R Assignment 02

Question 01

a) Separation of all the strings from given sequences and storing in a variable “gene_seqs”

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

b) Reversion of all the strings in gene_seqs using loop

gene_seqs = unlist(gene_seqs)   # converting list into vector
is.vector(gene_seqs)  # checking if conversion is successful or not
length(gene_seqs) # checking total number of strings in the sequence  

library(stringi)

for (i in 1:7) {
cat("The reverse of string", i,stri_reverse(gene_seqs[i]), "\n")  
}

c) Calculation of length of each string in gene_seqs using loop

for (i in 1:7) {
cat("Total character in string",i ,"is", nchar(gene_seqs[i]), "\n")
}

d) Using loop and condition

for (i in 1:7) {
if (nchar(gene_seqs[i]) > 7) {
    cat("Character numbers of string", i, "is greater than 7.", "Successful \n", "\n", "\n")
  } else {
    cat("Character numbers of string", i, "is lower than 7.", "Error", "\n", "\n", "\n")
  }
}

e) Finding locations and number of occurrences of pattern “GATC” in each string of gene_seqs

for (i in 1:7) {
pattern = "GATC"
    locations = gregexpr(pattern, gene_seqs[i])
  locations = unlist(locations)
 cat("Location of pattern GATC in the String number",i, "is", locations, "\n")
 num_occ = sum(locations != -1)
 cat("Number of occurences of pattern GATC in string number", i, "is", num_occ, "\n", "\n", "\n")
}
  

Bonus: Solving b to e using a single loop

library(stringi)
for (i in 1:7) {
pattern = "GATC"
    locations = gregexpr(pattern, gene_seqs[i])
  locations = unlist(locations)
 cat("Location of pattern GATC in the String number",i, "is", locations, "\n")
 num_occ = sum(locations != -1)
 cat("Number of occurences of string number", i, "is", num_occ, "\n")
  cat("Total character in string",i ,"is", nchar(gene_seqs[i]), "\n")  
cat("The reverse of string", i,stri_reverse(gene_seqs[i]), "\n")  
  if (nchar(gene_seqs[i]) > 7) {
    cat("Character numbers of string", i, "is greater than 7.", "Successful \n", "\n", "\n")
  } 
  else {
    cat("Character numbers of string", i, "is lower than 7.", "Error", "\n", "\n", "\n")
    
  }
}

Question 02

a) Creation of dataframe and addition of two rows and a “Income” column with numerical values

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)

new_row1 = c(6, "Magnus", 25, 99)
new_row2 = c(7, "Hikaru", 24, 96)

Income= c(4500, 4800, 6200, 6500, 7100, 9900, 8500)

exam_score_new = rbind(exam_score, new_row1, new_row2)   # addition of 2 rows
exam_score_ext = cbind(exam_score_new, Income)     # addition of a column
print(exam_score_ext)

exam_score_ext$Age= as.numeric(exam_score_ext$Age)  # conversion into numerical values
exam_score_ext$Score= as.numeric(exam_score_ext$Score)
exam_score_ext$Income= as.numeric(exam_score_ext$Income)

print(exam_score_ext)

b) Arithmetic Operation in Age, Score and Income Column

cat("Max Value of Age", "is",max(exam_score_ext$Age), "\n")
cat("Min Value of Age", "is",min(exam_score_ext$Age), "\n")
cat("Median Value of Age", "is",median(exam_score_ext$Age), "\n")
cat("Summation of Age", "is",sum(exam_score_ext$Age), "\n")
cat("Mean Value of Age", "is",mean(exam_score_ext$Age), "\n")
cat("Standard deviation of Age", "is", sd(exam_score_ext$Age), "\n")
cat("Variance of Age", "is",var(exam_score_ext$Age), "\n")
cat("Quantile Value of Age", "is", quantile(exam_score_ext$Age), "\n", "\n", "\n")



cat("Max Value of Score", "is",max(exam_score_ext$Score), "\n")
cat("Min Value of Score", "is",min(exam_score_ext$Score), "\n")
cat("Median Value of Score", "is",median(exam_score_ext$Score), "\n")
cat("Summation of Score", "is",sum(exam_score_ext$Score), "\n")
cat("Mean Value of Score", "is",mean(exam_score_ext$Score), "\n")
cat("Standard deviation of Score", "is", sd(exam_score_ext$Score), "\n")
cat("Variance of Score", "is",var(exam_score_ext$Score), "\n")
cat("Quantile Value of Score", "is", quantile(exam_score_ext$Score), "\n", "\n", "\n")


cat("Max Value of Income", "is",max(exam_score_ext$Income), "\n")
cat("Min Value of Income", "is",min(exam_score_ext$Income), "\n")
cat("Median Value of Income", "is",median(exam_score_ext$Income), "\n")
cat("Summation of Income", "is",sum(exam_score_ext$Income), "\n")
cat("Mean Value of Income", "is",mean(exam_score_ext$Income), "\n")
cat("Standard deviation of Income", "is", sd(exam_score_ext$Income), "\n")
cat("Variance of Income", "is",var(exam_score_ext$Income), "\n")
cat("Quantile Value of Income", "is", quantile(exam_score_ext$Income), "\n")

b) Arithmetic Operation in Age, Score and Income Column using loop

Here, Column 1,2 and 3 denote Age, Score and Income respectively

x= data.frame(exam_score_ext$Age, exam_score_ext$Score, exam_score_ext$Income)
print(x)
for(i in 1:3){
cat("Max of column",i, "is",max(x[1:7,i]), "\n")
  
cat("Min of column",i, "is",min(x[1:7,i]), "\n")

cat("Median of column",i, "is",median(x[1:7,i]), "\n")
cat("Sum of column",i, "is",sum(x[1:7,i]), "\n")
cat("Mean of column",i, "is",mean(x[1:7,i]), "\n")
cat("Standard deviation of column",i, "is",sd(x[1:7,i]), "\n")
cat("Variance of column",i, "is",var(x[1:7,i]), "\n")
cat("Quantiles of column",i, "is",quantile(x[1:7,i]), "\n","\n","\n")

}

c) Finding Correlation among Age, Score and Income

cat("Correlation between Age and Score is",cor(exam_score_ext$Age, exam_score_ext$Score), "\n", "\n")
cat("Correlation between Age and Income is",cor(exam_score_ext$Age, exam_score_ext$Income), "\n", "\n")
cat("Correlation between Score and Income is",cor(exam_score_ext$Score, exam_score_ext$Income), "\n", "\n")

d) Selection of rows where the score is greater than or equal to 80

exam_score_ext[exam_score_ext$Score >= 80,]

e) Selection of age range form 20 to 30

exam_score_ext[exam_score_ext$Age >= 20 & exam_score_ext$Age <= 30,]