ls()## character(0)getwd() # get the working directory## [1] "E:/R/WorkSpace"setwd(".") # set the working directory
save.image(file="R_workspace_save")
#save()
load(file="R_workspace_save") # to load the saved workspace fileThis is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00# declaring vector
x = c(4,3,3,4,3,1);x## [1] 4 3 3 4 3 1y = vector(mode="logical" , length = 4);y## [1] FALSE FALSE FALSE FALSEz = vector(mode="numeric" , length = 4);z## [1] 0 0 0 0# declaring vector with some pattern.
q = rep(3.2,times=10); q## [1] 3.2 3.2 3.2 3.2 3.2 3.2 3.2 3.2 3.2 3.2w = seq(0,1,by=0.1); w## [1] 0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0w2 = seq(0,1,length.out=11) ;w2## [1] 0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0#vector operation
w<=0.5## [1] TRUE TRUE TRUE TRUE TRUE TRUE FALSE FALSE FALSE FALSE FALSEany(w<=0.5)## [1] TRUEall(w<=0.5)## [1] FALSEwhich(w<=0.5)## [1] 1 2 3 4 5 6#subsetting from vector
w[w<=0.5]## [1] 0.0 0.1 0.2 0.3 0.4 0.5subset(w,w<=0.5) # equalivant to above command## [1] 0.0 0.1 0.2 0.3 0.4 0.5w[w<=0.5] = 0;w # zeroing out the values less than equal to 0.5## [1] 0.0 0.0 0.0 0.0 0.0 0.0 0.6 0.7 0.8 0.9 1.0# Arrays in R (tables)
z = seq(1,20,length.out = 20);z## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20x = array(data=z ,dim=c(4,5));x # reshape the value## [,1] [,2] [,3] [,4] [,5]
## [1,] 1 5 9 13 17
## [2,] 2 6 10 14 18
## [3,] 3 7 11 15 19
## [4,] 4 8 12 16 20#indexiing arrays
x[2,3] # x[row,col]## [1] 10x[-1,] # negative index correspond to take all row except 1. Dont take first row and take all columns## [,1] [,2] [,3] [,4] [,5]
## [1,] 2 6 10 14 18
## [2,] 3 7 11 15 19
## [3,] 4 8 12 16 20y = x[c(1,2),c(1,2)];y## [,1] [,2]
## [1,] 1 5
## [2,] 2 6#Manipulate array.
2*y+1 # applied to each element seperately## [,1] [,2]
## [1,] 3 11
## [2,] 5 13y%*%y # Matrix multiplication operator## [,1] [,2]
## [1,] 11 35
## [2,] 14 46# Inner product and transpose
x## [,1] [,2] [,3] [,4] [,5]
## [1,] 1 5 9 13 17
## [2,] 2 6 10 14 18
## [3,] 3 7 11 15 19
## [4,] 4 8 12 16 20x[1,] %*% x[1,]; # inner product of two vectors## [,1]
## [1,] 565t(x) # transpose of array## [,1] [,2] [,3] [,4]
## [1,] 1 2 3 4
## [2,] 5 6 7 8
## [3,] 9 10 11 12
## [4,] 13 14 15 16
## [5,] 17 18 19 20#outer product (cross product)
outer(x[,1],x[,1]) # outter product is matrix and is multiplication of i th element of first and jth element of second vector## [,1] [,2] [,3] [,4]
## [1,] 1 2 3 4
## [2,] 2 4 6 8
## [3,] 3 6 9 12
## [4,] 4 8 12 16# concatination
x## [,1] [,2] [,3] [,4] [,5]
