Week 9: Code Along 8

R For Data Science: Chapter 13

Introduction

nycflights13

Keys

Mutating joins

Inner Join

x <- tribble(
  ~key, ~val_x,
     1, "x1",
     2, "x2",
     3, "x3"
)
y <- tribble(
  ~key, ~val_y,
     1, "y1",
     2, "y2",
     4, "y3"
)

inner_join(x,y)

## Joining with `by = join_by(key)`

## # A tibble: 2 × 3
##     key val_x val_y
##   <dbl> <chr> <chr>
## 1     1 x1    y1   
## 2     2 x2    y2

Outer Join

left_join(x,y)

## Joining with `by = join_by(key)`

## # A tibble: 3 × 3
##     key val_x val_y
##   <dbl> <chr> <chr>
## 1     1 x1    y1   
## 2     2 x2    y2   
## 3     3 x3    <NA>

right_join(x,y)

## Joining with `by = join_by(key)`

## # A tibble: 3 × 3
##     key val_x val_y
##   <dbl> <chr> <chr>
## 1     1 x1    y1   
## 2     2 x2    y2   
## 3     4 <NA>  y3

full_join(x,y)

## Joining with `by = join_by(key)`

## # A tibble: 4 × 3
##     key val_x val_y
##   <dbl> <chr> <chr>
## 1     1 x1    y1   
## 2     2 x2    y2   
## 3     3 x3    <NA> 
## 4     4 <NA>  y3

Defining the key coloums

airports %>%
  semi_join(flights, c("faa" = "dest")) %>%
  ggplot(aes(lon, lat)) +
    borders("state") +
    geom_point() +
    coord_quickmap()

Filtering joins

semi_join(x,y)

## Joining with `by = join_by(key)`

## # A tibble: 2 × 2
##     key val_x
##   <dbl> <chr>
## 1     1 x1   
## 2     2 x2

semi_join(y,x)

## Joining with `by = join_by(key)`

## # A tibble: 2 × 2
##     key val_y
##   <dbl> <chr>
## 1     1 y1   
## 2     2 y2

anti_join(x,y)

## Joining with `by = join_by(key)`

## # A tibble: 1 × 2
##     key val_x
##   <dbl> <chr>
## 1     3 x3

anti_join(y,x)

## Joining with `by = join_by(key)`

## # A tibble: 1 × 2
##     key val_y
##   <dbl> <chr>
## 1     4 y3

Join problems

airports %>% count(alt, lon) %>% filter(n > 1)

## # A tibble: 0 × 3
## # ℹ 3 variables: alt <dbl>, lon <dbl>, n <int>

#> # A tibble: 0 × 3
#> # ℹ 3 variables: alt <dbl>, lon <dbl>, n <int>

Set operations

df1 <- tribble(
  ~x, ~y,
   1,  1,
   2,  1
)
df2 <- tribble(
  ~x, ~y,
   1,  1,
   1,  2
)

intersect(df1, df2)

## # A tibble: 1 × 2
##       x     y
##   <dbl> <dbl>
## 1     1     1

#> # A tibble: 1 × 2
#>       x     y
#>   <dbl> <dbl>
#> 1     1     1

# Note that we get 3 rows, not 4
union(df1, df2)

## # A tibble: 3 × 2
##       x     y
##   <dbl> <dbl>
## 1     1     1
## 2     2     1
## 3     1     2

#> # A tibble: 3 × 2
#>       x     y
#>   <dbl> <dbl>
#> 1     1     1
#> 2     2     1
#> 3     1     2

setdiff(df1, df2)

## # A tibble: 1 × 2
##       x     y
##   <dbl> <dbl>
## 1     2     1

#> # A tibble: 1 × 2
#>       x     y
#>   <dbl> <dbl>
#> 1     2     1

setdiff(df2, df1)

## # A tibble: 1 × 2
##       x     y
##   <dbl> <dbl>
## 1     1     2

#> # A tibble: 1 × 2
#>       x     y
#>   <dbl> <dbl>
#> 1     1     2