R Notebook

Question 1

a) Separation of string

sequence = "ATCGATCGATCG-ATCGAT-CGATC-GATCGAT-CGATCG-ATCGATCG-CGATCG"
gene_seqs = strsplit(sequence, '-')
print(gene_seqs)

[[1]]
[1] "ATCGATCGATCG" "ATCGAT"       "CGATC"        "GATCGAT"      "CGATCG"       "ATCGATCG"     "CGATCG"      

Question b to e in a loop

for(i in gene_seqs) {
  
reverse_seq = stri_reverse(i)
print(reverse_seq) 

seg_len = nchar(i)
print(seg_len)

new_pattern = 'GATC'
location = gregexpr(new_pattern, i)
location = unlist(location)
print(location)

occurance = sum(location != -1)
print(occurance)
}

[1] "GCTAGCTAGCTA" "TAGCTA"       "CTAGC"        "TAGCTAG"      "GCTAGC"       "GCTAGCTA"     "GCTAGC"      
[1] 12  6  5  7  6  8  6
[1]  4  8 -1  2  1  2  4  2
[1] 7

Question 2

exam_score = data.frame(
  ID = c(1, 2, 3, 4, 5),
  Name = c("Alice", "Bob", "David", "John", "Jenny"),
  Age = c(20, 25, 30, 22, 18),
  Score = c(100, 78, 90, 55, 81)
)
print(exam_score)

a) Row addition

new_row = data.frame(
  ID = c(6, 7),
  Name = c("Eli", "Farha"),
  Age = c(22, 16),
  Score = c(60, 85)
)

new_score1 = rbind(exam_score, new_row)
print(new_score1)

a) Column addition

Income = c(1200, 1500, 1100, 2700, 1500, 1750, 2200)
new_score2 = cbind(new_score1, Income)
print(new_score2)

b) Statistics of data frame

cat("Maximum of age ", max(new_score2[ ,3]), "Maximum of score ", max(new_score2[ ,4]), "Maximum of income ", max(new_score2[ ,5]), "\n")

Maximum of age  30 Maximum of score  100 Maximum of income  2700 

cat("Minimum of age ", min(new_score2[ ,3]), "Minimum of score ", min(new_score2[ ,4]), "Minimum of income ", min(new_score2[ ,5]), "\n")

Minimum of age  16 Minimum of score  55 Minimum of income  1100 

cat("Median of age ", median(new_score2[ ,3]), "Median of score ", median(new_score2[ ,4]), "Median of income ", median(new_score2[ ,5]), "\n")

Median of age  22 Median of score  81 Median of income  1500 

cat("Sum of age ", sum(new_score2[ ,3]), "Sum of score ", sum(new_score2[ ,4]), "Sum of income ", sum(new_score2[ ,5]), "\n")

Sum of age  153 Sum of score  549 Sum of income  11950 

cat("Mean of age ", mean(new_score2[ ,3]), "Mean of score ", mean(new_score2[ ,4]), "Mean of income ", mean(new_score2[ ,5]), "\n")

Mean of age  21.85714 Mean of score  78.42857 Mean of income  1707.143 

cat("Standar deviation of age ", sd(new_score2[ ,3]), "Standar deviation of score ", sd(new_score2[ ,4]), "Standar deviation of income ", sd(new_score2[ ,5]), "\n")

Standar deviation of age  4.634241 Standar deviation of score  16.00893 Standar deviation of income  568.938 

cat("variance of age ", var(new_score2[ ,3]), "Variance of score ", var(new_score2[ ,4]), "variance of income ", var(new_score2[ ,5]), "\n")

variance of age  21.47619 Variance of score  256.2857 variance of income  323690.5 

cat("Quantile of age ",quantile(new_score2[ ,3]), "Quantile of score ", quantile(new_score2[ ,4]), "Quantile of income ", quantile(new_score2[ ,5]))

Quantile of age  16 19 22 23.5 30 Quantile of score  55 69 81 87.5 100 Quantile of income  1100 1350 1500 1975 2700

c) Correlation

correlationi = cor(new_score2$Age, new_score2$Score)
print(correlationi)

[1] -0.003530227

correlationii = cor(new_score2$Age, new_score2$Income)
print(correlationii)

[1] -0.4167531

correlationiii = cor(new_score2$Score, new_score2$Income)
print(correlationiii)

[1] -0.7177034

d) Conditional selection

new_score2[new_score2$Score >=80, ]

e) Conditional selection with range

new_score2[new_score2$Age > 20 & new_score2$Age < 30, ]