loading the library and data
library(dslabs)
data(murders)
Question#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.
murders_rate <- murders$total / murders$population * 100000
low <-murders_rate < 1
murders_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
## [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
Question#2:
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
low_indixes <- which(low)
low_indixes
## [1] 12 13 16 20 24 30 35 38 42 45 46 51
Question#3:
results from the previous exercise to report the names of the states with murder rates lower than 1.
low_states<-murders$state[low_indixes]
low_states
## [1] "Hawaii" "Idaho" "Iowa" "Maine"
## [5] "Minnesota" "New Hampshire" "North Dakota" "Oregon"
## [9] "South Dakota" "Utah" "Vermont" "Wyoming"
Question#4:
Now extend the code from exercise 2 and 3 to report the states in the Northeast with murder rates lower than 1. Hint: use the previously defned logical vector low and the logical operator &.
ne <- murders$region == "Northeast"
ne_low <- ne & low
ne_low_state_names <- murders$state[ne_low]
ne_low_state_names
## [1] "Maine" "New Hampshire" "Vermont"
Question#5:
In a previous exercise we computed the murder rate for each state and the average of these numbers. How many states are below the average?
average_murders_rate <- mean(murders_rate)
below_average <- murders_rate < average_murders_rate
num_states_below_average <- sum(below_average)
num_states_below_average
## [1] 27
Question#6:
Use the match function to identify the states with abbreviations AK, MI, and IA. Hint: start by defning an index of the entries of murders$abb that match the three abbreviations, then use the [ operator to extract the states.
abbreviations <- c("AK", "MI", "IA")
match_indixes <- match(abbreviations, murders$abb)
match_states<- murders$state[match_indixes]
cat("States with Abbreviations AK, MI, and IA:\n")
## States with Abbreviations AK, MI, and IA:
print(match_states)
## [1] "Alaska" "Michigan" "Iowa"
Question#7:
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 ?
valid_abb<- state.abb
abbcheck <- c("MA", "ME", "MI", "MO", "MU")
valid_abbreviations <- abbcheck %in% valid_abb
cat("Valid Abbreviations:\n")
## Valid Abbreviations:
print(valid_abbreviations)
## [1] TRUE TRUE TRUE TRUE FALSE
Question#8:
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
not_val_index <- which(!valid_abbreviations)
not_val_index
## [1] 5
Creating a New dataframe having names,cgpa and grades of students
names<-c("Ali","Ahmad","Sania","Sara","Adil","Sharjeel","Subhan","Arbaz","Asad","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','B','A','B','B','B','A','D')
students<-data.frame(names,cgpa,grade)
students
## names cgpa grade
## 1 Ali 2.50 D
## 2 Ahmad 3.20 B
## 3 Sania 3.90 A
## 4 Sara 2.99 C
## 5 Adil 3.10 B
## 6 Sharjeel 2.99 A
## 7 Subhan 2.91 B
## 8 Arbaz 2.87 B
## 9 Asad 3.20 B
## 10 Hassan 3.52 A
## 11 Waleed 2.50 D
a: Selecting students with cgpa greater Or equal to 3.10
cgpa<-students$cgpa<=3.10
indeces<-which(cgpa)
students_names<-students$names[indeces]
students_names
## [1] "Ali" "Sara" "Adil" "Sharjeel" "Subhan" "Arbaz" "Waleed"
b: Selecting students with grade B
grade<-students$grade=='B'
indexes<-which(grade)
students_names<-students$names[indexes]
students_names
## [1] "Ahmad" "Adil" "Subhan" "Arbaz" "Asad"
c: Selecting students having cgpa grater to 3.1 and grade A
a<-students$cgpa>3.1 & students$grade=='A'
indexes<-which(a)
students_names<-students$names[indexes]
students_names
## [1] "Sania" "Hassan"