Class 2

string

pattern matching

print(matches)

[1] FALSE

split

genes = 'gene1,gene2,gene3'

gene_split = strsplit(genes, ',')

print (gene_split)

[[1]]
[1] "gene1" "gene2" "gene3"

reverse string

library(stringi)
s1 = 'abvhfsnjg'
rev_string = stri_reverse(s1)
print (rev_string)

[1] "gjnsfhvba"

number of occurances

DNA = 'ATGCATGCGCATGTTCG'
pattern = 'ATG'

locations = gregexpr(pattern, DNA)
locations = unlist(locations)
print (locations)

[1]  1  5 11

num_OF_occ = sum (locations != -1)
print (num_OF_occ)

[1] 3

Vector (list of information)

Create

ages = c(10, 25, 30, 40, 45)
print(ages)

[1] 10 25 30 40 45

Indexing

Third bracket means location + value means oi location

ages[3]

[1] 30

• value means oita bad

ages[-3]

[1] 10 25 40 45

Append

new info ager tay add korte chaile

ages_extended = c(ages, 100, 200)
ages_extended

[1]  10  25  30  40  45 100 200

ages_extended = c(ages, c(15, 25, 20, 30))
ages_extended

[1] 10 25 30 40 45 15 25 20 30

Slice or Subset

(:) this means location from

print(ages)

[1] 10 25 30 40 45

print(ages[2:3])

[1] 25 30

Length

print(length(ages))

[1] 5

Insert in a specific position

print(ages)

[1] 10 25 30 40 45

print(ages[1:2])

[1] 10 25

print(ages[3:5])

[1] 30 40 45

ages_extended = c(ages[1:2], 99, ages[3:5])
ages_extended

[1] 10 25 99 30 40 45

Vector conditional

ages

[1] 10 25 30 40 45

eligible_participant = ages[ages < 40]
eligible_participant

[1] 10 25 30

eligible_participant = ages[ages <= 40]
eligible_participant

[1] 10 25 30 40

#If we want to take 20 to 40
ages_20 = ages[ages >= 20]
ages_20

[1] 25 30 40 45

ages20_40 = ages_20[ages_20 <= 40]
ages20_40

[1] 25 30 40

# same like before
## or conditional

ages[ages >= 20 & ages <= 40]

[1] 25 30 40

Sorting

# bu default increasing order
sort(ages)

[1] 10 25 30 40 45

# for decrasing order
sort(ages, TRUE)

[1] 45 40 30 25 10

Simple Statistics

print(ages)

[1] 10 25 30 40 45

print(max(ages))

[1] 45

print(min(ages))

[1] 10

print(mean(ages))

[1] 30

# median
print(median(ages))

[1] 30

#sum
print(sum(ages))

[1] 150

# standard deviation
print(sd(ages))

[1] 13.69306

# variance
print(var(ages))

[1] 187.5

# percentile
print(quantile(ages))

  0%  25%  50%  75% 100% 
  10   25   30   40   45 

Corelation

ages

[1] 10 25 30 40 45

score = c(10, 20, 30, 40, 50)
length(score)

[1] 5

cor(ages, score) 

[1] 0.9814955

portion

ages

[1] 10 25 30 40 45

max(ages[2:5])

[1] 45

Data Frame

Exam_score = data.frame(
  ID = c(1, 2, 3, 4, 5),
  Name = c("Era", "Ema", "Ali", "Jon", "Jia"),
  Age = c(22, 23, 24, 25, 26),
  Score = c(15, 20, 25, 35, 40)
)
print(Exam_score)

#comma need after every column
#c er under er gulo row

Split from data set

# vector [location]
# data set [row,colm]
Exam_score[2:4, ]

Exam_score[2, ]

Exam_score[ ,3:4]

Split from data set another way

using vector

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

For selecting two distant column

#HERE $ means colum selector
Exam_score$Name

[1] "Era" "Ema" "Ali" "Jon" "Jia"

Exam_score$Score

[1] 15 20 25 35 40

Selected_column = data.frame(
  Name = Exam_score$Name,
  Score = Exam_score$Score
)
Selected_column

Row selection using range

Exam_score[Exam_score$Score > 20, ]

Exam_score[Exam_score$Score > 20 & Exam_score$Score < 40, ]

Sublist

selected_ID = c(1, 3)
Exam_score[Exam_score$ID %in% selected_ID, ]

New Row add

Exam_score

New_row = c(5, "Zen", 55, 89)
Exam_score2 = rbind(Exam_score, New_row)
Exam_score2

New Column

New_col = c("dhk", "Ctg","dhk", "Ctg","dhk")
cbind(Exam_score,New_col)