library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
# Dataset 1: Customers
customers <- tibble(
customer_id = c(1, 2, 3, 4, 5),
name = c("Alice", "Bob", "Charlie", "David", "Eve"),
city = c("New York", "Los Angeles", "Chicago", "Houston", "Phoenix")
)
# Dataset 2: Orders
orders <- tibble(
order_id = c(101, 102, 103, 104, 105, 106),
customer_id = c(1, 2, 3, 2, 6, 7),
product = c("Laptop", "Phone", "Tablet", "Desktop", "Camera", "Printer"),
amount = c(1200, 800, 300, 1500, 600, 150)
)
inner <- inner_join(customers , orders , by = 'customer_id')
There are 4 rows
because they do not have a match in the other table.
head(inner)
## # A tibble: 4 × 6
## customer_id name city order_id product amount
## <dbl> <chr> <chr> <dbl> <chr> <dbl>
## 1 1 Alice New York 101 Laptop 1200
## 2 2 Bob Los Angeles 102 Phone 800
## 3 2 Bob Los Angeles 104 Desktop 1500
## 4 3 Charlie Chicago 103 Tablet 300
left <- left_join(customers , orders , by = 'customer_id')
there are 6 rows
This is different from the inner join result because the left join includes David and Eve who are in the customers table but not in the orders table.
head(left)
## # A tibble: 6 × 6
## customer_id name city order_id product amount
## <dbl> <chr> <chr> <dbl> <chr> <dbl>
## 1 1 Alice New York 101 Laptop 1200
## 2 2 Bob Los Angeles 102 Phone 800
## 3 2 Bob Los Angeles 104 Desktop 1500
## 4 3 Charlie Chicago 103 Tablet 300
## 5 4 David Houston NA <NA> NA
## 6 5 Eve Phoenix NA <NA> NA
right <- right_join(customers , orders , by = 'customer_id')
there are 6 rows.
Customer id 6 and 7 have NULL for customer name and city. The reason is because their customer ID is not included in the data on the customer table so that information is missing.
head(right)
## # A tibble: 6 × 6
## customer_id name city order_id product amount
## <dbl> <chr> <chr> <dbl> <chr> <dbl>
## 1 1 Alice New York 101 Laptop 1200
## 2 2 Bob Los Angeles 102 Phone 800
## 3 2 Bob Los Angeles 104 Desktop 1500
## 4 3 Charlie Chicago 103 Tablet 300
## 5 6 <NA> <NA> 105 Camera 600
## 6 7 <NA> <NA> 106 Printer 150
full <- full_join(customers , orders , by = 'customer_id')
There are 8 rows
This result is different because it includes all the data from both tables regardless if there is a match in the other table.
head(full)
## # A tibble: 6 × 6
## customer_id name city order_id product amount
## <dbl> <chr> <chr> <dbl> <chr> <dbl>
## 1 1 Alice New York 101 Laptop 1200
## 2 2 Bob Los Angeles 102 Phone 800
## 3 2 Bob Los Angeles 104 Desktop 1500
## 4 3 Charlie Chicago 103 Tablet 300
## 5 4 David Houston NA <NA> NA
## 6 5 Eve Phoenix NA <NA> NA
semi <- semi_join(customers , orders , by = 'customer_id')
there are 3 rows.
A semi join returns rows from the left table that have matches in the right table, while an inner join includes matching rows and columns from both tables.
head(semi)
## # A tibble: 3 × 3
## customer_id name city
## <dbl> <chr> <chr>
## 1 1 Alice New York
## 2 2 Bob Los Angeles
## 3 3 Charlie Chicago
anti <- anti_join(customers , orders , by = 'customer_id')
David and Eve are in the result.
Those customers have null information in the orders table.
head(anti)
## # A tibble: 2 × 3
## customer_id name city
## <dbl> <chr> <chr>
## 1 4 David Houston
## 2 5 Eve Phoenix
You would use a left join because it shows all customers
You would use inner join because it combines from both based on matches of who has placed orders.
left <- left_join(customers , orders , by = 'customer_id')
inner <- inner_join(customers , orders , by = 'customer_id')
head(left)
## # A tibble: 6 × 6
## customer_id name city order_id product amount
## <dbl> <chr> <chr> <dbl> <chr> <dbl>
## 1 1 Alice New York 101 Laptop 1200
## 2 2 Bob Los Angeles 102 Phone 800
## 3 2 Bob Los Angeles 104 Desktop 1500
## 4 3 Charlie Chicago 103 Tablet 300
## 5 4 David Houston NA <NA> NA
## 6 5 Eve Phoenix NA <NA> NA
head(inner)
## # A tibble: 4 × 6
## customer_id name city order_id product amount
## <dbl> <chr> <chr> <dbl> <chr> <dbl>
## 1 1 Alice New York 101 Laptop 1200
## 2 2 Bob Los Angeles 102 Phone 800
## 3 2 Bob Los Angeles 104 Desktop 1500
## 4 3 Charlie Chicago 103 Tablet 300
customer_summary_full <- customers %>%
full_join(orders, by = "customer_id") %>%
group_by(customer_id, name, city) %>%
summarize(
total_orders = n(),
total_amount_spent = sum(amount, na.rm = TRUE),
.groups = "drop"
)
head(customer_summary_full)
## # A tibble: 6 × 5
## customer_id name city total_orders total_amount_spent
## <dbl> <chr> <chr> <int> <dbl>
## 1 1 Alice New York 1 1200
## 2 2 Bob Los Angeles 2 2300
## 3 3 Charlie Chicago 1 300
## 4 4 David Houston 1 0
## 5 5 Eve Phoenix 1 0
## 6 6 <NA> <NA> 1 600