Difference between revisions of "R tutorial"

input prompt

>

> help(rnorm)
>
> ?rnorm
>
> ?binom     
No documentation for 'binom' in specified packages and libraries:
you could try '??binom'
> ??binom
>
> ?Binomial
>
> ?apropos     
> apropos("med")   # all functions that contain the string "med"
> apropos("^med")  # all functions that begin with the string 
> apropos("med$")  # all functions that end with the string
> ?"+"
> ?"~"
> ?"["
> ?"%in%"
>
> ?var
> getwd()
[1] "/Users/steipe/R"
> setwd("~") # Note: ~ is the "tilde" - the squiggly line - not the straight hyphen
> getwd()
[1] "/Users/steipe"
> setwd("~/../chen")  
> getwd()
[1] "/Users/chen"
> setwd("/Users/steipe/abc/R_samples")  
> getwd()
[1] "Users/steipe/abc/R_samples"
> ?Startup
> ls() 
character(0)
>
> a <- 1; b <-2; eps <- 0.0001
> ls() 
[1] "a"   "b"   "eps"
>
> rm(a) 
> ls()
[1] "b"   "eps"
>
rm(list= ls()) 
> ls() 
character(0)
>
> library()
> search() 
 [1] ".GlobalEnv"        "tools:RGUI"        "package:stats"     "package:graphics" 
 [5] "package:grDevices" "package:utils"     "package:datasets"  "package:methods"  
 [9] "Autoloads"         "package:base"
> ?vignette
> ??install
> ?install.packages
> install.packages("seqinr")   # Note: quoted string!
also installing the dependency ‘ade4’

trying URL 'https://cran.rstudio.com/bin/macosx/mavericks/contrib/3.2/ade4_1.7-2.tgz'
Content type 'application/x-gzip' length 3365088 bytes (3.2 MB)
==================================================
downloaded 3.2 MB

trying URL 'https://cran.rstudio.com/bin/macosx/mavericks/contrib/3.2/seqinr_3.1-3.tgz'
Content type 'application/x-gzip' length 2462893 bytes (2.3 MB)
==================================================
downloaded 2.3 MB

The downloaded binary packages are in
	/var/folders/mx/ld0hdst54jjf11hpcjh8snfr0000gn/T//Rtmpsy5GMx/downloaded_packages

> library(seqinr)     # This refers to an installed page. No quotes here...
> library(help="seqinr")
> ls("package:seqinr")
  [1] "a"                       "aaa"                     "AAstat"                 
  [4] "acnucclose"              "acnucopen"               "al2bp"                  
     [...]
[205] "where.is.this.acc"       "words"                   "words.pos"              
[208] "write.fasta"             "zscore"                 
> ?a
> a("Tyr")
[1] "Y"
> choosebank()
 [1] "genbank"       "embl"          "emblwgs"       "swissprot"     "ensembl"      
    [...]
 [31] "refseqViruses"
?data
data(package="seqinr")   # list the available data
data(aaindex)            # load ''aaindex''
?aaindex                 # what is this?
aaindex$FASG890101       # two of the indices ...
aaindex$PONJ960101

# Lets use the data: plot amino acid codes by hydrophobicity and volume

plot(aaindex$FASG890101$I,
     aaindex$PONJ960101$I, 
     xlab="hydrophobicity", ylab="volume", type="n")
text(aaindex$FASG890101$I, 
     aaindex$PONJ960101$I, 
     labels=a(names(aaindex$FASG890101$I)))
choosebank("swissprot")
mySeq <- query("mySeq", "N=MBP1_YEAST")
mbp1 <- getSequence(mySeq)
closebank()
x <- AAstat(mbp1[[1]])
barplot(sort(x$Compo))
if (!require(seqinr, quietly=TRUE)) {
    install.packages("seqinr")
    library(seqinr)
}
if (!require(sos, quietly=TRUE)) {
    install.packages("sos")
    library(sos)
}

