R commands basics

we are on day 5 of the MSU NGS course. This morning, Ian Dworkin introduced some basic R.
I found it refreshing and put a gist below.
Pick one language, and learn it well!
pick up a dataset, and play with it!  Happy coding!
By the way, the food here at KBS is amazing, I am gaining weight :)

	#2014 MSU NGS R basics tutorial
	#http://angus.readthedocs.org/en/2014/R_Introductory_tutorial_2014.html
	#https://github.com/jrherr/quick_basic_R_tutorial/blob/master/R_tutorial.md
	#pick one language, and learn it well!
	#pick up a dataset, play with it!
	#object-oriented programming
	#functional programming
	#deal with big data in R: (R holds all the data in memory)
	#http://theodi.org/blog/fig-data-11-tips-how-handle-big-data-r-and-1-bad-pun
	#http://r-pbd.org/
	#packages: plyr, dplyr, ggplot2, reshape2, data.table (fread function)
	# commands start here!!
	q() # quit R
	getwd() # get working directory
	setwd() # set working directory
	y<- 2 # assign a variable
	x<- 3
	x + y # treat it as a calculator
	x * y
	x/y
	x %% y
	x == 3 # equal sign, will reture a logical vector: True or False
	# in R, True and False have numerical values: True resolves to 1 , False resolves to 0
	# exponents ** or ^
	2**2 # returns 4
	2^2 # returns 4
	log(2.7) # natural log returns 0.99325
	log(4,2) # returns 2
	a<- c(2,3,6,8) # assign a vector use c denotes concatenate
	b<- c(3,5,6,7)
	a + b #
	a * b #
	# when length of a and b are different, R will recycle the longer one and gives a warning
	length(a) # length of a, returns 4
	new_varaible <- c(a,b) # concatenate two variables
	crap<- rep(1:100) # index starts at 1
	rm (crap) # remove this variable
	?lm # get help for linear regression model function
	# simple functions
	a<- c(2,3,6,8)
	mean(a)
	sum(a)
	var(a)
	b<- c(3,5,6,7)
	cor(a,b) # pearson correlation for two vectors
	m<- cbind(a,b) # column bind the vector to a matrix
	m
	#> m
	# a b
	# [1,] 2 3
	# [2,] 3 5
	# [3,] 6 6
	# [4,] 8 7
	cor(m) # pearson correlation for columns of a matrix
	cor(m, method="spearman") # spearman correlation of columns of a matrix
	?cor
	mode (a) # numeric
	class (a) # numeric
	class (m) # matrix
	typeof(m)
	str(m) # structure of m, try it out in your R console
	dim(m) # dimension of m: 4 2
	nrow(m) # number of rows 4
	ncol(m) # number of columns 2
	length(m) # 8
	is.matrix(m) # True
	# create a matrix from scratch
	#> m1<- matrix(1:12,3,4)
	#> m1
	# [,1] [,2] [,3] [,4]
	#[1,] 1 4 7 10
	#[2,] 2 5 8 11
	#[3,] 3 6 9 12
	# strings
	cities<- c("E.lansing", "Gainesville", "Shanghai", "Yichun")
	class(cities)
	#[1] "character"
	length(cities) # 4 cities in the vector
	nchar(cities) # number of characters for each city
	#[1] 9 11 8 6
	sum(nchar(cities))
	#[1] 34
	rivers<- c("Red Cedar", "swamp", "Huang Pu", "Long He")
	cities_rivers<- cbind (cities,rivers)
	cities_rivers
	# cities rivers
	#[1,] "E.lansing" "Red Cedar"
	#[2,] "Gainesville" "swamp"
	#[3,] "Shanghai" "Huang Pu"
	#[4,] "Yichun" "Long He"
	class(cities_rivers) # matrix
	mode (citeis_rivers) # character
	model_1<- y ~ x1 + x2 + x1:x2
	model_1
	#> class(model_1)
	#[1] "formula"
	counts_transcript_a <- c(250, 157, 155, 300, 125, 100, 153, 175)
	genotype <- gl(n=2, k=4, labels = c("wild_type", "mutant"))
	#> genotype
	#[1] wild_type wild_type wild_type wild_type mutant
	#[6] mutant mutant mutant
	#Levels: wild_type mutant
	#alternative to gl function, one can
	genotype1<- factor(rep(c("wild_type","mutant"),each=4))
	#> genotype1
	#[1] wild_type wild_type wild_type wild_type mutant
	#[6] mutant mutant mutant
	#Levels: mutant wild_type
	#notice the use of the "each" argument
	genotype1<- factor(rep(c("wild_type","mutant"),4))
	#> genotype1
	#[1] wild_type mutant wild_type mutant wild_type
	#[6] mutant wild_type mutant
	#Levels: mutant wild_type
	#also, notice that the levels are different with that generated by gl function
	#we want the wild_type to be the base level. Instead, do:
	genotype1<- factor(rep(c("wild_type","mutant"),each=4), levels=c("wild_type","mutant"))
	#> genotype1
	#[1] wild_type wild_type wild_type wild_type mutant mutant mutant mutant
	#Levels: wild_type mutant
	?relevel # try it also
	expression_data <- data.frame(counts_transcript_a, genotype)
	#> expression_data
	# counts_transcript_a genotype
	#1 250 wild_type
	#2 157 wild_type
	#3 155 wild_type
	#4 300 wild_type
	#5 125 mutant
	#6 100 mutant
	#7 153 mutant
	#8 175 mutant
	expression_data$counts_transcript_a # access a column of the dataframe
	ls() # objects in the enviroment
	rm(list=ls()) # remove all the objects in the enviroment
	### write functions
	StdErr <- function(vector) {
	sd(vector)/sqrt(length(vector))
	}
	CoefVar<- function(vector){
	sd(vector)/mean(vector)
	}
	# apply families http://nsaunders.wordpress.com/2010/08/20/a-brief-introduction-to-apply-in-r/
	# with
	> with(expression_data, tapply(X=counts_transcript_a, INDEX=genotype, FUN=mean))
	wild_type mutant
	215.50 138.25
	# some commonly used functions, try ?to understand them
	head() # print the first 6 lines, different with linux (default 10 lines)
	table()
	rownames()
	colnames()
	nrow()
	ncol()
	by()
	with()
	rowSums()
	rowMeans()
	summary()
	# construct sequences
	one_to_20<- 1:20
	twenty_to_1<- 20:1
	seq1<- seq(from =1, to = 20, by 0.5)
	# or seq1<- seq(1,20,0.5)
	# repeat numbers
	many_2<- rep(2, times=20)
	many_a<- rep("a", times=20)
	seq_rep<- rep(1:10, times=2)
	rep_3_times<- rep(c(1,2,3), times=3)
	# different
	rep_each_3_times<- rep(c(1,2,3), each=3)
	# to do: subsetting for vectors and matrix
	# R mark-down

view raw ngs2014_R_basics.r hosted with ❤ by GitHub