##       a     b
##   <dbl> <dbl>
## 1     1    23
## 2     4    56

read_csv("a,b,c\n 1,2\n 1,2,3,4")

## # A tibble: 2 x 3
##       a     b     c
##   <dbl> <dbl> <dbl>
## 1     1     2    NA
## 2     1     2    34

read_csv("a,b\n \"1")

## # A tibble: 1 x 2
##       a b    
##   <dbl> <lgl>
## 1     1 NA

read_csv("a,b\n 1,2\n a,b")

## # A tibble: 2 x 2
##   a     b    
##   <chr> <chr>
## 1 1     2    
## 2 a     b

read_csv("a;b\n 1;3")

## # A tibble: 1 x 1
##   `a;b`
##   <chr>
## 1 1;3