findFn("moving average")
# sample script:
# define a vector
a <- c(1, 1, 2, 3, 5, 8, 13)
# list its contents
a
# calculate the mean of its values
mean(a)
source("intro.R")
print(a)

print(mean(a))
?sink
cat("vector: ", a, " (mean:", mean(a), ")\n")
5
5 + 3
5 + 1 / 2
3 * 2 + 1
3 * (2 + 1)
2^3 # Exponentiation
8 ^ (1/3) # Third root via exponentiation
7 %% 2  # Modulo operation (remainder of integer division)
7 %/% 2 # Integer division
cos(pi) #"pi" is a predefined constant.
sin(pi) # Note the rounding error. This number is not really different from zero.
sin(30 * pi/180) # Trigonometric functions use radians as their argument - this conversion calculates sin(30 degrees)
exp(1) # "e" is not predefined, but easy to calculate.
log(exp(1)) # functions can be arguments to functions - they are evaluated from the inside out.
log(10000) / log(10) # log() calculates natural logarithms; convert to any base by dividing by the log of the base. Here: log to base 10.
exp(complex(r=0, i=pi)) #Euler's identity
complex(1)
complex(4)
complex(1, 2) # imaginary part missing: if it's missing it defaults to zero
complex(1, 2, 3) # one complex number
complex(4, 2, 3) # four complex numbers
complex(real = 0, imaginary = pi) # defining values via named parameters
complex(imaginary = pi, real = 0) # same thing - if names are used, order is not important
complex(re = 0, im = pi) # names can be abbreviated ...
complex(r = 0, i = pi)   # ... to the shortest string that is unique among the named parameters.
                         # Use this feature with discretion to keep your code readable.
complex(i = pi, 1, 0) # Think: what have I done here? Why does this work?
exp(complex(i = pi, 1, 0)) # (The complex number above is the same as in Euler's identity.)
?make.names
?reserved
a <- 5
a
a + 3
b <- 8
b
a + b
a == b # not assignment: equality test
a != b # not equal
a < b  # less than
# I don't like...
col <- c("red", "grey")
hist(rnorm(200), col=col)

# I prefer, for example...
rgStripes <- c("red", "grey")
hist(rnorm(200), col=rgStripes)
info <- function(x) {
    print(x)  
    cat("str:    ")                
    str(x)  
    cat("mode:   ", mode(x), "\n")
    cat("typeof: ", typeof(x), "\n")
    cat("class:  ", class(x), "\n")
    # if there are attributes, print them too
    if (! is.null(attributes(x))) {
        cat("attributes:\n")
        print(attributes(x))
    }
}
info( 3 > 5 ) # Note: a > 5 is a logical expression, its value is FALSE.
info( 3 < 5 ) 

info( 3.0 )  # Double precision floating point number
info( 3.0e0 )  # Same value, exponential notation

info( 3 )  # Note: numbers are double precision floats by default.
info( as.integer(3) )  # If we really want an integer, we must coerce to type integer.

info( as.character(3) )  # Forcing the number to be interpreted as a character.

# More coercions. For each of these, first think what result you would expect:
info( as.numeric("3") )   # character as numeric
info( as.numeric("3.141592653") )   # string as numeric
info( as.numeric(pi) )   # not a string, but a predefined constant
info( as.numeric("pi") )   # another string as numeric. Ooops - what went wrong?

info( as.complex(1) )  
info( as.logical(0) )  
info( as.logical(1) )  
info( as.logical(-1) )  
info( as.logical(pi) )      # any non-zero number is TRUE ...
info( as.logical("pie") )   # ... but not non-numeric types. NA means "Not Available".

