Tidy Data

Pivoting

long to wide form

table4a_long <- table4a %>%
    
    pivot_longer(cols = c('1999', '2000'),
                 names_to = "year",
                 values_to = "cases")

##wide to long form

table4a_long %>%
    
    pivot_wider(names_from = year,
                values_from = cases)
## # A tibble: 3 × 3
##   country     `1999` `2000`
##   <chr>        <dbl>  <dbl>
## 1 Afghanistan    745   2666
## 2 Brazil       37737  80488
## 3 China       212258 213766

Seperating And Uniting

#separate a column

table3_sep <- table3 %>%
    
    separate(col = rate, into = c("cases", "population"))

unite two columns

table3_sep %>%
    
    unite(col = "rate", c(cases, population), sep = "/")
## # A tibble: 6 × 3
##   country      year rate             
##   <chr>       <dbl> <chr>            
## 1 Afghanistan  1999 745/19987071     
## 2 Afghanistan  2000 2666/20595360    
## 3 Brazil       1999 37737/172006362  
## 4 Brazil       2000 80488/174504898  
## 5 China        1999 212258/1272915272
## 6 China        2000 213766/1280428583

Missing Values

stocks <- tibble(
  year   = c(2015, 2015, 2015, 2015, 2016, 2016, 2016),
  qtr    = c(   1,    2,    3,    4,    2,    3,    4),
  return = c(1.88, 0.59, 0.35,   NA, 0.92, 0.17, 2.66)
)
stocks %>%
    
    pivot_wider(names_from = year, values_from = return)
## # A tibble: 4 × 3
##     qtr `2015` `2016`
##   <dbl>  <dbl>  <dbl>
## 1     1   1.88  NA   
## 2     2   0.59   0.92
## 3     3   0.35   0.17
## 4     4  NA      2.66
bikes <- tibble(
  bike_model = c("A", "A", "B", "B", "C"),
  material   = c("steel", "aluminium", "steel", "aluminium", "steel"),
  price      = c(100, 200, 300, 400, 500)
)
bikes %>%
    
    pivot_wider(names_from = bike_model, values_from = price)
## # A tibble: 2 × 4
##   material      A     B     C
##   <chr>     <dbl> <dbl> <dbl>
## 1 steel       100   300   500
## 2 aluminium   200   400    NA
bikes %>%
    
    complete(bike_model, material)
## # A tibble: 6 × 3
##   bike_model material  price
##   <chr>      <chr>     <dbl>
## 1 A          aluminium   200
## 2 A          steel       100
## 3 B          aluminium   400
## 4 B          steel       300
## 5 C          aluminium    NA
## 6 C          steel       500

Non-tidy data

treatment <- tribble(
  ~ person,           ~ treatment, ~response,
  "Derrick Whitmore", 1,           7,
  NA,                 2,           10,
  NA,                 3,           9,
  "Katherine Burke",  1,           4
)

treatment %>%
    
    fill(person, .direction = "up")
## # A tibble: 4 × 3
##   person           treatment response
##   <chr>                <dbl>    <dbl>
## 1 Derrick Whitmore         1        7
## 2 Katherine Burke          2       10
## 3 Katherine Burke          3        9
## 4 Katherine Burke          1        4
who1 <- who %>% 
  pivot_longer(
    cols = new_sp_m014:newrel_f65, 
    names_to = "key", 
    values_to = "cases", 
    values_drop_na = TRUE
  )
who1
## # A tibble: 76,046 × 6
##    country     iso2  iso3   year key          cases
##    <chr>       <chr> <chr> <dbl> <chr>        <dbl>
##  1 Afghanistan AF    AFG    1997 new_sp_m014      0
##  2 Afghanistan AF    AFG    1997 new_sp_m1524    10
##  3 Afghanistan AF    AFG    1997 new_sp_m2534     6
##  4 Afghanistan AF    AFG    1997 new_sp_m3544     3
##  5 Afghanistan AF    AFG    1997 new_sp_m4554     5
##  6 Afghanistan AF    AFG    1997 new_sp_m5564     2
##  7 Afghanistan AF    AFG    1997 new_sp_m65       0
##  8 Afghanistan AF    AFG    1997 new_sp_f014      5
##  9 Afghanistan AF    AFG    1997 new_sp_f1524    38
## 10 Afghanistan AF    AFG    1997 new_sp_f2534    36
## # ℹ 76,036 more rows