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
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)
)
q1 <- inner_join(customers , orders)
## Joining with `by = join_by(customer_id)`
print(q1)
## # 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
q2 <- left_join(customers, orders, by = "customer_id")
``` r
print(q2)
## # 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
q3 <- right_join(customers, orders, by = "customer_id")
print(q3)
## # 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
How many rows are in the result?
q4 <- full_join(customers, orders, by = "customer_id")
print(q4)
## # A tibble: 8 × 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
## 7 6 <NA> <NA> 105 Camera 600
## 8 7 <NA> <NA> 106 Printer 150
q5 <- semi_join(customers, orders, by = "customer_id")
print(q5)
## # 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
q6 <- anti_join(customers, orders, by = "customer_id")
print(q6)
## # A tibble: 2 × 3
## customer_id name city
## <dbl> <chr> <chr>
## 1 4 David Houston
## 2 5 Eve Phoenix
all_customers <- full_join(customers, orders, by = "customer_id")
print(all_customers)
## # A tibble: 8 × 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
## 7 6 <NA> <NA> 105 Camera 600
## 8 7 <NA> <NA> 106 Printer 150
customers_with_orders <- right_join(customers, orders, by = "customer_id")
print(customers_with_orders)
## # 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
library(tidyr)
customer_orders <- full_join(customers, orders, by = "customer_id")
summary_data <- customer_orders %>%
group_by(customer_id, name, city) %>%
summarize(
total_orders = n_distinct(order_id, na.rm = TRUE),
total_amount_spent = sum(amount, na.rm = TRUE)
) %>%
replace_na(list(total_orders = 0, total_amount_spent = 0))
## `summarise()` has grouped output by 'customer_id', 'name'. You can override
## using the `.groups` argument.
print(summary_data)
## # A tibble: 7 × 5
## # Groups: customer_id, name [7]
## 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 0 0
## 5 5 Eve Phoenix 0 0
## 6 6 <NA> <NA> 1 600
## 7 7 <NA> <NA> 1 150