R Notebook

Data Frame

data = data.frame(
  ID = c(1, 2, 3, 4, 5),
  Name = c("A", "B", "C", "D", 'E'),
  Age = c(25, 30, 22, 28, 35),
  Score = c(85, 92, 78, 89, 81)
)

data

Data Stats

data$Age

[1] 25 30 22 28 35

data$Score

[1] 85 92 78 89 81

mean(data$Age)

[1] 28

mean(data$Score)

[1] 85

summary(data)

       ID        Name                Age         Score   
 Min.   :1   Length:5           Min.   :22   Min.   :78  
 1st Qu.:2   Class :character   1st Qu.:25   1st Qu.:81  
 Median :3   Mode  :character   Median :28   Median :85  
 Mean   :3                      Mean   :28   Mean   :85  
 3rd Qu.:4                      3rd Qu.:30   3rd Qu.:89  
 Max.   :5                      Max.   :35   Max.   :92  

cor(data$Age, data$Score)

[1] 0.2480695

sd(data$Age)

[1] 4.949747

sd(data$Age) / sqrt(5)

[1] 2.213594

Data Select

data

Row selection

data[2:4 , ]

Col selection

data[ , 2:4]

data[2:4, 2:4]

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

data[2, 4]

[1] 92

data[2, ]

data[ , 4]

[1] 85 92 78 89 81

2:4

[1] 2 3 4

c(2, 3, 4)

[1] 2 3 4

data[c(1, 3, 5), ]

data[ , c(1, 3)]

Conditional Selection

# score > 80
data[ data$Score > 80 , ]

# age >= 30

data[ data$Age >= 30, ]

# age = 30
data[ data$Age == 30 , ]

# select the rows with age 22, 25 or 35

data[ data$Age == 22 | data$Age == 25 | data$Age == 35 , ]

NA

Col add

Dept = c("CS", "Bio", "Chem", "Phy", "Eco")
data = cbind(data, Dept)
data 

new_r = c(6, "F", 60, 100, "Eng")
data = rbind(data, new_r)
data

Add in the middle

new_r = c(10, "A", 40, 100, "Eng")

data[1:2 , ]

data[3:6, ]

data = rbind(data[1:2 , ], new_r, data[3:6, ])
data

data

Family_name = c("A", "X", "Y", "Z", "G", "V", "N")

cbind(data[ , 1:2], Family_name, data[ , 3:5])

cbind

function (..., deparse.level = 1) 
.Internal(cbind(deparse.level, ...))
<bytecode: 0x7f883e312da8>
<environment: namespace:base>

search in every column for a specific value

Real dataset

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

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                     

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" ...

# select row for setosa.
setosa = iris[iris$variety == "Setosa" , ]
head(setosa)

summary(setosa)

  sepal.length    sepal.width     petal.length    petal.width      variety         
 Min.   :4.300   Min.   :2.300   Min.   :1.000   Min.   :0.100   Length:50         
 1st Qu.:4.800   1st Qu.:3.200   1st Qu.:1.400   1st Qu.:0.200   Class :character  
 Median :5.000   Median :3.400   Median :1.500   Median :0.200   Mode  :character  
 Mean   :5.006   Mean   :3.428   Mean   :1.462   Mean   :0.246                     
 3rd Qu.:5.200   3rd Qu.:3.675   3rd Qu.:1.575   3rd Qu.:0.300                     
 Max.   :5.800   Max.   :4.400   Max.   :1.900   Max.   :0.600                     

# sepal length > 5.843
setosa[setosa$sepal.length > 5.843, ]

head(iris[iris$sepal.length > 5.843, ])

library(ggplot2)

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

iris[ ,1 ]

  [1] 5.1 4.9 4.7 4.6 5.0 5.4 4.6 5.0 4.4 4.9 5.4 4.8 4.8 4.3 5.8 5.7 5.4 5.1 5.7 5.1 5.4 5.1 4.6 5.1 4.8 5.0 5.0
 [28] 5.2 5.2 4.7 4.8 5.4 5.2 5.5 4.9 5.0 5.5 4.9 4.4 5.1 5.0 4.5 4.4 5.0 5.1 4.8 5.1 4.6 5.3 5.0 7.0 6.4 6.9 5.5
 [55] 6.5 5.7 6.3 4.9 6.6 5.2 5.0 5.9 6.0 6.1 5.6 6.7 5.6 5.8 6.2 5.6 5.9 6.1 6.3 6.1 6.4 6.6 6.8 6.7 6.0 5.7 5.5
 [82] 5.5 5.8 6.0 5.4 6.0 6.7 6.3 5.6 5.5 5.5 6.1 5.8 5.0 5.6 5.7 5.7 6.2 5.1 5.7 6.3 5.8 7.1 6.3 6.5 7.6 4.9 7.3
[109] 6.7 7.2 6.5 6.4 6.8 5.7 5.8 6.4 6.5 7.7 7.7 6.0 6.9 5.6 7.7 6.3 6.7 7.2 6.2 6.1 6.4 7.2 7.4 7.9 6.4 6.3 6.1
[136] 7.7 6.3 6.4 6.0 6.9 6.7 6.9 5.8 6.8 6.7 6.7 6.3 6.5 6.2 5.9

for (i in 1:4) {
  cat(1, i,  cor(iris[ , 1], iris[, i]), "\n")
}

1 1 1 
1 2 -0.1175698 
1 3 0.8717538 
1 4 0.8179411 

col_names = names(iris)
col_names

[1] "sepal.length" "sepal.width"  "petal.length" "petal.width"  "variety"     

for (c in col_names) {
  print(c)
}

[1] "sepal.length"
[1] "sepal.width"
[1] "petal.length"
[1] "petal.width"
[1] "variety"