info( as.character(pi) )

info( Inf )
info( NaN )
info( NA )
info( NULL )
info( as.factor("M") )     # factor
info( Sys.time() )         # time
info( letters )            # inbuilt
info( 1:4 )                # numeric vector
info( matrix(1:4, nrow=2)) # numeric matrix
info( list(arabic = 1:3, roman = c("I", "II", "III")))
info( data.frame(arabic = 1:3, roman = c("I", "II", "III"), stringsAsFactors=FALSE))
info( a ~ b )              # a formula
info( info )               # the function itself
#Create a vector and list its contents and length:
f <- c(1, 1, 3, 5, 8, 13, 21)
f
length(f)

# Various ways to retrieve values from the vector.
f[1] # By index: "1" is first element. 
f[length(f)] # length() is the index of the last element.
1:4 # This is the range operator
f[1:4] # using the range operator (it generates a sequence and returns it in a vector)
f[4:1] # same thing, backwards
seq(from=2, to=6, by=2) # The seq() function is a flexible, generic way to generate sequences
seq(2, 6, 2) # Same thing: arguments in default order
f[seq(2, 6, 2)]

# since a scalar is a vector of length 1, does this work?
5[1]

# ...using an index vector with positive indices
a <- c(1, 3, 4, 1) # the elements of index vectors must be 
                   # valid indices of the target vector. 
                   # The index vector can be of any length.
f[a] # In this case, four elements are retrieved from f[]

# ...using an index vector with negative indices
a <- -(1:4) # If elements of index vectors are negative integers,
            # the corresponding elements are excluded.
f[a] # Here, the first four elements are omitted from f[]
f[-((length(f)-3):length(f))] # Here, the last four elements are omitted from f[]

# ...using a logical vector
f>4 # A logical expression operating on the target vector
    # returns a vector of logical elements. It has the
    # same length as the target vector.
f[f>4]; # We can use this logical vector to extract only
        # elements for which the logical expression evaluates as TRUE.
        # This is sometimes called "filtering".

# Example: extending the Fibonacci series for three steps. 
# Think: How does this work? What numbers are we adding here and why does the result end up in the vector?
f <- c(f, f[length(f)-1] + f[length(f)]); f 
f <- c(f, f[length(f)-1] + f[length(f)]); f 
f <- c(f, f[length(f)-1] + f[length(f)]); f 

# coercion: all elements of vectors must be of the same mode
c(1, 2.0, "3", TRUE)
[1] "1"    "2"    "3"    "TRUE"
f
f+1
f*2

# computing with two vectors of same length
a <- f[-1]; a # like f[], but omitting the first element
b <- f[1:(length(f)-1)]; b # like f[], but shortened by the least element
c <- a / b # the "golden ratio", phi (~1.61803 or (1+sqrt(5))/2 ), 
           # an irrational number, is approximated by the ratio of
           # two consecutive Fibonacci numbers.
c
abs(c - ((1+sqrt(5))/2)) # Calculating the error of the approximation, element by element
x <- 8; sample(6:x)
x <- 7; sample(6:x)
x <- 6; sample(6:x)  # Oi!

# also consider
x <- 6:8; seq(x)
x <- 6:7; seq(x)
x <- 6:6; seq(x)    # Oi vay!
safeSample <- function(x, size, ...) {
	# Replace the sample() function to ensure sampling from a single
	# value gives that value with probability p == 1.
        # Respect additional arguments if present.
    if (length(x) == 1 && is.numeric(x) && x > 0) {
    	if (missing(size)) size <- 1
        return(rep(x, size))
    } else {
        return(sample(x, size, ...))
    }
}
a <- 1:12; a
dim(a) <- c(2,6); a
dim(a) <- c(2,2,3); a
dim(a)    # returns a vector
dim(a)[3]  # only the third value of the vector
a <- 1:4
b <- 5:8
m1 <- rbind(a, b); m1   # difference between rbind() and cbind()
m2 <- cbind(a, b); m2
m <- cbind(m2, 9:12); m2
m[1,] # first row
m[,2] # second column
m[3,2] # element at row == 3, column == 2
m[3:4, 1:2] # submatrix: rows 3 to 4 and columns 1 to 2
pUC19 <- list(size=2686, marker="ampicillin", ori="ColE1", accession="L01397", BanI=c(235, 408, 550, 1647) )
pUC19[[1]]
pUC19[[2]]
pUC19$ori
pUC19$BanI[2]
Name	Size	Marker	Ori	Sites
pUC19	2686	Amp	ColE1	EcoRI, SacI, SmaI, BamHI, XbaI, PstI, HindIII
pBR322	4361	Amp, Tet	ColE1	EcoRI, ClaI, HindIII
pACYC184	4245	Tet, Cam	p15A	ClaI, HindIII

