![Try
It!
#1
Overgrown
Calculator
• basic
calcula$ons
> 2 + 2 [Hit
ENTER]
> log(100) [Hit
ENTER]
• calculate
the
value
of
$100
aIer
10
years
at
5%
> 100 * exp(0.05*10) [Hit
ENTER]
• construct
a
vector
&
do
a
vectorized
calcula$on
> year <- (1,2,5,10,25) [Hit
ENTER]
this
returns
an
error.
why?
> year <- c(1,2,5,10,25) [Hit
ENTER]
> 100 * exp(0.05*year) [Hit
ENTER]](https://image.slidesharecdn.com/rworkshopforbeginners-120126154055-phpapp01/85/R-Workshop-for-Beginners-13-320.jpg)
![R
as
a
Programming
Language
fibonacci <- function(n) {
fib <- numeric(n)
fib [1:2] <- 1
for (i in 3:n) {
fib[i] <- fib[i-1] + fib[i-2]
}
return(fib[n])
Image from cover of Abelson
& Sussman’s textThe }
Structure and Interpretation
of Computer Languages](https://image.slidesharecdn.com/rworkshopforbeginners-120126154055-phpapp01/85/R-Workshop-for-Beginners-14-320.jpg)
![Data
Structures
in
R
numeric
x <- c(0,2:4)
vectors
y <- c(“alpha”, “b”, “c3”, “4”)
Character
logical
z <- c(1, 0, TRUE, FALSE)
> class(x)
[1] "numeric"
> x2 <- as.logical(x)
> class(x2)
[1] “logical”](https://image.slidesharecdn.com/rworkshopforbeginners-120126154055-phpapp01/85/R-Workshop-for-Beginners-16-320.jpg)
![Data
Structures
in
R
lists
lst <- list(x,y,z)
objects
M <- matrix(rep(x,3),ncol=3)
matrices
data
frames*
df <- data.frame(x,y,z)
> class(df)
[1] “data.frame"](https://image.slidesharecdn.com/rworkshopforbeginners-120126154055-phpapp01/85/R-Workshop-for-Beginners-17-320.jpg)
![A
Swiss-‐Army
Knife
for
Data
• Indexing
• Three
ways
to
index
into
a
data
frame
– array
of
integer
indices
– array
of
character
names
– array
of
logical
Booleans
• Examples:
df[1:3,]
df[c(“New York”, “Chicago”),]
df[c(TRUE,FALSE,TRUE,TRUE),]
df[df$city == “New York”,]](https://image.slidesharecdn.com/rworkshopforbeginners-120126154055-phpapp01/85/R-Workshop-for-Beginners-28-320.jpg)
More Related Content
Similar to R Workshop for Beginners (20)
![[1062BPY12001] Data analysis with R / week 2](https://cdn.slidesharecdn.com/ss_thumbnails/dataanalyzer01-180307063046-thumbnail.jpg?width=560&fit=bounds)
R Workshop for Beginners
- 1. Munging & Visualizing Data with R Michael E. Driscoll CTO, Metamarkets @medriscoll Xavier Léauté Metamarkets @xvrl Barret Schloerke Metamarkets
- 2. I. A Tour of R
- 5. R is a tool for… Data Manipula?on • connec$ng to data sources • slicing & dicing data Modeling & Computa?on • sta$s$cal modeling • numerical simula$on Data Visualiza?on • visualizing fit of models • composing sta$s$cal graphics
- 6. R is an environment
- 7. Its interface is plain
- 8. RStudio to the rescue
- 9. ## load in some Insurance Claim data library(MASS) data(Insurance) Insurance <- edit(Insurance) Let’s take a tour head(Insurance) dim(Insurance) ## plot it nicely using the ggplot2 package of some data in R library(ggplot2) qplot(Group, Claims/Holders, data=Insurance, geom="bar", stat='identity', position="dodge", facets=District ~ ., fill=Age, ylab="Claim Propensity", xlab="Car Group") ## hypothesize a relationship between Age ~ Claim Propensity ## visualize this hypothesis with a boxplot x11() library(ggplot2) qplot(Age, Claims/Holders, data=Insurance, geom="boxplot", fill=Age) ## quantify the hypothesis with linear model m <- lm(Claims/Holders ~ Age + 0, data=Insurance) summary(m)
- 10. R is “an overgrown calculator” sum(rgamma(rpois(1,lambda=2),shape=49,scale=.2)))
- 11. R is “an overgrown calculator” • simple math > 2+2 4 • storing results in variables > x <- 2+2 ## ‘<-’ is R syntax for ‘=’ or assignment > x^2 16 • vectorized math > weight <- c(110, 180, 240) ## three weights > height <- c(5.5, 6.1, 6.2) ## three heights > bmi <- (weight*4.88)/height^2 ## divides element-wise 17.7 23.6 30.4
- 12. R is “an overgrown calculator” • basic sta$s$cs mean(weight) sd(weight) sqrt(var(weight)) 176.6 65.0 65.0 # same as sd • set func$ons union intersect setdiff • advanced sta$s$cs > pbinom(40, 100, 0.5) ## P that a coin tossed 100 times 0.028 ## will comes up less than 40 heads > pshare <- pbirthday(23, 365, coincident=2) 0.530 ## probability that among 23 people, two share a birthday
