inkhorn

# Here's where I extract the database IDs and repeat them 50 times to make the column long enough for
# my new long-form dataset (596,100 rows)

client.data.new = rep(client.data[,1],50)

for (i in 2:32){
# for each column in the first 31 after the ID column, find the 49 matching columns 
# to the right and stack them using melt

    stacked.data = melt(client.data, id.vars="CnBio_ID", measure.vars=seq(i,(i+(31*49)),31), value.name=names(client.data)[i])

inkhorn

library(ff)
library(ffbase)
library(stringr)
library(ggplot2)
library(ggthemes)
library(reshape2)
library(RgoogleMaps)

# Loading 2 copies of the same data set so that I can convert one and have the original for its text values
casino = read.csv("/home/inkhorn/Downloads/casino_survey_results20130325.csv")

inkhorn

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

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-3.6426  -0.4745  -0.1156   0.4236   3.4835  

Coefficients:

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:

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

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

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

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(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

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")