relational_algebra_ex.R

library(tidyverse)

beans <- c("Caturra", "Grusti", "Double roasted")
coffees <- c("Garuda", "Blend 101", "Blend 201", "Exxxtra special blend")
location <- c("Rwanda", "Columbia", "Peru")
people <- c("Dan Wallach", "Chris Jermaine", "Scott Rikner", "Luay")

has_bean <- tibble(
  coffee = sample(coffees, 10, replace = TRUE),
  bean_name = sample(beans, 10, replace = TRUE)
) %>% 
  distinct()

drinks <- tibble(
  name = sample(people, 15, replace = TRUE),
  coffee = sample(coffees, 15, replace = TRUE)
) %>% 
  distinct()

bean <- tibble(
  bean_name = sample(beans, 20, replace = TRUE),
  from_location = sample(location, 20, replace = TRUE)
) %>% 
  distinct()

has_bean
drinks
bean

# code: relational algebraic equivalencies
# these are all from the `dplyr` library

# left_join: natural_join
# filter: (select/sigma operator)
# select: (project/pi operator)
# %>%: forward pipe operator, use to chain together operations

# you may also interested in the anti_join operator, as well as group_by,
# mutate, and summarize

# an example: all coffees with beans from Peru

bean %>% 
  left_join(has_bean) %>% 
  filter(from_location == "Peru")