Subsetting Lists

Suppose x is a list object in R. The follwoing chunk is showing you how to extract information from a list object or how to access it’s elements.

x<-list(A=1:6,B=c("a","b","c","d"))
x[1]
## $A
## [1] 1 2 3 4 5 6
x[[1]]
## [1] 1 2 3 4 5 6
x$A
## [1] 1 2 3 4 5 6
x<-list(course=689, credit=3, sem="FALL")
x[c(1,3)]
## $course
## [1] 689
## 
## $sem
## [1] "FALL"
name="credit"
x[[name]]
## [1] 3
x<-list(A=1:10,B=seq(20,25,by=1))
x[[2]][4]
## [1] 23

Subsetting matrices

x<-matrix(1:6,nrow=2,ncol=3)
x[1,2]
## [1] 3
x[1,2,  drop = F]
##      [,1]
## [1,]    3
#or 
x[1,]
## [1] 1 3 5
x[,2]
## [1] 3 4
x[1,,drop=F]
##      [,1] [,2] [,3]
## [1,]    1    3    5

Removing NA values

x<-c(1,2,NA,4,NA,5)
bad<-is.na(x)
x[!bad]
## [1] 1 2 4 5
y<-c("a","b",NA,"d",NA,"f")
select<-complete.cases(x,y)
x[select]
## [1] 1 2 4 5
y[select]
## [1] "a" "b" "d" "f"
data<-matrix(rnorm(100,0,1),nrow=10)
data[4,1]<-NA; data[6,2]<-NA; data[4,6]<-NA
keep<-complete.cases(data)
data[keep,][1:6,]
##            [,1]       [,2]       [,3]       [,4]       [,5]        [,6]
## [1,] -0.6271490  1.2794757 -0.2335086  0.4584832 -0.2036284  0.62244857
## [2,]  1.0832882 -0.3740906 -2.2665337 -1.0861524  0.5265468 -0.02471441
## [3,] -0.0717052 -1.4466038  0.1464550 -0.4964407 -0.1839417  1.86649438
## [4,] -0.1008556 -0.4059537 -1.6729458  1.4533749  2.2994596  1.29240559
## [5,] -0.7173906 -1.1021700  0.6713288 -0.5083368 -0.4972138 -0.07170019
## [6,] -0.5604094 -1.1133294  0.3064856  0.8752643  1.4867615 -0.82845830
##             [,7]        [,8]       [,9]       [,10]
## [1,] -0.40881749  0.29435523  0.6394091  1.63816964
## [2,] -0.13988885 -0.73297479 -1.3347625  0.48934312
## [3,] -1.07999952  0.05150205  0.6869289 -0.42631770
## [4,]  0.75537387 -0.32165687 -0.5780814  0.04231296
## [5,]  0.02394506  1.38402423  0.4705631 -0.95026361
## [6,] -0.02787642  0.42128630 -1.0245564 -2.79929037

matrix multiplication

x<-matrix(rpois(20,1.5),nrow=4)
y<-matrix(rpois(20,2),nrow=4)
x%*%t(y)
##      [,1] [,2] [,3] [,4]
## [1,]   16   21    8   19
## [2,]   14   19   14   23
## [3,]   16   21   14   22
## [4,]   11   15    5   11

control structures

if(<condition>){
   ## do something
}else {
    ## do something else
}

Example

x<-c(1:3,13:19)
count<-rep(0,length(x))
for(i in 1:length(x)){
if(x[i]%%3==0){
 count[i]<-1 
}else{
  count[i]<-0
}
}
count
##  [1] 0 0 1 0 0 1 0 0 1 0

Nested loops

x<-matrix(1:6,2,3)
for(i in 1:nrow(x)){
  for(j in 1:ncol(x)){
    print(x[i,j])
  }
}
## [1] 1
## [1] 3
## [1] 5
## [1] 2
## [1] 4
## [1] 6
count<-0
while(count< 10){
  print(count)
  count<-count+1
}
## [1] 0
## [1] 1
## [1] 2
## [1] 3
## [1] 4
## [1] 5
## [1] 6
## [1] 7
## [1] 8
## [1] 9
count<-10
while(count>=8 && count<=15){
  print(count)
  y<-rbinom(1,1,0.5)
  if(y==1){
    count<-count+1
  }else{
    count<-count-1
  