## [1,] 1 5 9 13 17
## [2,] 2 6 10 14 18
## [3,] 3 7 11 15 19
## [4,] 4 8 12 16 20rbind(x[1,],x[1,]) # rbind ==> row bind. concatinate rows or two vectors## [,1] [,2] [,3] [,4] [,5]
## [1,] 1 5 9 13 17
## [2,] 1 5 9 13 17x## [,1] [,2] [,3] [,4] [,5]
## [1,] 1 5 9 13 17
## [2,] 2 6 10 14 18
## [3,] 3 7 11 15 19
## [4,] 4 8 12 16 20cbind(x[1,],x[1,]) # conacatinates two vectors a columns## [,1] [,2]
## [1,] 1 1
## [2,] 5 5
## [3,] 9 9
## [4,] 13 13
## [5,] 17 17# List
# collection of different types. can be think of class in C.
# each position have a name associated with it
# List is kind of a row in a dataframe
L = list(name ="Deepak" , age = 30 , no.children =3 , children.age = c(2,5));L## $name
## [1] "Deepak"
##
## $age
## [1] 30
##
## $no.children
## [1] 3
##
## $children.age
## [1] 2 5names(L) # names is the function. returns the names of the positions## [1] "name" "age" "no.children" "children.age"L[[2]] # [[]] returns the object in second loc. if we only use single bracket it will return list## [1] 30L[2] # return list## $age
## [1] 30L$name # value of name## [1] "Deepak"L['name'] # python has syntax## $name
## [1] "Deepak"L[[4]][2]## [1] 5#Dataframes
# ordered seq of list sharing the same datatypes
vecn = c("Dave x","David y")
veca = c(22,33)
vecs = c(22000,22111)
frame = data.frame(name = vecn , age=veca ,salary= vecs)
#load iris data set. THis is inbuilt in R
data(iris)
names(iris)## [1] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
## [5] "Species"seq(1,4,1) ## [1] 1 2 3 4first_four <- iris[c(1,2,3,4),] # first for rows
head(iris,4)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosairis[c(1,2,3,4),]## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosafirst_four## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosairis[1,]## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosairis$Sepal.Length[1:10] # sepel length of first 10 samples## [1] 5.1 4.9 4.7 4.6 5.0 5.4 4.6 5.0 4.4 4.9#manupulation of data set
mean(iris$Sepal.Length) # mean of a column## [1] 5.843333#head(iris)
iris[,1:4] # filter multiple column## Sepal.Length Sepal.Width Petal.Length Petal.Width
## 1 5.1 3.5 1.4 0.2
## 2 4.9 3.0 1.4 0.2
## 3 4.7 3.2 1.3 0.2
## 4 4.6 3.1 1.5 0.2
## 5 5.0 3.6 1.4 0.2
## 6 5.4 3.9 1.7 0.4
## 7 4.6 3.4 1.4 0.3
## 8 5.0 3.4 1.5 0.2
## 9 4.4 2.9 1.4 0.2
## 10 4.9 3.1 1.5 0.1
## 11 5.4 3.7 1.5 0.2
## 12 4.8 3.4 1.6 0.2
## 13 4.8 3.0 1.4 0.1
## 14 4.3 3.0 1.1 0.1
## 15 5.8 4.0 1.2 0.2
## 16 5.7 4.4 1.5 0.4
## 17 5.4 3.9 1.3 0.4
## 18 5.1 3.5 1.4 0.3
## 19 5.7 3.8 1.7 0.3
## 20 5.1 3.8 1.5 0.3
## 21 5.4 3.4 1.7 0.2
## 22 5.1 3.7 1.5 0.4
## 23 4.6 3.6 1.0 0.2
## 24 5.1 3.3 1.7 0.5
