rpietro

#creating a dataset with 1.8 GIGs
setwd("~/Desktop")
bigdf <- data.frame(dim=sample(letters, replace=T, 4e7), fact1=rnorm(4e7), fact2=rnorm(4e7, 20, 50))
write.csv(bigdf, 'bigdf.csv', quote = F)

#opening the dataset and measuring performance time
setwd("~/Desktop")
library(sqldf)
f <- file("bigdf.csv")
system.time(bigdf <- sqldf("select * from f", dbname = tempfile(), file.format = list(header = T, row.names = F)))

rpietro

#this documented script is based on the article "Toolkit for Weighting and Analysis of Nonequivalent Groups: A tutorial for the twang package" http://goo.gl/2xYBX as well as the package documentation at http://goo.gl/BWaLH

library(twang)
library(lattice)
set.seed(1)
data(lalonde)
ps.lalonde <- ps(treat ~ age + educ + black + hispan + nodegree + married + re74 + re75, data = lalonde, n.trees=5000, #n.trees is the maximum number of iterations that gbm will run
                 interaction.depth=2, #The maximum depth of variable interactions. 1 implies an additive model, 2 implies a model with up to 2-way interactions, etc.
                 shrinkage=0.01, #ps() will issue a warning if the estimated optimal number of iterations is too close to the bound selected in this argument because it indicates that balance may improve if more complex models (i.e., those with more trees) are considered. The user should increase n.trees or decrease shrinkage if this warning appears.
                 perm.test.iters=0, #spec

rpietro

#Load sqldf package, which will load all others necessary
#By default, SQLite runs in background to do processing, could use others DB engines if you wanted

library("sqldf")

#Import employees data

employees  <- structure(list(id = 1:20, lastname = structure(c(5L, 14L, 13L, 15L, 6L, 16L, 9L, 1L, 3L, 12L, 10L, 8L, 12L, 3L, 11L, 13L, 10L, 7L, 2L, 4L), .Label = c("a", "b", "c", "f", "g", "h", "i", "j", "n", "o", "p", "r", "s", "t", "w", "z"), class = "factor"), firstname = structure(c(12L, 6L, 5L, 12L, 11L, 15L, 9L, 18L, 17L, 7L, 8L, 10L, 4L, 14L, 19L, 16L, 1L, 13L, 2L, 3L), .Label = c("chris", "dima", "drew", "eric", "hila", "jason", "jeremy", "joe", "jon", "jowanza", "lashanda", "matt", "michael", "michelle", "randy", "rudi", "solon", "stewart", "tim"), class = "factor"), gender = structure(c(2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("f", "m"), class = "factor")), .Names = c("id", "lastname", "firstname", "gender"), class = "data.frame", row.names = c(NA, -20

rpietro

#assume you have a data set represented by an object called BOD (BOD is actually a dataset internal to R). then run dput with that data object
dput(BOD)
#the ouput of this function will be the representation of that data set: structure(list(Time = c(1, 2, 3, 4, 5, 7), demand = c(8.3, 10.3, 19, 16, 15.6, 19.8)), .Names = c("Time", "demand"), row.names = c(NA, -6L), class = "data.frame", reference = "A1.4, p. 270")
#when you want to request help, just start the reproducible example by throwing the output of dput into a data object:
BOD  <- structure(list(Time = c(1, 2, 3, 4, 5, 7), demand = c(8.3, 10.3, 19, 16, 15.6, 19.8)), .Names = c("Time", "demand"), row.names = c(NA, -6L), class = "data.frame", reference = "A1.4, p. 270")
#from here on then just write the code you wrote and the corresponding error message

rpietro

rm(list = ls(all = TRUE)) #CLEAR WORKSPACE
library(quantmod)

#Scrape data from the website
library(XML)
rawPMI <- readHTMLTable('http://www.ism.ws/ISMReport/content.cfm?ItemNumber=10752')
rawPMI
PMI <- data.frame(rawPMI[[1]])
PMI
names(PMI)[1] <- 'Year'

rpietro

library(catR)
Bank <- createItemBank(items = 500, model = "3PL", thMin = -4, thMax = 4, step = 0.05)
Start <- list(nrItems = 1, theta = 0, startSelect = "MFI")
Test <- list(method = "WL", itemSelect = "MFI")
Stop <- list(rule = "classification", thr = 2, alpha = 0.05)
Final <- list(method = "WL", alpha = 0.05)
res <- randomCAT(trueTheta = 1, itemBank = Bank, start = Start, test = Test, stop = Stop, final = Final)
res
plot(res, ci = TRUE, trueTh = TRUE, classThr = 2)

rpietro

Slimdown

A very basic regex-based Markdown parser. Supports the following elements (and can be extended via Slimdown::add_rule()):

• Headers
• Links
• Bold
• Emphasis
• Deletions

rpietro

```{r echo=FALSE, error=TRUE}
perc <- function(var){
    result <- 100*(table(var))/sum(table(var))
    return(result)
}

```

rpietro

# this code comes straight from the three posts by Joel Caldwell's on his outstanding blog Engaging Market Research at http://joelcadwell.blogspot.com/ . Specifically, the posts are http://goo.gl/Rcsn4 , http://goo.gl/dDPnV and http://goo.gl/8C9Aj

library(psych)
library(lavaan)
library(mvtnorm)
library(qgraph)

# The goal is to show all the R code that you would need
# to reproduce everything that has been reported.
# We will use the mvtnorm package in order to randomly 

rpietro

Sublime Text 2 - Useful Shortcuts

Tested in Mac OS X: super == command

Open/Goto

---

• super+t: go to file
• super+ctrl+p: go to project
• super+r: go to methods