plasmidData <- read.table("plasmidData.tsv", sep="\t", header=TRUE, stringsAsFactors = FALSE)
plasmidData   # show what the data frame contains
pD2 <- edit(plasmidData)
> ?"["     # Note that you need quotation marks around the operator for this.
plasmidData[1, ]
plasmidData[2, ]

# we can extract more than one row by specifying
# the rows we want in a vector ...
plasmidData[c(1, 2), ]   

# ... this works in any order ...
plasmidData[c(3, 1), ]   

# ... and for any number of rows ...
plasmidData[c(1, 2, 1, 2, 1, 2), ]   

# Same for columns
plasmidData[ ,2 ]

# We can select rows and columns by name if a name has been defined...
plasmidData[,"Name"]
plasmidData$Name      # different syntax, same thing

# Watch this!
plasmidData$Name[plasmidData$Ori != "ColE1"]
# What happened here?
# plasmidData$Ori != "ColE1" is a logical expression, it gives a vector of TRUE/FALSE values
plasmidData$Ori != "ColE1"

# We insert this vector into the square brackets. R then returns all rows for
# which the vector is TRUE.

# In this way we can "filter" for values
plasmidData$Size > 3000
plasmidData$Name[plasmidData$Size > 3000]

# This principle is what we use when we want to "sort" an object
# by some value. The function order() is used to return values
# that are sorted. Remember this: not sort() but order().
order(plasmidData$Size)
plasmidData[order(plasmidData$Size), ]

# grep() matches substrings in strings 
grep("Tet", plasmidData$Marker)
plasmidData[grep("Tet", plasmidData$Marker), ]
plasmidData[grep("Tet", plasmidData$Marker), "Ori"]
x <- sample(1:10)
x
x[4] <- 99
x
x <- x[order(x)]
x
#defining the function:
myFunction <- function(myParameters) { 
	result <- doSomethingWith(myParameters)
	return(result)
}

# using the function:
myEpiphany <- myFunction(Arguments)
biCode <- function(s) { 
	substr(s, 4, 5) <- substr(strsplit(s,"\\s+")[[1]][2], 1, 2)
	return (toupper(substr(s, 1, 5)))
}

