jflanaga

# Modified from https://martinctc.github.io/blog/vignette-write-and-read-multiple-excel-files-with-purrr/
# Note: this will return numeric codes rather than value labels. Use `as_factor()` to get the latter

library(tidyverse)
    
    
# function for writing the csv files    
output_csv <- function(data, names){ 
    # output directory
    folder_path <- "data/"

jflanaga

#!/usr/bin/env python
# adopted from https://github.com/derekgreene/twitter-jsonl-tools

import argparse
import codecs
import fileinput
import itertools
import logging
import operator
import ujson as json

jflanaga

# -- coding: utf-8 --
# adapted from https://raw.githubusercontent.com/DocNow/twarc/master/twarc/json2csv.py

import binascii
import csv
import codecs
import gzip
import json

jflanaga

# Method 1
from collections import defaultdict

def count_words(string):
    '''count number of times each word apppears in a string'''
    counts = defaultdict(int)
    for word in string.split():
        counts[word] += 1
    return counts
  

jflanaga

# Count values in a dictionary when values are in a list 
d2 = {'a': ['I','said','that', 'I'],'b': ['she','was','here']}
from collections import Counter
counts = {k: Counter(v) for k, v in d2.items()}

# Count items in sublists
lst = [['I', 'said', 'that'], ['said', 'I']]
Counter(word for sublist in lst for word in sublist)

# Combining the two

jflanaga

#----------------------------------------------------------------------------------------
# File: 
# Author: Joseph Flanagan, adopted from https://stackoverflow.com/questions/10002021/split-dataframe-into-multiple-output-files-in-r
# email:   [email protected]
# Purpose: Split a dataframe by group, then save each as separate .csv file
#----------------------------------------------------------------------------------------

# new tidyverse solution with `group_walk`
library(dplyr)
library(readr)

jflanaga

#----------------------------------------------------------------------------------------
# File: pvalues-prob-sim.R
# Author: Joseph Flanagan, reworking of script by Daniel Lakens
# email:   [email protected]
# Purpose: Function for demonstrating different probability distributions of p-values
#----------------------------------------------------------------------------------------

library(pwr)

sim_pvalues <- function(n, mean, sd, mu = 100, n_sims = 100000){

jflanaga

sound = selected ("Sound")
textgrid = selected ("TextGrid")
spectrogram = selected ("Spectrogram")
formant = selected ("Formant")
Select inner viewport: 1, 5, 1, 2
select sound
Draw... 0 0 0 0 no Curve
Draw inner box
Select inner viewport: 1, 5, 2, 3.4
select spectrogram

jflanaga

PREFIX dc:<http://purl.org/dc/terms/>
PREFIX austalk:<http://ns.austalk.edu.au/>
PREFIX olac:<http://www.language-archives.org/OLAC/1.1/>
PREFIX ausnc:<http://ns.ausnc.org.au/schemas/ausnc_md_model/>
PREFIX foaf:<http://xmlns.com/foaf/0.1/>
PREFIX dbpedia:<http://dbpedia.org/ontology/>
PREFIX rdf:<http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#>
PREFIX geo:<http://www.w3.org/2003/01/geo/wgs84_pos#>
PREFIX iso639schema:<http://downlode.org/rdf/iso-639/schema#>

jflanaga

#This is my attempt to recreate the [Hack Session for NYTimes Dialect Map Visualization](http://nycdatascience.com/meetup/hack-session-for-nytimes-dialect-map-visualization-sponsored-by-oreilly-strata/)
# See question on [stackoverflow](http://stackoverflow.com/questions/29362681/loop-multiple-webpages-in-r)



library("RCurl")
library("XML")


# Get the data