Hadley Wickham hadley

LLM for code generation

Currently three main styles:

Autocomplete
- e.g. github copilot, windsurf
- Inline "ghost text" as you type
- Sometimes amazingly good; often pretty useless
- Need to train yourself to ignore spurious suggestions

Convert <ingredients> to JSON using the following format:

If an ingredient has both weight and volume, extract only the weight:

¾ cup (150g) dark brown sugar
[{"name": "dark brown sugar", "quantity": 150, "unit": "g"}]

If an ingredient only lists a volume, extract that.

library(tidyverse)

simple_data <- tibble(
  group = factor(rep(c("A", "B"), each = 15)),
  subject = 1:30,
  score = c(rnorm(15, 40, 20), rnorm(15, 60, 10))
)

simple_data_se &lt;- simple_data %&gt;%

	library(tidyverse)

	# https://twitter.com/buddyherms/status/1576966150680121344 --------------

	# PROs: at, by, and regexp examples
	# CONs: quite simple

	vt_census <- tidycensus::get_decennial(
	geography = "block",
	state = "VT",

	f1 <- function(n) {
	x <- numeric()
	for (i in 1:n) {
	x <- c(x, i)
	}
	x
	}

	f1.5 <- function(n) {
	x <- numeric()

	data(diamonds, package = "ggplot2")

	# Most straightforward
	diamonds$ppc <- diamonds$price / diamonds$carat

	# Avoid repeating diamonds
	diamonds$ppc <- with(diamonds, price / carat)

	# The inspiration for dplyr's mutate
	diamonds <- transform(diamonds, ppc = price / carat)

	library(rtweet)
	library(tidyverse)

	auth_setup_default()
	json <- search_tweets("#rstats", n = 5000, include_rts = FALSE, parse = FALSE)[1:5]

	tweets <- tibble(json = json) %>%
	unnest_wider(json) %>%
	select(statuses) %>%
	unnest_longer(statuses) %>%

	library(ggplot2)

	x <- c("بقرة", "دجاج", "حصان")
	df <- data.frame(x = x, y = 1:3)

	labels_rtl <- function(x) paste0("\u202B", x)

	ggplot(df, aes(x, y)) +
	geom_point() +
	scale_x_discrete(labels = labels_rtl) +

	# need + validate -----------------------------------------------------------
	validate(
	need(
	mzfinder::check_mzr_object(ms_object$mzr_connection),
	"Wasn't able to connect to MS file"
	)
	)
	validate(
	need(!is.null(input$ppm_input), "ppm_input must not be null"),
	need(input$ppm_input > 0L, "ppm_input must be > 0")

	# Code for quick exploration of
	# https://github.com/rfordatascience/tidytuesday/tree/master/data/2020/2020-05-26
	# Video at https://youtu.be/kHFmtKCI_F4

	library(tidyverse)

	cocktails <- readr::read_csv("boston_cocktails.csv")


	# Are name and row_id equivalent? -----------------------------------------