Hao Ye ha0ye

Trying to better and open science a little bit every day

ha0ye / zs_dist.R

Created October 20, 2021 23:13

distribution of zodiac signs in US population

	library(tidyverse)
	library(lubridate)

	# modified from https://stackoverflow.com/questions/48026462/writing-r-function-using-lubridate-package-that-takes-dateex-august-14-and
	zodiac_sign <- function(input)
	{
	zodiac_sign_df <- data.frame(Month = c("March", "April", "May", "June", "July", "August", "September", "October", "November", "December", "January", "February"),
	Zodiac_Separation_Dt = c(21, 20, 21, 21, 23, 23, 23, 23, 22, 22, 20, 19),
	LowerSideZS = c("Pisces", "Aries","Taurus","Gemini","Cancer","Leo","Virgo","Libra","Scorpio","Sagittarius","Capricorn","Aquarius"),
	UpperSideZS = c("Aries","Taurus","Gemini","Cancer","Leo","Virgo","Libra","Scorpio","Sagittarius","Capricorn","Aquarius", "Pisces"),

ha0ye / generate_sequences.R

Last active August 31, 2021 21:07

generate random sequences without consecutive repeats

	f <- function(x)
	{
	n <- sum(x)
	v <- numeric(n)
	prev <- NULL
	for (i in 1:n)
	{
	idx <- x > floor(sum(x)/2) # how many counts are > n/2
	if (sum(idx) >= 2) # error if more than 2 (impossible?)
	{

ha0ye / main.R

Last active June 26, 2020 14:59

EDM simplex calculations test (E = 1)

	library(rEDM)

	# generate time series
	set.seed(42)
	ts_length <- 50
	x <- rnorm(ts_length)

	# pre-compute distance matrix
	x_dists <- as.matrix(dist(x))
	x_dists <- x_dists[, -ts_length] # last point can't be a nearest neighbor

ha0ye / gist:197de5797df1d4e2b14a8bff4fb99c95

Created March 28, 2020 01:15

pairwise overlap calculations

	calc3 <- function(sets)
	{
	sets <- check_sets(sets)
	set_lengths <- vapply(sets, length, 0)
	set_order <- order(set_lengths)
	sets <- sets[set_order]
	set_lengths <- set_lengths[set_order]

	n_sets <- length(sets)
	set_names <- names(sets)

ha0ye / gist:d62b33b1d735b09610852a7113f6bda3

Created March 12, 2020 16:35

Forward forecasts using rEDM

	library(rEDM)

	#### Example 1: a single forward prediction

	# Assume we have already done the analysis, finding that the best embedding
	# dimension is 2. Our objective is to make multiple 1-step ahead forecasts
	# using simplex and E = 2.
	dat <- data.frame(yr = as.numeric(time(sunspot.year)),
	sunspot_count = as.numeric(sunspot.year))
	E <- 3

ha0ye / script.R

Created February 18, 2020 16:13

read in param output from text file

	full_text <- readLines(file, warn = FALSE)
	start_par_line <- grep("^\\$par", full_text)
	start_objective_line <- grep("^\\$objective", full_text)
	param_lines <- seq(from = start_par_line,
	to = start_objective_line - 3,
	by = 2)

	params <- purrr::map_dfc(param_lines, function(line_idx)
	{
	readr::read_delim(file, delim = " ",

ha0ye / dplyr-timing-test.R

Last active July 8, 2019 04:00

	library(dplyr)
	library(microbenchmark)

	set.seed(42)
	n <- 10000
	df <- data.frame(a = rep(seq(n), 2),
	x = rnorm(2 * n))

	group_summarize_mutate <- function(df)
	{

ha0ye / change legend labels in "likert" package

Created June 29, 2019 00:47

	library(likert)
	data(pisaitems)

	##### Item 24: Reading Attitudes
	items24 <- pisaitems[,substr(names(pisaitems), 1,5) == 'ST24Q']
	head(items24); ncol(items24)

	names(items24) <- c(
	ST24Q01="I read only if I have to.",
	ST24Q02="Reading is one of my favorite hobbies.",

ha0ye / drake-parallel.R

Created June 21, 2019 16:29

parallelization within drake targets

	library(drake)
	library(furrr)

	future::plan(future::multiprocess)

	tictoc::tic()
	params = data.frame(t = c(1, 2, 3, 1, 2, 3))
	out = purrr::pmap(params, Sys.sleep)
	tictoc::toc()

ha0ye / lavaan to visNetwork

Created May 3, 2019 18:57