inkhorn

library(jsonlite)

cp = fromJSON(txt = "Cell Phone Data.txt", simplifyDataFrame = TRUE)

num.atts = c(4,9,11,12,13,14,15,16,18,22)

cp[,num.atts] = sapply(cp[,num.atts], function (x) as.numeric(x))
cp$aspect.ratio = cp$att_pixels_y / cp$att_pixels_x
cp$isSmartPhone = ifelse(grepl("smart|iphone|blackberry", cp$name, ignore.case=TRUE) == TRUE | cp$att_screen_size >= 4, "Yes", "No")

inkhorn

library(plyr)
library(ggplot2)
library(ggmap)

libraries = read.csv("ontario_library_stats_2010.csv")
libraries$isFN = ifelse(libraries$Library.Service.Type == "First Nations Library",1,0)

# Here we create the 'proportionate' versions of all the variables
libraries[,143:265] = sapply(libraries[,20:142], function (x) x/libraries[,13])
names(libraries)[143:265] = paste(names(libraries)[20:142], "P",sep=".")

inkhorn

import os
rfiles = os.listdir('.')
rc = []
for f in rfiles:
    if '.txt' in f: 
    # The recipes come in 3 txt files consisting of 1 recipe per line, the 
    # cuisine of the recipe as the first entry in the line, and all subsequent ingredient
    # entries separated by a tab
        infile = open(f, 'r')
        rc.append(infile.read())

inkhorn

recipes = readLines('recipes combined.tsv')

# Once I read it into R, I have to get rid of the /t
# characters so that it's more acceptable to the tm package

recipes.new = apply(as.matrix(recipes), 1, function (x) gsub('\t',' ', x))

recipes.corpus = Corpus(VectorSource(recipes.new))
recipes.dtm = DocumentTermMatrix(recipes.corpus)

inkhorn

# ****Introduction****

# Data analysis is like an interview.  In any interview, the interviewer hopes to use a series of 
# questions in order to discover a story.  The questions the interviewer asks, of course, are 
# subjectively chosen.  As such, the story that one interviewer gets out of an interviewee might 
# be fairly different from the story that another interviewer gets out of the same person.  In the 
# same way, the commands (and thus the analysis) below are not the only way of analyzing the data.  
# When you understand what the commands are doing, you might decide to take a different approach 
# to analyzing the data.  Please do so, and be sure to share what you find!

inkhorn

ltep = read.csv("ltep-survey-results-all.csv")

library(likert)
library(ggthemes)

# Here I flip the scoring
ltep[,13:19] = sapply(ltep[,13:19], function (x) 8 - x)
deal.w.esources = likert(ltep[,13:19])
summary(deal.w.esources)
plot(deal.w.esources, text.size=6, text.color="black") + theme(axis.text.x=element_text(colour="black", face="bold", size=14), axis.text.y=element_text(colour="black", face="bold", size=14), axis.title.x=element_text(colour="black", face="bold", size=14), plot.title=element_text(size=18, face="bold")) + ggtitle("What guidelines should Ontario use\n for its future mix of energy sources?")

inkhorn

docs = []
from os import listdir, chdir
import re

   
# Here's the section where I try to filter useless stuff out.
# Notice near the end all of the regex patterns where I've called 
# "re.DOTALL".  This is pretty key here.  What it means is that the
# .+ I have referenced within the regex pattern should be able to 
# pick up alphanumeric characters, in addition to newline characters

inkhorn

library(stringr)
library(plyr)
library(tm)
library(tm.plugin.mail)
library(SnowballC)
library(topicmodels)

# At this point, the python script should have been run, 
# creating about 126 thousand txt files.  I was very much afraid
# to import that many txt files into the tm package in R (my computer only

inkhorn

docs = []
from os import listdir, chdir
import re

   
# Here's my attempt at coming up with regular expressions to filter out
# parts of the enron emails that I deem as useless.

email_pat = re.compile(".+@.+")
to_pat = re.compile("To:.+\n")

inkhorn

library(ff)
library(ffbase)
library(RgoogleMaps)
library(plyr)

addTrans <- function(color,trans)
{
  # This function adds transparancy to a color.
  # Define transparancy with an integer between 0 and 255
  # 0 being fully transparant and 255 being fully visable