achetverikov

library(ggplot2)
library(data.table)
library(brms)
library(cmdstanr)
set_cmdstan_path('//wsl$/Ubuntu/home/andche/.cmdstan/cmdstan-2.35.0')


distr_fun_std <- function(x, mean, sigma, lambda){
  lambda+(1-2*lambda)*pnorm((x- mean)/sigma)
}

achetverikov

#!/usr/bin/python

from apscheduler.schedulers.blocking import BlockingScheduler
from datetime import datetime
import json
import pickle
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait

achetverikov

library(data.table)
library(xml2)
library(stm)
library(quanteda)
library(gofastr)
library(stopwords)
library(spacyr)
library(quanteda)
library(quanteda.textplots)
library(Hmisc)

achetverikov

library(BayesFactor)
library(future.apply)
library(future.batchtools)

# for the simulations, I used our cluster that runs PBS Torque 
plan(batchtools_torque, resources = list(walltime = '01:00:00', memory = '2Gb')) # specify that the PBS Torque cluster is used and the resources we want

# create conditions combinations
conditions <- expand.grid(d = seq(0, 0.36, 0.04), N = seq(5, 65, 4))

achetverikov

#!/bin/bash
#PBS -N <%= job.name %>
#PBS -o <%= log.file %>
#PBS -l walltime=<%= resources$walltime %>,mem=<%= resources$memory %>M
#PBS -q batch
#PBS -j oe

## setup modules

## create our own temp dir (and clean it up later)

achetverikov

library(datasauRus)
library(data.table)
library(ragg)
library(ggplot2)

dsd <- datasaurus_dozen
setDT(dsd)
dsd <- dsd[dataset%in%c('star','dino','away', 'circle')]
dsd[,z:=rnorm(.N, sd = 0.4)]
dsd[,y_new:=0.2*x+z+y, by = dataset]

achetverikov

seq_presentation <- function(p, name = 'plot_layers_%i.png', res = 320, width = 6.2, height = 6.2){
  n_layers <- length(p$layers)
  y_range <- ggplot_build(p)$layout$panel_scales_y[[1]]$range$range
  
  for (i in c(n_layers:0)){
    if (!is.null(name))
      png(file = sprintf(name , i), res = res, width = width*res, height = height*res)
    if (i!=0) {
      p_copy <- copy(p)
      p_copy$layers[n_layers:i] <- NULL

achetverikov

library(ggplot2)
library(gganimate)
library(ggthemes)
library(data.table)

n = 80 # number of dots
max_r = 300 # aperture radius

dt <- data.table(r = max_r*sqrt(runif(n)), theta =2*pi*runif(n), dot_n = 1:n)

achetverikov

# turboscale values are from https://gist.github.com/mikhailov-work/ee72ba4191942acecc03fe6da94fc73f
library(grDevices)

turbo_colormap_data = matrix(c(c(0.18995,0.07176,0.23217),
c(0.19483,0.08339,0.26149),
c(0.19956,0.09498,0.29024),
c(0.20415,0.10652,0.31844),
c(0.20860,0.11802,0.34607),
c(0.21291,0.12947,0.37314),
c(0.21708,0.14087,0.39964),