R
R is a programming language and software environment for statistical computing and graphics supported by the R Foundation for Statistical Computing.
Links
Tutorials
- Input data into R
- Data types in R
- Basic Operations and Numerical Descriptions
Examples
Assign values
> a=16 > b<-1/3
Print values
> a
Get all variables you filled so far
> ls()
Read values into a vector
> myVector <- c(3,5,7,9) > myVector [1] 3 5 7 9
Get 3. element
> myVector[3] [1] 7
Get type of vector
> myVector[0] numeric(0)
Get Vector with this size and every value is 0
a <- numeric(10)
Get an overview of the data in a vector
> summary(myVector) Min. 1st Qu. Median Mean 3rd Qu. Max. 3.0 4.5 6.0 6.0 7.5 9.0
For more than one columns, get summary only for column "Clicks"
> summary(myOtherVector$Clicks)
Add 1 to any element in the vector
> myVector [1] 3 5 7 9 > myVector<-myVector+1 > myVector [1] 4 6 8 10
Watch out if vectors have a different size!
> a=c(1,2,3,4) > b=c(5,6) > a+b [1] 6 8 8 10
Calculate
> b=sqrt(16)
> e=exp(1) > e [1] 2.718282
> log(e) [1] 1
Mean
> mean(myVector) [1] 7
> var(myVector) [1] 6.666667
> round(myVector, digits=2)
Sum
> sum(myVector) [1] 28
> sort(question1,decreasing = TRUE) [1] "Weekly" "Weekly" "Sometimes" "Sometimes" "Sometimes" "Sometimes" "Once a year" "Never"
> min(question1) [1] "Never"
> max(question1) [1] "Weekly"
Filter Only smaller 5
> myValues<-c(1,8,2,4,7,1,2,3) > myValues[myValues<5] [1] 1 2 4 1 2 3
> myValues[myValues==2 | myValues==1] [1] 1 2 1 2
Read Data from CSV file
> myCSVFile <- read.csv(file="/tmp/myFile.csv",head=TRUE,sep=",")
Get help on a command
> help(read.csv)
File commands
> dir() > getwd()
Columns may have names, get all the names
> names(myCSVFile)
Get values from a column by name (column has name "Clicks")
> myCSVFile$Clicks
Get all column and all row names
> attributes(myCSVFile)
Strings
> s <- "Hello World"
Factors Sometimes columns do not contain numbers but names or labels of a discrete set of possible values. For example any row might belong to group A, B or C so you have a column Group and any row has on of those labels in it. R calls such a value a Factor. If your labels are numbers (e.g. 1,2 or 3) you can tell R that they are Factors.
> myCSVFile$Reviews<-factor(myCSVFile$Reviews)
Data Frames Data Frames can group serveral different variables into one object
myFrame <- data.frame(A=a,B=b)
Logical
> spock=5>2 > spock
[1] TRUE
Matrix
> myMatrix=matrix(c(4,3,2,5,6,7,8,9,0),ncol=3,byrow=TRUE) > myMatrix [,1] [,2] [,3] [1,] 4 3 2 [2,] 5 6 7 [3,] 8 9 0
> colnames(myMatrix) <- c("A","B","C")
> myMatrix
A B C
[1,] 4 3 2
[2,] 5 6 7
[3,] 8 9 0
Tables Get some factors and a table to find out how often the different values appear
> people<-factor(c("Smoker", "NonSmoker", "NonSmoker", "Smoker", "Smoker", "Smoker"))
> myTable<-table(people)
> myTable
people
NonSmoker Smoker
2 4
A matrix with named columns and rows may also be turned into a table
> myMatrix=matrix(c(4,3,2),ncol=3,byrow=TRUE)
> colnames(myMatrix) <- c("A","B","C")
> rownames(myMatrix) <- c("R1")
> myTable<-as.table(myMatrix)
> myTable
A B C
R1 4 3 2
Two Way Tables
Assume you asked 8 people 2 questions. This is how a table will show you how often a person who replied with a given answer to the first question replied to the second question
> question1<-c("Sometimes","Sometimes","Never","Weekly","Weekly","Sometimes","Sometimes","Once a
year")
> question2<-c("Maybe","Maybe","Yes","Maybe","Maybe","No","Yes","No")
> myTable<-table(question1,question2)
> myTable
question2
question1 Maybe No Yes
Never 0 0 1
Once a year 0 1 0
Sometimes 2 1 1
Weekly 2 0 0
Probability
Plotting
Get linear regression model for y=f(x)
- https://en.wikipedia.org/wiki/R_%28programming_language%29#Examples
- http://www.cyclismo.org/tutorial/R/linearLeastSquares.html
> year <- c(2000 , 2001 , 2002 , 2003 , 2004) > rate <- c(9.34 , 8.50 , 7.62 , 6.93 , 6.60)
> fit <- lm(rate ~ year)
> plot(year,rate) > abline(fit) > plot(fit)
Demo data There is some demo data included
> ?mtcars > mtcars mpg cyl disp hp drat wt qsec vs am gear carb Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 ...
