Assignment 5

Create the code makes a table for each of the below questions.

1. join + filter - Which airplanes fly LGA to XNA (1 POINT)

q1 <- flights %>%
  filter(origin == "LGA", dest == "XNA") %>%
  inner_join(planes, by = "tailnum")
print(q1)

## # A tibble: 66 × 27
##    year.x month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
##     <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
##  1   2013     1     2     1531           1530         1     1846           1805
##  2   2013     1     3      703            705        -2     1014            940
##  3   2013     1     7     1737           1745        -8     2009           2020
##  4   2013     1     9     1736           1745        -9     2008           2020
##  5   2013     1    13     1741           1745        -4     2028           2020
##  6   2013     1    14     1530           1530         0     1914           1805
##  7   2013     1    15     1734           1745       -11     2030           2020
##  8   2013     1    17     1526           1530        -4     1800           1805
##  9   2013     1    18      657            705        -8      923            940
## 10   2013     1    21     1642           1530        72     1937           1805
## # ℹ 56 more rows
## # ℹ 19 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
## #   tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
## #   hour <dbl>, minute <dbl>, time_hour <dttm>, year.y <int>, type <chr>,
## #   manufacturer <chr>, model <chr>, engines <int>, seats <int>, speed <int>,
## #   engine <chr>

2. join - Add the airline name to the flights table (1 POINT)

q2 <- flights %>%
  left_join(airlines, by = "carrier")
print(q2)

## # A tibble: 336,776 × 20
##     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
##  1  2013     1     1      517            515         2      830            819
##  2  2013     1     1      533            529         4      850            830
##  3  2013     1     1      542            540         2      923            850
##  4  2013     1     1      544            545        -1     1004           1022
##  5  2013     1     1      554            600        -6      812            837
##  6  2013     1     1      554            558        -4      740            728
##  7  2013     1     1      555            600        -5      913            854
##  8  2013     1     1      557            600        -3      709            723
##  9  2013     1     1      557            600        -3      838            846
## 10  2013     1     1      558            600        -2      753            745
## # ℹ 336,766 more rows
## # ℹ 12 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
## #   tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
## #   hour <dbl>, minute <dbl>, time_hour <dttm>, name <chr>

3. join + select + distinct() - Which airports have no commercial flights (1 POINT)

q3 <- airports %>%
  left_join(flights, by = c("faa" = "origin")) %>%
  filter(is.na(flight)) %>%
  select(faa, name) %>%
  distinct()
print(q3)

## # A tibble: 1,455 × 2
##    faa   name                          
##    <chr> <chr>                         
##  1 04G   Lansdowne Airport             
##  2 06A   Moton Field Municipal Airport 
##  3 06C   Schaumburg Regional           
##  4 06N   Randall Airport               
##  5 09J   Jekyll Island Airport         
##  6 0A9   Elizabethton Municipal Airport
##  7 0G6   Williams County Airport       
##  8 0G7   Finger Lakes Regional Airport 
##  9 0P2   Shoestring Aviation Airfield  
## 10 0S9   Jefferson County Intl         
## # ℹ 1,445 more rows

4. EXTRA CREDIT - (2 POINT2) - NO HELP - NO PARTIAL CREDIT

Create a table with the names of the airports with the most

winds (wind_speed > 30). The table must contain only the airport

name (airports$name) and no duplicate rows

q4 <- weather %>%
  filter(wind_speed > 30) %>%
  inner_join(airports, by = c("origin" = "faa")) %>%
  select(name) %>%
  distinct()
print(q4)

## # A tibble: 3 × 1
##   name               
##   <chr>              
## 1 Newark Liberty Intl
## 2 John F Kennedy Intl
## 3 La Guardia