Before starting...

• You can write your own answer in each question

• Don't forget to import library data.table

library(data.table)

• We will use flights data in nycflights13 library and remove NA

library(nycflights13)
data("flights")
flights <- as.data.table(flights) |> na.exclude()

Question 1

Get all the flights in the May 15th

ans <- flights[month == 5 & day == 15]

Question 2

Sort flights first by column 'month' in ascending order, and then by 'day' in decending order

ans <- flights[order(month, -day)]

Question 3

Select both arr_delay and dep_delay columns

ans <- flights[, .(arr_delay, dep_delay)]
head(ans)

##    arr_delay dep_delay
## 1:        11         2
## 2:        20         4
## 3:        33         2
## 4:       -18        -1
## 5:       -25        -6
## 6:        12        -4

Question 4

How many trips have had total delay(arr_delay + dep_delay) > 0?

ans <- flights[, sum( (arr_delay + dep_delay) > 0 )]
ans

## [1] 135059

Question 5

Calculate the average arrival and departure delay for all flights in the may 15th

ans <- flights[month == 5 & day == 15,
               .(m_arr = mean(arr_delay), m_dep = mean(dep_delay))]
ans

##        m_arr    m_dep
## 1: -2.029598 9.809725

Question 6

How can get the number of trips corresponding to each origin airport?

ans <- flights[, .(.N), by = .(origin)]
ans

##    origin      N
## 1:    EWR 117127
## 2:    LGA 101140
## 3:    JFK 109079

Question 7

How can we get the average arrival and departure delay for each origin and month?

ans <- flights[,
        .(mean(arr_delay), mean(dep_delay)),
        by = .(origin, month)]