- 13. Try It! #1 Overgrown Calculator • basic calcula$ons > 2 + 2 [Hit ENTER] > log(100) [Hit ENTER] • calculate the value of $100 aIer 10 years at 5% > 100 * exp(0.05*10) [Hit ENTER] • construct a vector & do a vectorized calcula$on > year <- (1,2,5,10,25) [Hit ENTER] this returns an error. why? > year <- c(1,2,5,10,25) [Hit ENTER] > 100 * exp(0.05*year) [Hit ENTER]
- 14. R as a Programming Language fibonacci <- function(n) { fib <- numeric(n) fib [1:2] <- 1 for (i in 3:n) { fib[i] <- fib[i-1] + fib[i-2] } return(fib[n]) Image from cover of Abelson & Sussman’s textThe } Structure and Interpretation of Computer Languages
- 15. Func$on Calls • There are ~ 1100 built-‐in commands in the R “base” package, which can be executed on the command-‐line. The basic structure of a call is thus: output <- function(arg1, arg2, …) • Arithme$c Opera$ons + - * / ^ • R func$ons are typically vectorized x <- x/3 works whether x is a one or many-‐valued vector
- 16. Data Structures in R numeric x <- c(0,2:4) vectors y <- c(“alpha”, “b”, “c3”, “4”) Character logical z <- c(1, 0, TRUE, FALSE) > class(x) [1] "numeric" > x2 <- as.logical(x) > class(x2) [1] “logical”
- 17. Data Structures in R lists lst <- list(x,y,z) objects M <- matrix(rep(x,3),ncol=3) matrices data frames* df <- data.frame(x,y,z) > class(df) [1] “data.frame"
- 18. Summary of Data Structures Linear Rectangular ? Homogeneous vectors matrices Heterogeneous lists data frames*
- 19. R is a numerical simulator • built-‐in func$ons for classical probability distribu$ons • let’s simulate 10,000 trials of 100 coin flips. what’s the distribu$on of heads? > heads <- rbinom(10^5,100,0.50) > hist(heads)
- 20. Func$ons for Probability Distribu$ons ddist( ) density func$on (pdf) pdist( ) cumula$ve density func$on qdist( ) quan$le func$on rdist( ) random deviates Examples Normal dnorm, pnorm, qnorm, rnorm Binomial dbinom, pbinom, … Poisson dpois, … > pnorm(0) 0.05 > qnorm(0.9) 1.28 > rnorm(100) vector of length 100
- 21. Func$ons for Probability Distribu$ons distribu?on dist suffix in R How to find the func?ons for Beta -‐beta lognormal distribu?on? Binomial -‐binom Cauchy -‐cauchy 1) Use the double ques$on mark Chisquare -‐chisq Exponen?al -‐exp ‘??’ to search F -‐f > ??lognormal Gamma -‐gamma Geometric -‐geom 2) Then iden$fy the package Hypergeometric -‐hyper > ?Lognormal Logis?c -‐logis Lognormal -‐lnorm Nega?ve Binomial -‐nbinom 3) Discover the dist func$ons Normal -‐norm dlnorm, plnorm, qlnorm, Poisson -‐pois rlnorm Student t -‐t Uniform -‐unif Tukey -‐tukey Weibull -‐weib Wilcoxon -‐wilcox
- 22. Try It! #2 Numerical Simula$on • simulate 1m drivers from which we expect 4 claims > numclaims <- rpois(n, lambda) (hint: use ?rpois to understand the parameters) • verify the mean & variance are reasonable > mean(numclaims) > var(numclaims) • visualize the distribu$on of claim counts > hist(numclaims)
- 23. Gehng Data In -‐ from Files > Insurance <- read.csv(“Insurance.csv”,header=TRUE) from Databases > con <- dbConnect(driver,user,password,host,dbname) > Insurance <- dbSendQuery(con, “SELECT * FROM claims”) from the Web > con <- url('http://labs.dataspora.com/test.txt') > Insurance <- read.csv(con, header=TRUE) from R data objects > load(‘Insurance.Rda’)
- 24. Gehng Data Out • to Files write.csv(Insurance,file=“Insurance.csv”) • to Databases con <- dbConnect(dbdriver,user,password,host,dbname) dbWriteTable(con, “Insurance”, Insurance) to R Objects save(Insurance, file=“Insurance.Rda”)
- 25. Naviga$ng within the R environment • lis$ng all variables > ls() • examining a variable ‘x’ > str(x) > head(x) > tail(x) > class(x) • removing variables > rm(x) > rm(list=ls()) # remove everything
- 26. Try It! #3 Data Processing • load data & view it library(MASS) head(Insurance) ## the first 7 rows dim(Insurance) ## number of rows & columns • write it out write.csv(Insurance,file=“Insurance.csv”, row.names=FALSE) getwd() ## where am I? • view it in Excel, make a change, save it remove the first district • load it back in to R & plot it Insurance <- read.csv(file=“Insurance.csv”) plot(Claims/Holders ~ Age, data=Insurance)
- 27. A Swiss-‐Army Knife for Data
