Week 8: Code Along 7

R For Data Science: Chapter 12

Tidy Data

Pivoting

Long to wide form

table4a %>% 
  pivot_longer(c(`1999`, `2000`), names_to = "year", values_to = "cases")

## # A tibble: 6 × 3
##   country     year   cases
##   <chr>       <chr>  <dbl>
## 1 Afghanistan 1999     745
## 2 Afghanistan 2000    2666
## 3 Brazil      1999   37737
## 4 Brazil      2000   80488
## 5 China       1999  212258
## 6 China       2000  213766

Wide to long form

table2 %>%
    pivot_wider(names_from = type, values_from = count)

## # A tibble: 6 × 4
##   country      year  cases population
##   <chr>       <dbl>  <dbl>      <dbl>
## 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

Separating and uniting

Seprate a Column

table3 %>% 
  separate(rate, into = c("cases", "population"), sep = "/")

## # A tibble: 6 × 4
##   country      year cases  population
##   <chr>       <dbl> <chr>  <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

Unite two Columns

table5 %>% 
  unite(new, century, year, sep = "")

## # A tibble: 6 × 3
##   country     new   rate             
##   <chr>       <chr> <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","steel", "aluminium",  "aluminium", "steel"), 
  return = c(100, 200, 300, 400, 500)
)

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

Non-tidy data