A short list of some useful R commands

help() #give help regarding a command, e.g. help(hist)

c() #concatenate objects, e.g. x = c(3,5,8,9) or y = c(”Jack”,”Queen”,”King”)
1:19 #create a sequence of integers from 1 to 19
(…) #give arguments to a function, e.g. sum(x), or help(hist)
[…] #select elements from a vector or list, e.g. x[2] gives 5, x[c(2,4)] gives 5 9 for x as above
matrix() #fill in (by row) the values from y in a matrix of 4 rows and 3 columns by giving
#m = matrix(y,4,3,byrow=T)
dim() #gives the number of rows and the number of columns of a matrix, or a data frame
head() #gives the first 6 rows of a large matrix, or data frame
tail() #gives the last 6 rows of a large matrix, or data frame
m[ ,3] #gives the 3rd column of the matrix m
m[2, ] #gives the 2nd row of the matrix m
= or <- #assign something to a variable, e.g. x = c(”a”,”b”,”b”,”e”)
== #ask whether two things are equal, e.g. x = c(3,5,6,3) and then x == 3 gives T F F T
#Then y[x == 3] gives those entries of y where x equals 3, i.e. the 1st and 4th entry of y
< #ask whether x is smaller than y, e.g. x < 6 in the example above gives True True False True
> #ask whether x is larger than y
& #logical „and‟
| #logical „or‟
sum() #get the sum of the values in x by sum(x)
mean() #get the mean of the values in x by mean(x)
median() #get the median of the values in x by median(x)
sd() #get the standard deviation of the values in x
var() #get the variance of the values in x
IQR() #get the IQR of the values in x
summary() #get the summary statistics of a single variable, or of all variables in a data frame
round() #round values in x to 3 decimal places by round(x,3)
sort() #sort the values in x by giving sort(x)
unique() #get the non-duplicate values from a list, e.g. x = c(3,5,7,2,3,5,9,3) and then
unique(x) #gives 3 5 7 2 9
length(x) #gives the length of the vector x, which is 8
hist() #create a histogram of the values in x by hist(x)
stem() #create a stem and leaf plot of the values in x by stem(x)
boxplot() #create a boxplot of the values in x by boxplot(x)
plot() #scatterplot of x vs. y by plot(x,y); for more parameters see help(plot.default)
cor() #gives the linear correlation coefficient
lm() #fit a least squares regression of y (response) on x (predictor) by fit = lm(y~x)
names() #get or set the names of elements in a R object. E.g. names(fit) will give the names of the R
#object named “fit”, or
#get or set the names of variables in a data frame.
fit$coef #gives the least squares coefficients from the fit above, i.e. intercept and slope
fit$fitted #gives the fitted values for the regression fitted above
fit$residuals #gives the residuals for the regression fitted above
lines() #add a (regression) line to a plot by lines(x,fit$fitted)
abline() #add a straight line to a scatterplot
points() #add additional points (different plotting character) to a plot by points(x,y2,pch=5)
scan() #read data for one variable from a text file, e.g. y = scan(”ping.dat”)
#Don‟t forget to change to the appropriate directory first
read.table() #read spreadsheet data (i.e. more than one variable) from a text file
table() #frequency counts of entries, ideally the entries are factors(although
#it works with integers or even reals)
write() #write the values of a variable y in a file data.txt by write(y,file=”data.txt”)
log() #natural logarithm (i.e. base e)
log10() #logarithm to base 10
seq() #create a sequence of integers from 2 to 11 by increment 3 with seq(2,11,by=3)
rep() #repeat n times the value x, e.g. rep(2,5) gives 2 2 2 2 2
getwd() #get the current working directory.
setwd() #change the directory to. E.g. setwd("c:/RESEARCH/GENE.project/Chunks/")
dir() #list files in the current working directory
search() #searching through reachable datasets and packages
library() #link to a downloaded R package to the current R session. E.g. library(Biostrings) link to the
#R package #called “Biostrings” which you had downloaded earlier onto your laptop

Input and Display

load("c:/RData/pennstate1.RData") #load a R data frame

read.csv(filename="c:/stat251/ui.csv",header=T) #read .csv file with labels in first row
x=c(1,2,4,8,16) #create a data vector with specified elements
y=c(1:10) #create a data vector with elements 1-10
vect=c(x,y) #combine them into one vector of length 2n
mat=cbind(x,y) #combine them into a n x 2 matrix
mat[4,2] #display the 4th row and the 2nd column
mat[3,] #display the 3rd row
mat[,2] #display the 2nd column
subset(dataset,logical) #those objects meeting a logical criterion
subset(data.df,select=variables,logical) #get those objects from a data frame that meet a
#logical criterion
data.df[data.df=logical] #yet another way to get a subset
x[order(x$B),] #sort a dataframe by the order of the elements in B
x[rev(order(x$B)),] #sort the dataframe in reverse order

Moving Around

ls() #list the R objects in the current workspace

rm(x) #remove x from the workspace
rm(list=ls()) #remove all the variables from the workspace
attach(mat) #make the names of the variables in the matrix or data frame
#available in the workspace
detach(mat) #releases the names
new=old[,-n] #drop the nth column
new=old[-n,] #drop the nth row
new=subset(old,logical) #select those cases that meet the logical condition
complete = subset(data.df,complete.cases(data.df)) #find those cases with no missing values
new=old[n1:n2,n3:n4] #select the n1 through n2 rows of variables n3 through n4)

Data Manipulation

x.df=data.frame(x1,x2,x3 ...) #combine different kinds of data into a data frame

scale() #converts a data frame to standardized scores
round(x,n) #rounds the values of x to n decimal places
ceiling(x) #vector x of smallest integers > x
floor(x) #vector x of largest interger < x
as.integer(x) #truncates real x to integers (compare to round(x,0)
as.integer(x < cutpoint) #vector x of 0 if less than cutpoint, 1 if greater than cutpoint)
factor(ifelse(a < cutpoint, "Neg", "Pos")) #is another way to dichotomize and to make a factor for analysis
transform(data.df,variable names = some operation) #can be part of a set up for a data set

Statistical Tests

binom.test()
prop.test() #perform test with proportion(s)
t.test() #perform t test
chisq.test() #perform Chi-square test
pairwise.t.test()
power.anova.test()
power.t.test()
aov()
anova()
TukeyHSD()
kruskal.test()

Distributions

sample(x, size, replace = FALSE, prob = NULL) # take a simple random sample of size n from the
# population x with or without replacement
rbinom(n,size,p)
pbinom()
qbinom()
dbinom()

rnorm(n,mean,sd) #randomly generate n numbers from a Normal distribution with the specific mean and sd
pnorm() #find probability (area under curve) of a Normal(10,3^2) distribution to the left
#of 8,i.e. P(X <= 8), by pnorm(8,mean=10,sd=3)
qnorm() #find quantity or value x such that area under Normal(10,3^2) curve and to the left
#of x equals 0.25 by qnorm(0.25,mean=10,sd=3)
rt()
pt()
qt()

runif(n,lower,upper)
punif()
qunif()