Correlation Get test data
> myData<-with(mtcars, data.frame(mpg, hp, wt)) > summary(myData) mpg hp wt Min. :10.40 Min. : 52.0 Min. :1.513 1st Qu.:15.43 1st Qu.: 96.5 1st Qu.:2.581 Median :19.20 Median :123.0 Median :3.325 Mean :20.09 Mean :146.7 Mean :3.217 3rd Qu.:22.80 3rd Qu.:180.0 3rd Qu.:3.610 Max. :33.90 Max. :335.0 Max. :5.424
Packages
> library(reshape)
Error in library(reshape) : there is no package called ‘reshape’
> install.packages("reshape")
Installing package into ‘/usr/local/lib/R/site-library’
> library(reshape2)
> install.packages('ggplot2', dep = TRUE)
ggplot2 : Quick correlation matrix heatmap http://www.sthda.com/english/wiki/ggplot2-quick-correlation-matrix-heatmap-r-software-and-data-visualization
Load test data
> myData<-with(mtcars, data.frame(mpg, hp, wt))
Calculate Correlation
> myCorrelation=round(cor(myData),2) > myCorrelation mpg hp wt mpg 1.00 -0.78 -0.87 hp -0.78 1.00 0.66 wt -0.87 0.66 1.00
Filter out the upper triangle
> upper.tri(myCorrelation) [,1] [,2] [,3] [1,] FALSE TRUE TRUE [2,] FALSE FALSE TRUE [3,] FALSE FALSE FALSE
Overwrite it with NA
> myCorrelation[upper.tri(myCorrelation)] <- NA > myCorrelation mpg hp wt mpg 1.00 NA NA hp -0.78 1.00 NA wt -0.87 0.66 1
Only one correlation per line
> library(reshape2) > myDataMelted=melt(myCorrelation) > myDataMelted Var1 Var2 value 1 mpg mpg 1.00 2 hp mpg -0.78 3 wt mpg -0.87 4 mpg hp NA 5 hp hp 1.00 6 wt hp 0.66 7 mpg wt NA 8 hp wt NA 9 wt wt 1.00
Filter out the NA
> myDataMelted=na.omit(myDataMelted) > myDataMelted Var1 Var2 value 1 mpg mpg 1.00 2 hp mpg -0.78 3 wt mpg -0.87 5 hp hp 1.00 6 wt hp 0.66 9 wt wt 1.00
Plot it
> library(ggplot2) > ggplot(data = myDataMelted, aes(x=Var1, y=Var2, fill=value)) + geom_tile()
Bigger example, fancier
> library(reshape2) > myData<-with(mtcars, data.frame(mpg, cyl, disp, hp, drat, wt, qsec, vs, am, gear, carb)) > myCorrelation=round(cor(myData),2) > hc=hclust(as.dist(1-myCorrelation)/2) > myCorrelationSorted<-myCorrelation[hc$order, hc$order] > myCorrelationSorted[lower.tri(myCorrelation)] <- NA > data<-na.omit(melt(myCorrelationSorted))
> library(ggplot2) > plotMe<-ggplot(data, aes(Var2, Var1, fill = value))+ geom_tile(color = "white")+ scale_fill_gradient2(low = "blue", high = "red", mid = "white", midpoint = 0, limit = c(-1,1), name="PearsonnCorrelation") + theme_minimal()+ theme(axis.text.x = element_text(angle = 45, vjust = 1, size = 12, hjust = 1))+coord_fixed() > print(plotMe)
> plotMe + geom_text(aes(Var2, Var1, label = value), color = "black", size = 4) + theme( axis.title.x = element_blank(), axis.title.y = element_blank(), panel.grid.major = element_blank(), panel.border = element_blank(), panel.background = element_blank(), axis.ticks = element_blank(), legend.justification = c(1, 0), legend.position = c(0.6, 0.7), legend.direction = "horizontal")+ guides(fill = guide_colorbar(barwidth = 7, barheight = 1, title.position = "top", title.hjust = 0.5))
http://www.peterhaschke.com/r/2013/04/23/CorrelationMatrix.html
http://jeromyanglim.blogspot.de/2012/05/example-reproducile-report-using-r.html