JoFrhwld

#' SQL Load
#' 
#' This is function meant to be used along with ldply to read data in using sqldf.
#' 
#' @param x the path to a file to be read
#' @param selection the columns to return. Defaults to \code{"*"}
#' @param condition conditions defining which data rows to load in SQL
#' @param file.format an argument to be passed to \code{sqldf}. 
#' Defaults to assume a tab-delimited file with a header row.
#' See \code{?sqldf} for more info

JoFrhwld

libarary(plyr)
library(dplyr)
library(ggplot2)


baseball %>%
  group_by(year)%>%
  summarise(r=sum(r)) %>%
  ggplot(., aes(year, r)) +
    geom_point()

JoFrhwld

library(lme4)

mod <-  lmer(F1_n ~ plt_vclass * Decade_c * freq_c + (plt_vclass + freq_c| File) + (Decade_c|word), 
             data = ays_to_test)

boot_fun <- function(mod){
  # x is a named vector
  x <- fixef(mod)
  
  #out is a longer named vector

JoFrhwld

library(babynames)
library(dplyr)
library(ggplot2)

lifetables %>%
  mutate(decade = year)%>%
  group_by(decade)%>%
  mutate(prob_alive = lx/100000,
         study_year = year + x)->prob_people

JoFrhwld

from nltk.corpus import cmudict
import string
import re

the_dict = cmudict.dict()
the_dict2 = {word: [string.join(x, sep = " ") 
			for x in entries] 
				for word, entries in the_dict.items()}

two_n = {word: entries 

JoFrhwld

• As datasets grow in size, it's going to become trivial to find "significant" effects (i.e. non-zero).
  • That isn't a problem that can be fixed by just shrinking α down.
• We need to ask ourselves:
  1. Are the effects we're observing large enough to be interesting?
  2. How big did we expect them to be?
• To answer (2), we need an articulated theory that can make quantitative predictions.
• I walk through two examples where I try to predict effect sizes given background theory.
• link: https://jofrhwld.github.io/papers/plc39_2015/

JoFrhwld

scored_vclass <- function(df,class,vowels, dims = c("F1","F2")){
	require(MASS)
	df <- df[df[ ,class] %in% vowels, ]
	

	df[ ,class] <- as.character(df[ ,class])
	df[,class] <- as.factor(df[,class])
	
	
	for(i in dims){

JoFrhwld

clip.border <- function(deldir.obj, border){
	## deldir.obj = output of deldir::deldir
	## border = list of borders defined in data frames
	##		Importantly, with columns called "x" and "y" 
	require(gpclib)

	## bord will be a gpc polygon of all of the regions given to the argument "border"
	bord <- as(matrix(ncol = 2), "gpc.poly")
	for(i in seq(along = border)){
		b <- as(border[[i]], "gpc.poly")

JoFrhwld

##########
## Block 1: Preparing the data

library(plyr)
library(reshape)

## Create a Subsystem Column
all_philly$Subsystem <- all_philly$VClass
levels(all_philly$Subsystem) <- c("Vhr", "Vw", "V", "misc", "Vh", "Vh", "Vhr", "Vw", "Vy", 
"Vy", "V", "Vy", "Vy", "Vy", "V", "Vw", "Vy", "Vy", "Vhr", 

JoFrhwld

library(purrr)
library(dplyr)
library(data.table)

meas_files <- Sys.glob("DataDirectory/speakers/*/*.txt")

meas_files %>%
  map(~fread(.)[,list(idstring =  gsub("(*).txt",
                                       "\\1", 
                                       basename(.)),