biCode("Homo sapiens")              # HOMSA
biCode("saccharomyces cerevisiae")  # SACCE
fibSeq <- function(n) { 
   if (n < 1) { return( c(0) ) }
   else if (n == 1) { return( c(1) ) }
   else if (n == 2) { return( c(1, 1) ) }
   else {
      v <- c(1, 1)
      for ( i in 3:n ) {
         v <- c(v, v[length(v)-1] + v[length(v)])
      }
      return( v )
   }
}
rollDice <- function(len=1, MIN=1, MAX=6) {
    v <- rep(0, len)
    for (i in 1:len) {
        x <- runif(1, min=MIN, max=MAX)
        x <- as.integer(x)
        v[i] <- x
    }
    return(v)
}
rollDice()
table(rollDice(1000))
debug(rollDice)
rollDice(10)
debugging in: rollDice(10)
debug at #1: {
    v <- rep(0, len)
    for (i in 1:len) {
        x <- runif(1, min = MIN, max = MAX)
        x <- as.integer(x)
    	v[i] <- x
    }
    return(v)
}
Browse[2]> 
debug at #2: v <- rep(0, len)
Browse[2]> 
debug at #3: for (i in 1:len) {
    x <- runif(1, min = MIN, max = MAX)
    x <- as.integer(x)
    v[i] <- x
}
Browse[2]> 
debug at #4: x <- runif(1, min = MIN, max = MAX)
Browse[2]> 
debug at #5: x <- as.integer(x)
Browse[2]> x   # Here we examine the current value of x
[1] 4.506351
Browse[2]> 
debug at #6: v[i] <- x
Browse[2]> 
debug at #4: x <- runif(1, min = MIN, max = MAX)
Browse[2]> v
[1] 4      # Aha: as.integer() truncates, but doesn't round!
Browse[2]> Q
undebug(rollDice)
rollDice <- function(len=1, MIN=1, MAX=6) {
    v <- rep(0, len)
    for (i in 1:len) {
    	x <- runif(1, min=MIN, max=MAX+1)
    	x <- as.integer(x)
    	v[i] <- x
    }
    return(v)
}
table(rollDice(1000))
# Disclaimer 1: this function would be better
# written as ...

rollDice <- function(len=1, MIN=1, MAX=6) {
	return(as.integer(runif(len, min=MIN, max=MAX+1)))
}

# Check the output:
table(rollDice(1000))

# This works, since runif() can return a vector of deviates,
# but if we write the function this way we can't check the value of
# individual trials.

# Disclaimer 2: the function relies on a side-effect of as.integer(), which is
# to drop the digits after the comma when it converts. More explicit and
# therefore clearer would be to use the function floor() instead. Here, the
# truncation is not a side effect, but the desired behaviour. This is
# actually important: there is no guarantee how as.integer() constructs an
# integer from a float, it could e.g. round, instead of truncating. But rounding
# would give a wrong distribution! An error that may be hard to spot. (You
# can easily try using the round() function and think about how the result is wrong.)

# A better alternative is thus to write:

rollDice <- function(len=1, MIN=1, MAX=6) {
	return(floor(runif(len, min=MIN, max=MAX+1)))
}

# Disclaimer 3
# A base R function exists that already rolls dice in the required way: sample()

table(sample(1:6, 1000, replace=TRUE))

