brickster

library(brickster)

# only requires `DATABRICKS_HOST` if using OAuth U2M
# first request will open browser window to login
Sys.setenv(DATABRICKS_HOST = "https://<workspace-prefix>.cloud.databricks.com")

# open RStudio/Positron connection pane to view Databricks resources
open_workspace()

# list all SQL warehouses
warehouses <- db_sql_warehouse_list()

library(brickster)
library(DBI)

# Connect to Databricks using DBI (assumes you followed quickstart to authenticate)
con <- dbConnect(
  DatabricksSQL(),
  warehouse_id = "<warehouse-id>"
)

# Standard {DBI} operations
tables <- dbListTables(con)
dbGetQuery(con, "SELECT * FROM samples.nyctaxi.trips LIMIT 5")

# Use with {dbplyr} for {dplyr} syntax
library(dplyr)
library(dbplyr)

nyc_taxi <- tbl(con, I("samples.nyctaxi.trips"))

result <- nyc_taxi |>
  filter(year(tpep_pickup_datetime) == 2016) |>
  group_by(pickup_zip) |>
  summarise(
    trip_count = n(),
    avg_fare = mean(fare_amount, na.rm = TRUE),
    avg_distance = mean(trip_distance, na.rm = TRUE)
  ) |>
  collect()

library(readr)
library(brickster)

# upload `data.csv` to a volume
local_file <- tempfile(fileext = ".csv")
write_csv(x = iris, file = local_file)
db_volume_write(
  path = "/Volumes/<catalog>/<schema>/<volume>/data.csv",
  file = local_file
)

# read `data.csv` from a volume and write to a file
downloaded_file <- tempfile(fileext = ".csv")
file <- db_volume_read(
  path = "/Volumes/<catalog>/<schema>/<volume>/data.csv",
  destination = downloaded_file
)
volume_csv <- read_csv(downloaded_file)

library(brickster)

# commands after this will run on the interactive cluster
# read the vignette for more details
db_repl(cluster_id = "<interactive_cluster_id>")