Code Along 7

R for Data Science Chapter 12

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

Separating 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", "aluminum", "steel", "aluminim", "steel"),
  price = c(100, 200, 300, 400, 500)
)

bikes %>% 
  pivot_wider(names_from = bike_model, values_from = price)

## # A tibble: 3 × 4
##   material     A     B     C
##   <chr>    <dbl> <dbl> <dbl>
## 1 steel      100   300   500
## 2 aluminum   200    NA    NA
## 3 aluminim    NA   400    NA

bikes %>% 
  complete(bike_model, material)

## # A tibble: 9 × 3
##   bike_model material price
##   <chr>      <chr>    <dbl>
## 1 A          aluminim    NA
## 2 A          aluminum   200
## 3 A          steel      100
## 4 B          aluminim   400
## 5 B          aluminum    NA
## 6 B          steel      300
## 7 C          aluminim    NA
## 8 C          aluminum    NA
## 9 C          steel      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