dgrtwo’s gists

dgrtwo / gist:39af4512dff5b7357b534a04a971405d

Created March 14, 2018 22:21

Early attempt at creating materialized SQL views from dplyr

	separate_sql <- function(expression) {
	s <- paste(deparse(expression), collapse = "\n")
	s <- stringr::str_replace(s, "%>%", "%>%\n ")
	s <- stringr::str_split(s, "\n")[[1]]

	val <- eval(expression)

	list(expression = expression,
	dplyr_code = s,
	sql = as.character(dbplyr:::remote_query(val)),

dgrtwo / file663a44ec31fa.R

Created October 4, 2017 01:16

	library(purrr)

	transition_mc <- function(steps, start, mat) {
	i <- seq_len(nrow(mat))

	transition <- ~ sample(i, 1, prob = (i == .) %*% mat)

	accumulate(seq_len(steps), transition, .init = start)
	}

dgrtwo / file663a4c3ed972.R

Created October 4, 2017 01:16

	---
	title: "R Notebook"
	output: html_notebook
	---

	```{r}
	library(purrr)

	transition_mc <- function(steps, start, mat) {
	i <- seq_len(nrow(mat))

dgrtwo / mnist_pairs.R

Created May 31, 2017 18:56

Comparing pairs of MNIST digits based on one pixel

	library(tidyverse)

	# Data is downloaded from here:
	# https://www.kaggle.com/c/digit-recognizer
	kaggle_data <- read_csv("~/Downloads/train.csv")

	pixels_gathered <- kaggle_data %>%
	mutate(instance = row_number()) %>%
	gather(pixel, value, -label, -instance) %>%
	extract(pixel, "pixel", "(\\d+)", convert = TRUE)

dgrtwo / month_tag.csv

Created May 11, 2017 18:51

Number of Stack Overflow questions asked about each tag per month; data behind the Stack Overflow Trends tool

We can't make this file beautiful and searchable because it's too large.

	Year,Month,Questions,Tag,MonthTotal,TagTotal
	2008,8,4,.htaccess,3929,57155
	2008,9,12,.htaccess,14543,57155
	2008,10,10,.htaccess,14951,57155
	2008,11,16,.htaccess,12967,57155
	2008,12,12,.htaccess,12324,57155
	2009,1,24,.htaccess,16152,57155
	2009,2,35,.htaccess,17889,57155
	2009,3,43,.htaccess,20785,57155
	2009,4,46,.htaccess,21701,57155

dgrtwo / code-faces.R

Last active April 14, 2017 19:28

geom_vase vs geom_faces

	library(readr)
	library(dplyr)
	library(ggplot2)

	faces <- read_csv("faces.csv")

	vase <- bind_rows(select(faces, x = x1, y),
	select(faces, x = x2, y) %>% arrange(y))

	faces %>%

dgrtwo / sample-size-power.R

Created March 11, 2017 18:51

Code from this tweet: https://twitter.com/drob/status/840636042470400000

	library(tidyverse)
	library(broom)
	library(scales)
	theme_set(theme_minimal())

	crossing(n = round(10 ^ seq(1, 7, .1)),
	delta = 10 ^ seq(-1, -3, -1),
	sig.level = .05,
	sd = .3) %>%
	invoke(power.t.test, ., type = "one.sample") %>%

dgrtwo / route_data.csv

Created March 10, 2017 16:20

dgrtwo / qgraph.R

Created December 15, 2016 21:39

	library(ggplot2)
	library(igraph)
	library(ggraph)
	library(scales)
	library(ggforce)

	network_theme <- theme_no_axes() +
	theme(panel.border = element_blank())
	theme_set(network_theme)

dgrtwo / distransam_alternative.R

Created October 24, 2016 13:32

	# randomly select min_n_plates from each strain
	randomly_sampled_dataframe <- x %>%
	dplyr::group_by_(grouping_var, plate_var, sample_var) %>%
	tidyr::nest(.key = id_data) %>%
	dplyr::group_by_(grouping_var, plate_var) %>%
	dplyr::sample_n(min_n_id_per_plate) %>%
	tidyr::nest(.key = plate_data) %>%
	dplyr::group_by_(grouping_var) %>%
	dplyr::sample_n(min_n_plates_per_strain) %>%
	tidyr::unnest() %>%

David Robinson dgrtwo