## 25 4.8 3.4 1.9 0.2
## 26 5.0 3.0 1.6 0.2
## 27 5.0 3.4 1.6 0.4
## 28 5.2 3.5 1.5 0.2
## 29 5.2 3.4 1.4 0.2
## 30 4.7 3.2 1.6 0.2
## 31 4.8 3.1 1.6 0.2
## 32 5.4 3.4 1.5 0.4
## 33 5.2 4.1 1.5 0.1
## 34 5.5 4.2 1.4 0.2
## 35 4.9 3.1 1.5 0.2
## 36 5.0 3.2 1.2 0.2
## 37 5.5 3.5 1.3 0.2
## 38 4.9 3.6 1.4 0.1
## 39 4.4 3.0 1.3 0.2
## 40 5.1 3.4 1.5 0.2
## 41 5.0 3.5 1.3 0.3
## 42 4.5 2.3 1.3 0.3
## 43 4.4 3.2 1.3 0.2
## 44 5.0 3.5 1.6 0.6
## 45 5.1 3.8 1.9 0.4
## 46 4.8 3.0 1.4 0.3
## 47 5.1 3.8 1.6 0.2
## 48 4.6 3.2 1.4 0.2
## 49 5.3 3.7 1.5 0.2
## 50 5.0 3.3 1.4 0.2
## 51 7.0 3.2 4.7 1.4
## 52 6.4 3.2 4.5 1.5
## 53 6.9 3.1 4.9 1.5
## 54 5.5 2.3 4.0 1.3
## 55 6.5 2.8 4.6 1.5
## 56 5.7 2.8 4.5 1.3
## 57 6.3 3.3 4.7 1.6
## 58 4.9 2.4 3.3 1.0
## 59 6.6 2.9 4.6 1.3
## 60 5.2 2.7 3.9 1.4
## 61 5.0 2.0 3.5 1.0
## 62 5.9 3.0 4.2 1.5
## 63 6.0 2.2 4.0 1.0
## 64 6.1 2.9 4.7 1.4
## 65 5.6 2.9 3.6 1.3
## 66 6.7 3.1 4.4 1.4
## 67 5.6 3.0 4.5 1.5
## 68 5.8 2.7 4.1 1.0
## 69 6.2 2.2 4.5 1.5
## 70 5.6 2.5 3.9 1.1
## 71 5.9 3.2 4.8 1.8
## 72 6.1 2.8 4.0 1.3
## 73 6.3 2.5 4.9 1.5
## 74 6.1 2.8 4.7 1.2
## 75 6.4 2.9 4.3 1.3
## 76 6.6 3.0 4.4 1.4
## 77 6.8 2.8 4.8 1.4
## 78 6.7 3.0 5.0 1.7
## 79 6.0 2.9 4.5 1.5
## 80 5.7 2.6 3.5 1.0
## 81 5.5 2.4 3.8 1.1
## 82 5.5 2.4 3.7 1.0
## 83 5.8 2.7 3.9 1.2
## 84 6.0 2.7 5.1 1.6
## 85 5.4 3.0 4.5 1.5
## 86 6.0 3.4 4.5 1.6
## 87 6.7 3.1 4.7 1.5
## 88 6.3 2.3 4.4 1.3
## 89 5.6 3.0 4.1 1.3
## 90 5.5 2.5 4.0 1.3
## 91 5.5 2.6 4.4 1.2
## 92 6.1 3.0 4.6 1.4
## 93 5.8 2.6 4.0 1.2
## 94 5.0 2.3 3.3 1.0
## 95 5.6 2.7 4.2 1.3
## 96 5.7 3.0 4.2 1.2
## 97 5.7 2.9 4.2 1.3
## 98 6.2 2.9 4.3 1.3
## 99 5.1 2.5 3.0 1.1
## 100 5.7 2.8 4.1 1.3
## 101 6.3 3.3 6.0 2.5
## 102 5.8 2.7 5.1 1.9
## 103 7.1 3.0 5.9 2.1
## 104 6.3 2.9 5.6 1.8
## 105 6.5 3.0 5.8 2.2
## 106 7.6 3.0 6.6 2.1
## 107 4.9 2.5 4.5 1.7
## 108 7.3 2.9 6.3 1.8
## 109 6.7 2.5 5.8 1.8
## 110 7.2 3.6 6.1 2.5
## 111 6.5 3.2 5.1 2.0
## 112 6.4 2.7 5.3 1.9
## 113 6.8 3.0 5.5 2.1
## 114 5.7 2.5 5.0 2.0
## 115 5.8 2.8 5.1 2.4
## 116 6.4 3.2 5.3 2.3
## 117 6.5 3.0 5.5 1.8
## 118 7.7 3.8 6.7 2.2
## 119 7.7 2.6 6.9 2.3
## 120 6.0 2.2 5.0 1.5
## 121 6.9 3.2 5.7 2.3
## 122 5.6 2.8 4.9 2.0
## 123 7.7 2.8 6.7 2.0
## 124 6.3 2.7 4.9 1.8
## 125 6.7 3.3 5.7 2.1
## 126 7.2 3.2 6.0 1.8
## 127 6.2 2.8 4.8 1.8
## 128 6.1 3.0 4.9 1.8
## 129 6.4 2.8 5.6 2.1
## 130 7.2 3.0 5.8 1.6
## 131 7.4 2.8 6.1 1.9
## 132 7.9 3.8 6.4 2.0
## 133 6.4 2.8 5.6 2.2
## 134 6.3 2.8 5.1 1.5
## 135 6.1 2.6 5.6 1.4
## 136 7.7 3.0 6.1 2.3
## 137 6.3 3.4 5.6 2.4
## 138 6.4 3.1 5.5 1.8
## 139 6.0 3.0 4.8 1.8
## 140 6.9 3.1 5.4 2.1
## 141 6.7 3.1 5.6 2.4
## 142 6.9 3.1 5.1 2.3
## 