##Tidy data

##Pivoting

Long to wide form

table4a
## # A tibble: 3 × 3
##   country     `1999` `2000`
##   <chr>        <dbl>  <dbl>
## 1 Afghanistan    745   2666
## 2 Brazil       37737  80488
## 3 China       212258 213766
table4a_long <- table4a %>%
    
    pivot_longer(cols = c("1999", "2000"), names_to = "year", values_to = "cases")

table4a_long
## # 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

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

Seperating a column

table3
## # 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
table3_separate <- table3 %>%
    
    separate(rate, into = c("cases", "population"))

table3_separate
## # 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

table3_separate %>%
    
    unite(col = "rate", 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
## # A tibble: 7 × 3
##    year   qtr return
##   <dbl> <dbl>  <dbl>
## 1  2015     1   1.88
## 2  2015     2   0.59
## 3  2015     3   0.35
## 4  2015     4  NA   
## 5  2016     2   0.92
## 6  2016     3   0.17
## 7  2016     4   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",   "aluminum",    "steel"), 
  price = c(100, 200,  300, 400, 500)
)

bikes
## # A tibble: 5 × 3
##   bike_model material price
##   <chr>      <chr>    <dbl>
## 1 A          steel      100
## 2 A          aluminum   200
## 3 B          steel      300
## 4 B          aluminum   400
## 5 C          steel      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 aluminum   200   400    NA
bikes %>%
    
    complete(bike_model, material)
## # A tibble: 6 × 3
##   bike_model material price
##   <chr>      <chr>    <dbl>
## 1 A          aluminum   200
## 2 A          steel      100
## 3 B          aluminum   400
## 4 B          steel      300
## 5 C          aluminum    NA
## 6 C          steel      500
treatment <- tribble(
  ~ person,           ~ treatment, ~response,
  "Derrick Whitmore", 1,           7,
  NA,                 2,           10,
  NA,                 3,           9,
  "Katherine Burke",  1,           4
)

treatment
## # A tibble: 4 × 3
##   person           treatment response
##   <chr>                <dbl>    <dbl>
## 1 Derrick Whitmore         1        7
## 2 <NA>                     2       10
## 3 <NA>                     3        9
## 4 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

##Importing Tidy Data

library(tidyverse)
library(here)
data <- readr::read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2022/2022-01-25/details.csv")

    write_csv(data, here("00_data/boardgame_details.csv"))

Non-Tidy Data