In hrbrmstr/sergeant-caffeinated: RJDBC Interface for Apache Drill

hrbrpkghelpr::global_opts()

hrbrpkghelpr::stinking_badges()

hrbrpkghelpr::yank_title_and_description()

What's Inside The Tin

The following functions are implemented:

hrbrpkghelpr::describe_ingredients()

Installation

remotes::install_github("hrbrmstr/sergeant-caffeinated")

Usage

library(sergeant.caffeinated)

# current version
packageVersion("sergeant.caffeinated")

library(tidyverse)

# use localhost if running standalone on same system otherwise the host or IP of your Drill server
test_host <- Sys.getenv("DRILL_TEST_HOST", "localhost")

be_quiet()

con <- dbConnect(drv = DrillJDBC(), sprintf("jdbc:drill:zk=%s", test_host))

db <- tbl(con, "cp.`employee.json`")

# without `collect()`:
db %>% 
  count(
    gender, 
    marital_status
  )

db %>% 
  count(
    gender, 
    marital_status
  ) %>% 
  collect()

db %>% 
  group_by(position_title) %>% 
  count(gender) -> tmp2

group_by(db, position_title) %>% 
  count(gender) %>% 
  ungroup() %>% 
  mutate(
    full_desc = ifelse(gender=="F", "Female", "Male")
  ) %>% 
  collect() %>% 
  select(
    Title = position_title, 
    Gender = full_desc, 
    Count = n
  )

arrange(db, desc(employee_id)) %>% print(n=20)

db %>% 
  mutate(
    position_title = tolower(position_title),
    salary = as.numeric(salary),
    gender = ifelse(gender == "F", "Female", "Male"),
    marital_status = ifelse(marital_status == "S", "Single", "Married")
  ) %>%
  group_by(supervisor_id) %>% 
  summarise(
    underlings_count = n()
  ) %>% 
  collect()