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)

library(nycflights13)
library(tidyverse)

flights_lga_xna <- flights %>%
  inner_join(airports, by = c("origin" = "faa")) %>%
  inner_join(airports, by = c("dest" = "faa"), suffix = c("_origin", "_dest")) %>%
  filter(origin == 'LGA', dest == 'XNA') %>%
  select(flight, tailnum, origin, dest)

head(flights_lga_xna , 10)

## # A tibble: 10 × 4
##    flight tailnum origin dest 
##     <int> <chr>   <chr>  <chr>
##  1   4534 N722MQ  LGA    XNA  
##  2   4525 N719MQ  LGA    XNA  
##  3   4413 N739MQ  LGA    XNA  
##  4   4534 N719MQ  LGA    XNA  
##  5   4525 N711MQ  LGA    XNA  
##  6   4413 N723MQ  LGA    XNA  
##  7   4534 N711MQ  LGA    XNA  
##  8   4525 N730MQ  LGA    XNA  
##  9   4413 N722MQ  LGA    XNA  
## 10   4534 N719MQ  LGA    XNA

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

flights_with_airline <- inner_join(flights, airlines, by = 'carrier') 

head(flights_with_airline , 10)

## # A tibble: 10 × 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 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)

airports_no_flights <- airports %>%
  anti_join(flights, by = c("faa" = "origin")) %>%
  select(name) %>%
  distinct()

head(airports_no_flights , 10)

## # A tibble: 10 × 1
##    name                          
##    <chr>                         
##  1 Lansdowne Airport             
##  2 Moton Field Municipal Airport 
##  3 Schaumburg Regional           
##  4 Randall Airport               
##  5 Jekyll Island Airport         
##  6 Elizabethton Municipal Airport
##  7 Williams County Airport       
##  8 Finger Lakes Regional Airport 
##  9 Shoestring Aviation Airfield  
## 10 Jefferson County Intl

4. EXTRA CREDIT - (2 POINTS) - 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

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

head(high_wind_airports , 10)

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