       }
  }
## [1] 10
## [1] 11
## [1] 12
## [1] 11
## [1] 12
## [1] 11
## [1] 10
## [1] 11
## [1] 10
## [1] 9
## [1] 10
## [1] 11
## [1] 10
## [1] 9
## [1] 8
## [1] 9
## [1] 8

Application of lapply

x<-list(a=1:6,b=rnorm(20))
lapply(x,mean)
## $a
## [1] 3.5
## 
## $b
## [1] 0.3309427
#OR

n= 20:25
lapply(n,rnorm)
## [[1]]
##  [1]  0.48854714 -1.26325141 -0.29414303  0.27281617 -1.42467594
##  [6] -1.41259012 -1.23597651  1.15876777  0.19443662  0.05161971
## [11] -0.05172900  0.10142570 -1.41401398  0.24866032  0.27696152
## [16]  0.17280489 -0.24053153 -0.16559129 -0.70341867  1.34216153
## 
## [[2]]
##  [1] -0.5109436 -0.5043873 -0.1904385 -0.6657738  0.6874222 -0.2342082
##  [7]  1.2897946 -1.0574992  2.2516772 -0.6805431 -1.1521277  0.5283933
## [13] -0.1562630  0.8580294 -0.4970907 -0.4663930  0.1992250  0.9303913
## [19] -0.8088025 -1.6718232 -1.6894229
## 
## [[3]]
##  [1] -1.4633121 -0.3683112 -0.5123979 -1.5042865 -0.7626365  0.1916466
##  [7]  1.3997910  0.2917191 -0.3723488  0.7039750  1.7656462 -0.1924491
## [13]  0.6952221  0.5774937  0.8043867  0.1397612 -0.1675083 -1.1934418
## [19]  0.9435622  0.0465076 -1.0160125 -2.2722410
## 
## [[4]]
##  [1] -0.11355655 -1.34656848  1.18613838  0.80816823  1.48430545
##  [6] -0.12628790 -1.02506334 -0.93503002  1.67641350 -0.76981173
## [11]  0.94198329 -0.39369622 -0.31050915  2.00319961  1.37329376
## [16] -1.24256141  0.32519004 -0.93915578  0.71280314  1.38358481
## [21]  0.86829649  0.05292082 -2.37386582
## 
## [[5]]
##  [1]  1.45937594  0.72422439  0.43744336 -0.49635735  1.33251070
##  [6] -1.51985626  0.95858907 -0.52526699  0.67981929 -0.29853150
## [11]  1.08021909 -1.21664542  0.03802331  0.30913841 -0.10060330
## [16]  1.44724505  0.28063096  1.21657339  0.21004710  1.23603779
## [21]  1.39252155 -1.65432004  0.49228912 -0.64943850
## 
## [[6]]
##  [1]  0.18097612  1.36738417 -0.66978994 -1.34089326 -1.02262208
##  [6] -0.05907545  0.74275686  0.04471133 -0.99234373  0.79910909
## [11]  1.64772092 -0.42724391  1.55052761  0.61758758  0.80334260
## [16] -0.21677186  1.79323008 -1.34608079 -0.36288422  0.03447574
## [21] -1.51644172 -1.14826493  0.00732521  0.91001525  0.35684399
#

Application of apply

x<-matrix(rnorm(10),nrow=5)
apply(x,2,mean)
## [1]  0.13151458 -0.03733971
apply(x,1,mean)
## [1]  0.8111073  0.8445551  0.2546650 -1.0039340 -0.6709563
#rowSums; colMeans

use of strsplit

data<-read.csv("TobaccoVars.csv",sep=",",header=T)
rownames(data)<-data[,1];data<-data[,-1]
N<-colnames(data);
n<-strsplit(N[2:33],"[.]")
n[1:10]
## [[1]]
## [1] "hsa" "let" "7b" 
## 
## [[2]]
## [1] "hsa" "let" "7d" 
## 
## [[3]]
## [1] "hsa" "mir" "10a"
## 
## [[4]]
## [1] "hsa"  "mir"  "1266"
## 
## [[5]]
## [1] "hsa" "mir" "128" "1"  
## 
## [[6]]
## [1] "hsa"  "mir"  "1287"
## 
## [[7]]
## [1] "hsa"  "mir"  "1293"
## 
## [[8]]
## [1] "hsa"  "mir"  "1304"
## 
## [[9]]
## [1] "hsa"  "mir"  "135b"
## 
## [[10]]
## [1] "hsa"  "mir"  "181d"