143 5.8 2.7 5.1 1.9
## 144 6.8 3.2 5.9 2.3
## 145 6.7 3.3 5.7 2.5
## 146 6.7 3.0 5.2 2.3
## 147 6.3 2.5 5.0 1.9
## 148 6.5 3.0 5.2 2.0
## 149 6.2 3.4 5.4 2.3
## 150 5.9 3.0 5.1 1.8colMeans(iris[,1:4]) # generate column multiple mean seperately## Sepal.Length Sepal.Width Petal.Length Petal.Width
## 5.843333 3.057333 3.758000 1.199333subset(iris,iris$Species=="setosa" & iris$Sepal.Length<5) # find subset## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 7 4.6 3.4 1.4 0.3 setosa
## 9 4.4 2.9 1.4 0.2 setosa
## 10 4.9 3.1 1.5 0.1 setosa
## 12 4.8 3.4 1.6 0.2 setosa
## 13 4.8 3.0 1.4 0.1 setosa
## 14 4.3 3.0 1.1 0.1 setosa
## 23 4.6 3.6 1.0 0.2 setosa
## 25 4.8 3.4 1.9 0.2 setosa
## 30 4.7 3.2 1.6 0.2 setosa
## 31 4.8 3.1 1.6 0.2 setosa
## 35 4.9 3.1 1.5 0.2 setosa
## 38 4.9 3.6 1.4 0.1 setosa
## 39 4.4 3.0 1.3 0.2 setosa
## 42 4.5 2.3 1.3 0.3 setosa
## 43 4.4 3.2 1.3 0.2 setosa
## 46 4.8 3.0 1.4 0.3 setosa
## 48 4.6 3.2 1.4 0.2 setosadim(subset(iris,iris$Species=="setosa"))[1] # to get the dimention## [1] 50summary(iris) # column wise summary## Sepal.Length Sepal.Width Petal.Length Petal.Width
## Min. :4.300 Min. :2.000 Min. :1.000 Min. :0.100
## 1st Qu.:5.100 1st Qu.:2.800 1st Qu.:1.600 1st Qu.:0.300
## Median :5.800 Median :3.000 Median :4.350 Median :1.300
## Mean :5.843 Mean :3.057 Mean :3.758 Mean :1.199
## 3rd Qu.:6.400 3rd Qu.:3.300 3rd Qu.:5.100 3rd Qu.:1.800
## Max. :7.900 Max. :4.400 Max. :6.900 Max. :2.500
## Species
## setosa :50
## versicolor:50
## virginica :50
##
##
## # control flow in R. Similar to C/C++
a = 10 ; b = 5 ; c =1
if (a<b){
d =1
}else if (a ==b){
d =2
}else {
d = 3
}
print(d)## [1] 3# logical operator is similar to C++ or Java
# AND &&
# OR ||
# euality ==
# inequality !=
# For loop example
sum = 0
for(num in seq(1,100, by=1)){
sum = sum + num
}
print(sum)## [1] 5050# repeat loop demo. Similar to while(1) loop in C
total = function(n){
sum = 5050
num = n
repeat {
sum = sum - num
num = num -1
if(sum <=0){
break
}
}
###Put the code for the 'repeat' loop here.
return(sum)
}
total(100)## [1] 0# while loop is exactly similar to C
#while(a<b){
# a= a+1
#}
# Defining functions in R
mypow = function (bas = 10,pow=2){
res = bas ^pow
return(res)
}
mypow(2,3) ## [1] 8mypow(bas=3) # default value to pow## [1] 9# can pass parameters with order same as specified in function
# different order than defined in function by specifiing the parameter explicitly
# Also can ignore the defaut parameters
# Vectorized code.
# vectorized code as much as you can for runtime benefit
# Use C++/C hooks to seedup the code which can't be vectorized and have bottleneck
# use .Call() API
# or Use Rcpp API