R Notebook

Vector

# Create
score = c(100, 90, 60, 70, 85, 90)
age =c(30, 35, 60, 50, 32, 25)

# select
score[3]

[1] 60

age[5]

[1] 32

age[10]

[1] NA

length(score)

[1] 6

length(age)

[1] 6

Append element

age

[1] 30 35 60 50 32 25

age = c(age, 2000)
age

[1]   30   35   60   50   32   25 2000

score = c(score, 78)
score

[1] 100  90  60  70  85  90  78

age = c(40, age)
age

[1]   40   30   35   60   50   32   25 2000

age[1:4]

[1] 40 30 35 60

age[5:8]

[1]   50   32   25 2000

age = c(age[1:4], 45, age[5:8] )
age

[1]   40   30   35   60   45   50   32   25 2000

Select a vector segment

age[3:5]

[1] 35 60 45

score[4:10]

[1] 70 85 90 78 NA NA NA

Remove element

age = age[-8]
age

[1]   40   30   35   60   45   50   32 2000

Update

score

[1] 100  90  60  70  85  90  78

score[4] = 80
score

[1] 100  90  60  80  85  90  78

Conditional Selection

age

[1]   40   30   35   60   45   50   32 2000

age[ age < 50 ]

[1] 40 30 35 45 32

age[ age <= 50 ]

[1] 40 30 35 45 50 32

age[ age > 50 ]

[1]   60 2000

age[ age >= 50 ]

[1]   60   50 2000

# 40 <= age <=50
age_grater_40 = age[ age >= 40 ]
age_grater_40

[1]   40   60   45   50 2000

age_40_50 = age_grater_40[ age_grater_40 <= 50 ]
age_40_50

[1] 40 45 50

age_40_50_v2 = age[ age >= 40  & age <= 50]
age_40_50_v2

[1] 40 45 50

Condition

result = score >= 80
result

[1]  TRUE  TRUE FALSE  TRUE  TRUE  TRUE FALSE

Simple stats

min(score)

[1] 60

max(score)

[1] 100

mean(score)

[1] 83.28571

sum(score)

[1] 583

median(score)

[1] 85

sd(score)

[1] 12.60574

var(score)

[1] 158.9048

quantile(score)

  0%  25%  50%  75% 100% 
  60   79   85   90  100 

mode(score)

[1] "numeric"

Correlation

score = c(score, c(100, 80, 20, 20))

age = c(age, c(30, 70, 75))

score

 [1] 100  90  60  80  85  90  78 100  80  20  20

age

 [1]   40   30   35   60   45   50   32 2000   30   70   75

score2 = c(10, 50, 30, 40)
age2 = c(20, 25, 30, 35)
cor(score2, age2)

[1] 0.5291503

cor(score, age)

[1] 0.2961703

cor(age, score)

[1] 0.2961703

# +: positive correlation 
# -: neg correlation

Data Frame

data = data.frame(
ID = c(1, 2, 3, 4, 5),
name = c("A", "S", "D", "P", "C"),
score = c(10, 50, 30, 40, 45),
age = c(20, 25, 30, 35, 32)
)

data

Select column

data$score

[1] 10 50 30 40 45

data$age

[1] 20 25 30 35 32

Selection: data[row : col]

data[2, ]

data[ ,2]

[1] "A" "S" "D" "P" "C"

data[ 2, 2]

[1] "S"

data[ , c(1, 3) ]

data[ , c(1, 3,4) ]

data[c(2, 4) , c(1,3,4) ]

data

data[ data$age <= 30 , ]

select students score greater than equal 40

data[ data$score >= 40 , ]

data[ data$score >= 40 , c(1, 2, 3) ]

Select students with score ge 40 and age ge 30. Show only name and score.

data[ data$score >= 40  & data$age >= 30, c(2, 3) ]

Ordering dataset

data[order(data$score) , ]

data[order(data$score, decreasing = TRUE) , ]

Add new col

dept = c("CS", "Bio", "Genetics", "Phy", "Sports")

data = cbind(data, dept)
data

NA

Column reorder

data = data[ , c(1, 2, 5, 3, 4)]
data

delete a column

data = data[ , c(1, 2, 3, 4)]
data

data

summary(data)

       ID        name               dept               score   
 Min.   :1   Length:5           Length:5           Min.   :10  
 1st Qu.:2   Class :character   Class :character   1st Qu.:30  
 Median :3   Mode  :character   Mode  :character   Median :40  
 Mean   :3                                         Mean   :35  
 3rd Qu.:4                                         3rd Qu.:45  
 Max.   :5                                         Max.   :50  

str(data)

'data.frame':   5 obs. of  4 variables:
 $ ID   : num  1 2 3 4 5
 $ name : chr  "A" "S" "D" "P" ...
 $ dept : chr  "CS" "Bio" "Genetics" "Phy" ...
 $ score: num  10 50 30 40 45

IRIS Dataset

iris = read.csv("iris.csv")
iris

str(iris)

'data.frame':   150 obs. of  5 variables:
 $ sepal.length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
 $ sepal.width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
 $ petal.length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
 $ petal.width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
 $ variety     : chr  "Setosa" "Setosa" "Setosa" "Setosa" ...

summary(iris)

  sepal.length    sepal.width     petal.length    petal.width      variety         
 Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100   Length:150        
 1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300   Class :character  
 Median :5.800   Median :3.000   Median :4.350   Median :1.300   Mode  :character  
 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                     

Scatter plot

library(ggplot2)

ggplot(iris, aes(x = sepal.length, y = sepal.width, color = variety)) +
  geom_point() +
  theme_minimal()

Boxplot

ggplot(iris, aes(y = sepal.length, x = variety, fill = variety)) +
  geom_boxplot()

Boxplot

ggplot(iris, aes(y = sepal.length, x = variety, fill = variety)) +
  geom_violin()