- 28. A Swiss-‐Army Knife for Data • Indexing • Three ways to index into a data frame – array of integer indices – array of character names – array of logical Booleans • Examples: df[1:3,] df[c(“New York”, “Chicago”),] df[c(TRUE,FALSE,TRUE,TRUE),] df[df$city == “New York”,]
- 29. A Swiss-‐Army Knife for Data • subset – extract subsets mee$ng some criteria subset(Insurance, District==1) subset(Insurance, Claims < 20) • transform – add or alter a column of a data frame transform(Insurance, Propensity=Claims/Holders) • cut – cut a con$nuous value into groups cut(Insurance$Claims, breaks=c(-1,100,Inf), labels=c('lo','hi')) • Put it all together: create a new, transformed data frame transform(subset(Insurance, District==1), ClaimLevel=cut(Claims, breaks=c(-1,100,Inf), labels=c(‘lo’,’hi’)))
- 30. A Swiss-‐Army Knife for Data • sqldf – a library that allows you to query R data frames as if they were SQL tables. Par$cularly useful for aggrega$ons. library(sqldf) sqldf('select country, sum(revenue) revenue FROM sales GROUP BY country') country revenue 1 FR 307.1157 2 UK 280.6382 3 USA 304.6860
- 31. A Sta$s$cal Modeler • R’s has a powerful modeling syntax • Models are specified with formulae, like y ~ x growth ~ sun + water model rela$onships between con$nuous and categorical variables. • Models are also guide the visualiza$on of rela$onships in a graphical form
- 32. A Sta$s$cal Modeler • Linear model m <- lm(Claims/Holders ~ Age, data=Insurance) • Examine it summary(m) • Plot it plot(m)
- 33. A Sta$s$cal Modeler • Logis$c model m <- glm(Age ~ Claims/Holders, data=Insurance, family=binomial(“logit”)) • Examine it summary(m) • Plot it plot(m)
- 34. Try It! #4 Sta$s$cal Modeling • fit a linear model m <- lm(Claims/Holders ~ Age + 0, data=Insurance) • examine it summary(m) • plot it plot(m)
- 35. Visualiza$on: Mul$variate Barplot library(ggplot2) qplot(Group, Claims/Holders, data=Insurance, geom="bar", stat='identity', position="dodge", facets=District ~ ., fill=Age)
- 36. Visualiza$on: Boxplots library(ggplot2) library(lattice) qplot(Age, Claims/Holders, bwplot(Claims/Holders ~ Age, data=Insurance, data=Insurance) geom="boxplot“)
- 37. Visualiza$on: Histograms library(ggplot2) library(lattice) qplot(Claims/Holders, densityplot(~ Claims/Holders | Age, data=Insurance, data=Insurance, layout=c(4,1) facets=Age ~ ., geom="density")
- 38. Try It! #5 Data Visualiza$on • simple line chart > x <- 1:10 > y <- x^2 > plot(y ~ x) • box plot > library(lattice) > boxplot(Claims/Holders ~ Age, data=Insurance) • visualize a linear fit > abline(0,1)
- 39. Gehng Help with R Help within R itself for a func?on > help(func) > ?func For a topic > help.search(topic) > ??topic • search.r-‐project.org • Google Code Search www.google.com/codesearch • Stack Overflow hsp://stackoverflow.com/tags/R • R-‐help list hsp://www.r-‐project.org/pos$ng-‐guide.html
- 40. Six Indispensable Books on R Learning R Data Manipula?on Visualiza?on: la-ce & ggplot2 Sta?s?cal Modeling
- 41. Extending R with Packages Over one thousand user-‐contributed packages are available on CRAN – the Comprehensive R Archive Network hsp://cran.r-‐project.org Install a package from the command-‐line > install.packages(‘actuar’) Install a package from the GUI menu “Packages”--> “Install packages(s)”
- 43. lahce = trellis (source: hsp://lmdvr.r-‐forge.r-‐project.org )
- 44. list of lahce func$ons densityplot(~ speed | type, data=pitch)
- 45. Visualiza?on with ggplot2
- 46. ggplot2 = grammar of graphics
- 47. ggplot2 = grammar of graphics
- 48. Visualizing 50,000 Diamonds with ggplot2
- 49. qplot(carat, price, data = diamonds)
- 50. qplot(log(carat), log(price), data = diamonds)
- 51. qplot(log(carat), log(price), data = diamonds, alpha = I(1/20))
- 52. qplot(log(carat), log(price), data = diamonds, alpha = I(1/20), colour=color)
- 53. qplot(log(carat), log(price), data = diamonds, alpha=I(1/20)) + facet_grid(. ~ color)
- 54. qplot(color, price/carat, qplot(color, price/carat, data = diamonds, data = diamonds, alpha = I(1/20), geom=“boxplot”) geom=“jitter”)
- 56. (live demo)
- 57. visualizing six dimensions of MLB pitches with ggplot2
- 58. Demo with MLB Gameday Data Code, data, and instructions at: http://metamx-mdriscol-adhoc.s3.amazonaws.com/gameday/README.R