inkhorn

safe.max = function(invector) {
  na.pct = sum(is.na(invector))/length(invector)
  if (na.pct == 1) {
    return(NA) }
  else {
    return(max(invector,na.rm=TRUE))
  }
}

inkhorn

testvars = c(6,7,9,10,11,12,13,14,16, 17,18,19,20,21,23,24,25,26,384,375,376,386,385,387,388)

resultlist = c()
for (i in testvars) {
  xsq = chisq.test(big.dataset[,i], big.dataset$DV_3lvls)$statistic
  varname = names(big.dataset)[i]
  tab = xtabs(~DV_3lvls + big.dataset[,i], data=big.dataset)
  resultlist = rbind(resultlist, list(chisq=xsq, testvar=varname, xtab=tab))
}

inkhorn

# These column numbers represent fields with name/contact info that I've 
# marked with 1s and 0s depending on whether or not there's anything in 
# the field.

bio_cols = c(5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,23,24,25,26)

# Now we get the row numbers of all the records with duplicate IDs

dupe_id_rows = which(duplicated(big.dataset$ID) == TRUE)

inkhorn

scents = read.table("clipboard",header=TRUE,sep="\t")
strial3.by.sex.wide = ddply(scents, 'Sex', function (x) quantile(x$S.Trial.3, c(0,.5,1), na.rm=TRUE))
strial3.by.sex.smokers = melt(ddply(subset(scents,Smoker == "Y") , 'Sex', function (x) quantile(x$S.Trial.3, c(0,1), na.rm=TRUE)),variable.name="Percentile",value.name="Time")

ggplot() + geom_crossbar(data=strial3.by.sex.wide, aes(x=Sex, y=strial3.by.sex.wide$"50%", ymin=strial3.by.sex.wide$"0%", ymax=strial3.by.sex.wide$"100%"),fill="#bcc927",width=.75) +
geom_point(data=strial3.by.sex.smokers, aes(x=Sex, y=Time, stat="identity"), size=3) 
+ opts(legend.title = theme_text(size=10, face="bold"), legend.text = theme_text(size=10),
 axis.text.x=theme_text(size=10), axis.text.y=theme_text(size=10,hjust=1), axis.title.x=theme_text(size=12,face="bold"), axis.title.y=theme_text(size=12, angle=90, 
face="bold")) + scale_y_continuous(name="Time to Completion")

inkhorn

penultimax = function(invector) {
   # If the vector starts off as only having 1 or 0 numbers, return NA
  if (length(invector) <= 1) {
    return(NA)
  }
  first.max = safe.max(invector)
   #Once we get the max, take it out of the vector and make newvector
  newvector = invector[!invector == first.max]
   #If newvector now has nothing in it, return NA
  if (length(newvector) == 0) {

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|)