@@ Line 1,102: / Line 1,102: @@
 ====Coding style====
-Code is read much more often than it is written and it should always be your goal to write as clearly as possible. '''R''' has many complex idioms, and as a functional language that can generally insert functions anywhere into expressions it is possible to write very terse, expressive code. Don't do it. Pace yourself, and make sure your reader can follow your flow of thought. More often than not the poor soul who will be confused by a particularly witty use of the language will be you, yourself, half a year later. There is an astute observation by Brian Kernighan that applies completely:
-:"Debugging is twice as hard as writing the code in the first place. Therefore, if you write the code as cleverly as possible, you are, by definition, not smart enough to debug it."
-<div class="mw-collapsible mw-collapsed" data-expandtext="Expand" data-collapsetext="Collapse" style="border:#000000 solid 1px; padding: 10px;">A number of guides for '''R''' coding style are available ... expand here to see what I recommend (or require).<div  class="mw-collapsible-content">
-<div class="colmask doublepage">
-  <div class="colleft">
-    <div class="col1">
-      <!-- Column 1 start -->
-* Use informative and specific '''filenames''' for code sources; give them the extension {{c|.R}}
-* Give your '''sources''' headers stating purpose, author, date and version information, and note bugs and issues.
-* Give your '''functions''' headers that describe purpose, arguments (including required datatypes), and return values. Callers should be able to work with the function without having to read the code.
-* Use lots of '''comments'''. Never describe what the code does, but explain '''why'''.
-* Use '''separators''' ({{c|# --- SECTION -----------------}}) to structure your code.
-* '''Indent''' comment hashes to align with the expressions in a block.
-* Use only {{c|<-}} for assignment, not {{c|{{=}}}}
-* ...but do use {{c|{{=}}}} when defining parameters of functions.
-* Don't use {{c|<<-}} (global assignment) except in very unusual cases.
-* Use the concise {{c|camelCaseStyle}} for variable names, never use the {{c|confusing.dot.style}} or the rambling {{c|separating_with_underscores_style}}.
-* Define parameters at the beginning of the code, use all caps variable names ({{c|MAXWIDTH}}). Never have "magic numbers" appear in your code.
-* In mathematical expressions, always use '''parentheses''' to define priority. Never rely on convention. {{c|(( 1 + 2 ) / 3 ) * 4}}
-* Always separate operators and arguments with spaces.<ref>Separating operators with spaces is especially important for the assignment operator {{c|<-}}. Consider this: {{c| myPreciousData < -2}} returns a vector of {{c|TRUE}} and {{c|FALSE}}, depending on whether the values in {{c|myPreciousData}} are less than 2. But  {{c| myPreciousData<-2}} overwrites evry single element with the number {{c|2}}!</ref>
-* Never separate function names and the brackets that enclose argument lists.
-* Don't abbreviate argument names.
-      <!-- Column 1 end -->
-    </div>
-    <div class="col2">
-      <!-- Column 2 start -->
-* Try to limit yourself to ~80 characters per line.
-* Always use braces {{c|{}}}, even if you write single-line {{c|if}} statements and loops.
-* Always use a '''space''' after a comma, and never before a comma.
-* Always '''explicitly return''' values from functions, never rely on returning the last expression.
-* Use spaces to '''align''' repeating parts of code, so errors become easier to spot.
-* '''Don't repeat''' code. Use functions instead.
-* Write out crucial arguments to functions, even if you think you know that this is redundant with the default.
-* Never reassign reserved words.
-* Don't use {{c|c}} as a variable name since {{c|c()}}  is a function.
-* Don't call your data frames {{c|df}} since {{c|df()}} is a function.
-* Don't use semicolons, and don't write more than one command on a line.
-* Don't use {{c|attach()}}.
-* Use {{c|for (i in seq(along{{=}}x)) {...}}}   not {{c|for (i in 1:length(x)) {...}}} because of an unwanted loop if {{c|x {{=}}{{=}} NULL}}
-* If possible, do not grow data structures, but create the whole structure with {{c|NULL}} values, then modify them. This is '''much''' faster.
-;Specific naming conventions I like:
-:{{c|isValid}}, {{c|hasNeighbour}}  ... Boolean variables
-:{{c|findRange()}}, {{c|getLimits()}} ... simple function names (verbs!)
-:{{c|initializeTable()}} ... not {{c|initTab()}}
-:{{c|node}} ... for one element; {{c|nodes}} ... for more elements
-:{{c|nPoints}} ... for number-of
-:{{c|isError}} ... not {{c|isNotError}}: avoid double negation
-<hr />
-Consider using the [http://cran.r-project.org/web/packages/formatR/index.html '''formatR'''] package for consistent code.
-And seriously - [http://xkcd.com/1513/ XKCD: Code Quality]
-      <!-- Column 2 end -->
-    </div>
-  </div>
-</div>
-</div>
-</div>
+{{#lst:Software_development|codingStyle}}
 &nbsp;

Difference between revisions of "R tutorial"

Revision as of 22:26, 1 October 2015

Contents

The environment

Install R

Install R Studio

Notation

User interface

The Help system

Working directory

.Rprofile - startup commands

... unix systems

... Mac OS X systems

...Windows systems

The "Workspace"

Packages

Scripts

Simple commands

Operators

Functions

Variables

Scalar data

Vectors

Matrices

Lists

Data frames

Subsetting

Writing your own functions

Coding style

Debugging

Finishing

Notes

Further reading and resources

Navigation menu

Search