jwdink

library('dplyr')
library('tidyr')
library('pbapply')

#' simulate()
#'
#' @param num_groups Number of groups
#' @param num_per_group Number of observations per group
#' @param true_coef The true `beta_1` in `Y_t ~ beta_0 + beta_1*X_t`
#' @param phi A function that takes Y_t-1,...,Y_t and returns Xt

jwdink

library(dplyr)
library(purrr)
library(broom)

# A Single Study: ----
a_study <- function(effect_size_distr_function, main_n = 100, pilot_n = 0, pilot_effect_size_threshold = NULL) {
  this_study_effect_size <- effect_size_distr_function()

  pilot <- list(result_vec = rnorm(n = pilot_n, mean = this_study_effect_size, sd = 1),
                occurred = pilot_n > 0)

jwdink

library('dplyr')
library('survival')

## Make the Data: -----
set.seed(3)
n_sub <- 1000
current_date <- 365*2

true_shape <- 2
true_scale <- 365

jwdink

generate_markdown_for_site <- function(path_to_rmd, path_to_knit_to) {
  filename <- basename(path_to_rmd)
  message("Setting working directory to ", path_to_rmd)
  setwd(dirname(path_to_rmd))
  post_name <- sub("^([^.]*).*", "\\1", filename)
  content <- readLines(paste0(post_name, ".Rmd"))
  render_markdown(strict=TRUE)
  opts_knit$set(out.format='markdown')
  opts_knit$set(base.dir= paste0(path_to_knit_to, "/", post_name,"/") )
  opts_knit$set(base.url= paste0("/static/",post_name,"/") )

jwdink

fitgamma <- function(x) {
  # Equivalent to `MASS::fitdistr(x, densfun = "gamma")`, where x are first rescaled to 
  # the appropriate scale for a gamma distribution. Useful for fitting the gamma distribution to 
  # data which, when multiplied by a constant, follows this distribution
  if (!requireNamespace("MASS")) stop("Requires MASS package.")
  
  fit <- glm(formula = x ~ 1, family = Gamma)
  out <- MASS::fitdistr(x * coef(fit), "gamma")
  out$scaling_multiplier <- unname(coef(fit))
  out

jwdink

# load *eyetrackingR* and set data options
library(eyetrackingR)
data("word_recognition")
dataset <- make_eyetrackingr_data(word_recognition, 
                               participant_column = "ParticipantName",
                               trial_column = "Trial",
                               time_column = "TimeFromTrialOnset",
                               trackloss_column = "TrackLoss",
                               aoi_columns = c('Animate','Inanimate'),
                               treat_non_aoi_looks_as_missing = TRUE

jwdink

center_predictors = function(data, predictors) {
  if (!require('dplyr')) stop("Dplyr required")
  require('lazyeval')
  
  dots = list()
  for (i in seq_along(predictors)) {
    name = paste0(predictors[i], "_C")
    if (is.factor(data[[predictors[i]]])) {
      if (length(levels(data[[predictors[i]]])) > 2) stop("'", predictors[i], "' is a factor with more than 2 levels, cannot center.")
      message("'", predictors[i], "' is a factor, will convert so that '", levels(data[[predictors[i]]])[2], "' will be 'positive'.")

jwdink

# This takes a folder of session files, converts them to dataframe

## MAIN:
convert_session_files = function(path, 
                                 trial_advance_str= "TrialNum", 
                                 identifier_colnames = c("TrialNum", "BlockNum", "PhaseNum"),
                                 participant_string = "subject_code", 
                                 exp_time_string = "start_time",
                                 overwrite_conflict_function = NULL,
                                 echo=TRUE) {

jwdink

# Dplyr's Join w/ Progress Bar
#
# @author Jacob Dink
#         jacobwdink@gmail.com
#         github.com/jwdink
#
# @created April 8, 2015
#
# Dplyr's join functions with a progress bar. Hacky but helpful.
# Don't call this function, call the dplyr-named versions (e.g., left_join_pb)

jwdink

summary_se = function(data, measurevar, idvar, betweenvars) {
  require('dplyr')
  require('lazyeval')
  
  summarized = data %>%
    group_by_(.dots=c(idvar, betweenvars)) %>%
    dplyr::summarise_(.dots = list(
      MeasureVar = interp( ~mean( MEASUREVAR, na.rm=TRUE), MEASUREVAR = as.name(measurevar)  )
    )) %>%
    ungroup() %>%