library(dslabs)
data(murders)

#1. Compute the per 100,000 murder rate for each state and store it in an object called murder_rate. Then use logical operators to create a logical vector named low that tells us which entries of murder_rate are lower than 1.

murder_rate <- murders$total / murders$population * 100000
murder_rate
##  [1]  2.8244238  2.6751860  3.6295273  3.1893901  3.3741383  1.2924531
##  [7]  2.7139722  4.2319369 16.4527532  3.3980688  3.7903226  0.5145920
## [13]  0.7655102  2.8369608  2.1900730  0.6893484  2.2081106  2.6732010
## [19]  7.7425810  0.8280881  5.0748655  1.8021791  4.1786225  0.9992600
## [25]  4.0440846  5.3598917  1.2128379  1.7521372  3.1104763  0.3798036
## [31]  2.7980319  3.2537239  2.6679599  2.9993237  0.5947151  2.6871225
## [37]  2.9589340  0.9396843  3.5977513  1.5200933  4.4753235  0.9825837
## [43]  3.4509357  3.2013603  0.7959810  0.3196211  3.1246001  1.3829942
## [49]  1.4571013  1.7056487  0.8871131
low <- murder_rate < 1
low
##  [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE
## [13]  TRUE FALSE FALSE  TRUE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE  TRUE
## [25] FALSE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE  TRUE FALSE
## [37] FALSE  TRUE FALSE FALSE FALSE  TRUE FALSE FALSE  TRUE  TRUE FALSE FALSE
## [49] FALSE FALSE  TRUE

#Q2: Now use the results from the previous exercise and the function which to determine the indices of murder_rate associated with values lower than 1.

murder_rate <- murders$total/murders$population*100000

low <- murder_rate < 1

which(low)
##  [1] 12 13 16 20 24 30 35 38 42 45 46 51

#Q3: Use the results from the previous exercise to report the names of the states with murder rates lower than 1.

murder_rate <- murders$total/murders$population*100000

low <- murder_rate < 1
murders$state[low]
##  [1] "Hawaii"        "Idaho"         "Iowa"          "Maine"        
##  [5] "Minnesota"     "New Hampshire" "North Dakota"  "Oregon"       
##  [9] "South Dakota"  "Utah"          "Vermont"       "Wyoming"

#Q4: Now extend the code from exercise 2 and 3 to report the states in the Northeast with murder rates lower than 1. Hint: use the previously defned logical vector low and the logical operator &.

murder_rate <- murders$total/murders$population*100000
low <- murder_rate < 1
ind <- low & murders$region=='Northeast'
murders$state[ind]
## [1] "Maine"         "New Hampshire" "Vermont"

#Q5: In a previous exercise we computed the murder rate for each state and the average of these numbers. How many states are below the average?

murder_rate <- murders$total/murders$population*100000
avg <- mean(murder_rate)
sum(murder_rate<avg)
## [1] 27

#Q6: Use the match function to identify the states with abbreviations AK, MI, and IA. Hint: start by defining an index of the entries of murders$abb that match the three abbreviations, then use the [ operator to extract the states.

abbs <- c('AK','MI','IA')
ind <- match(abbs , murders$abb)
murders$state[ind]
## [1] "Alaska"   "Michigan" "Iowa"

#Q7: Use the %in% operator to create a logical vector that answers the question: which of the following are actual abbreviations: MA, ME, MI, MO, MU ?

abbs <- c('MA', 'ME', 'MI', 'MO', 'MU')
abbs%in%murders$abb
## [1]  TRUE  TRUE  TRUE  TRUE FALSE

#Q8: Extend the code you used in exercise 7 to report the one entry that is not an actual abbreviation. Hint: use the ! operator, which turns FALSE into TRUE and vice versa, then which to obtain an index.

abbs <- c("MA", "ME", "MI", "MO", "MU") 
ind <- which(!abbs%in%murders$abb)
abbs[ind]
## [1] "MU"
bs5th <- data.frame(
  name = c("Ali", "Ahmad", "Sania", "Sara", "Adil", "sharjeel", "subhan", "arbaz", "athar", "hassan", "waleed"),
  cgpa = c(2.5, 3.2, 3.9, 2.99, 3.10, 2.99, 2.91, 2.87, 3.2, 3.52, 2.50),
  grade = c("D", "B", "A", "C", "D", "A", "B", "B", "B", "A", "D")
)

##(a) which students have cgpa greater than 3

student_with_greater_than_3_cgpa <- bs5th[bs5th$cgpa > 3, ]
print(student_with_greater_than_3_cgpa)
##      name cgpa grade
## 2   Ahmad 3.20     B
## 3   Sania 3.90     A
## 5    Adil 3.10     D
## 9   athar 3.20     B
## 10 hassan 3.52     A

#(b)which student have get “A” grade

students_with_A_grade <- subset(bs5th, grade == "A")
print(students_with_A_grade)
##        name cgpa grade
## 3     Sania 3.90     A
## 6  sharjeel 2.99     A
## 10   hassan 3.52     A

##(c)which student have cgpa >3 and get A

students_cgpa_A <- subset(bs5th, cgpa > 3 & grade == "A")
print(students_cgpa_A)
##      name cgpa grade
## 3   Sania 3.90     A
## 10 hassan 3.52     A

##(d)which student have cgpa >3 or get A

students_cgpa_or_A <- subset(bs5th, cgpa > 3 | grade == "A")
print(students_cgpa_or_A) 
##        name cgpa grade
## 2     Ahmad 3.20     B
## 3     Sania 3.90     A
## 5      Adil 3.10     D
## 6  sharjeel 2.99     A
## 9     athar 3.20     B
## 10   hassan 3.52     A