inkhorn

library(ff)
library(ggthemes)
ffload(file="casino", overwrite=TRUE)

casino.orig$Outside.of.Toronto = as.ff(ifelse(casino.orig[,"City"] == "Toronto",0,1))

casino.in.toronto = glm(casino.orig[,"Q6"] == "City of Toronto" ~ Outside.of.Toronto, data=casino.orig, family=binomial(logit))
casino.outside.toronto = glm(casino.orig[,"Q6"] == "Adjacent Municipality" ~ Outside.of.Toronto, data=casino.orig, family=binomial(logit))

summary(casino.in.toronto)

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

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

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

inkhorn

library(rpart)
library(plyr)
library(rpart.plot)

ebike = read.csv("E-Bike_Survey_Responses.csv")

# This next part is strictly to change any blank responses into NAs
ebike[,2:10][ebike[,2:10] == ''] = NA

# In this section we use mapvalues from the plyr package to get rid of blanks, but also 

inkhorn

library(stringr)
library(plyr)

# We're assuming you've downloaded the SSA files into your R project directory.

file_listing = list.files()[3:135]
for (f in file_listing) {
  year = str_extract(f, "[0-9]{4}")
  if (year == "1880") { # Initializing the very long dataframe
    name_data = read.csv(f, header=FALSE)

inkhorn

Call:
glm(formula = casino$Q6 == "Neither" ~ GoBigorGoHome + TechnicalDetails + 
    Soc.Env.Issues, family = binomial(logit), data = casino)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-2.4090  -0.7344  -0.3934   0.8966   2.7194  

Coefficients:
                 Estimate Std. Error z value Pr(>|z|)    

inkhorn

Call:
glm(formula = casino$Q6 == "Adjacent Municipality" ~ GoBigorGoHome + 
    TechnicalDetails + Soc.Env.Issues, family = binomial(logit), 
    data = casino)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-1.0633  -0.7248  -0.5722  -0.3264   2.7136  

Coefficients: