Assignment 5

library(nycflights13)
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Question 1

flights_lga_xna <- flights %>%
  filter(origin == "LGA", dest == "XNA") %>%
  select(flight, tailnum)

flights_lga_xna

## # A tibble: 745 × 2
##    flight tailnum
##     <int> <chr>  
##  1   4534 N722MQ 
##  2   4525 N719MQ 
##  3   4413 N739MQ 
##  4   4534 N719MQ 
##  5   4525 N711MQ 
##  6   4413 N723MQ 
##  7   4534 N711MQ 
##  8   4525 N730MQ 
##  9   4413 N722MQ 
## 10   4534 N719MQ 
## # ℹ 735 more rows

head(flights_lga_xna)

## # A tibble: 6 × 2
##   flight tailnum
##    <int> <chr>  
## 1   4534 N722MQ 
## 2   4525 N719MQ 
## 3   4413 N739MQ 
## 4   4534 N719MQ 
## 5   4525 N711MQ 
## 6   4413 N723MQ

Question 2

flights_with_airline <- flights %>%
  left_join(airlines, by = "carrier") %>%
  select(flight, airline_name = name, everything())

flights_with_airline

## # A tibble: 336,776 × 20
##    flight airline_name        year month   day dep_time sched_dep_time dep_delay
##     <int> <chr>              <int> <int> <int>    <int>          <int>     <dbl>
##  1   1545 United Air Lines …  2013     1     1      517            515         2
##  2   1714 United Air Lines …  2013     1     1      533            529         4
##  3   1141 American Airlines…  2013     1     1      542            540         2
##  4    725 JetBlue Airways     2013     1     1      544            545        -1
##  5    461 Delta Air Lines I…  2013     1     1      554            600        -6
##  6   1696 United Air Lines …  2013     1     1      554            558        -4
##  7    507 JetBlue Airways     2013     1     1      555            600        -5
##  8   5708 ExpressJet Airlin…  2013     1     1      557            600        -3
##  9     79 JetBlue Airways     2013     1     1      557            600        -3
## 10    301 American Airlines…  2013     1     1      558            600        -2
## # ℹ 336,766 more rows
## # ℹ 12 more variables: arr_time <int>, sched_arr_time <int>, arr_delay <dbl>,
## #   carrier <chr>, tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>,
## #   distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>

head(flights_with_airline)

## # A tibble: 6 × 20
##   flight airline_name         year month   day dep_time sched_dep_time dep_delay
##    <int> <chr>               <int> <int> <int>    <int>          <int>     <dbl>
## 1   1545 United Air Lines I…  2013     1     1      517            515         2
## 2   1714 United Air Lines I…  2013     1     1      533            529         4
## 3   1141 American Airlines …  2013     1     1      542            540         2
## 4    725 JetBlue Airways      2013     1     1      544            545        -1
## 5    461 Delta Air Lines In…  2013     1     1      554            600        -6
## 6   1696 United Air Lines I…  2013     1     1      554            558        -4
## # ℹ 12 more variables: arr_time <int>, sched_arr_time <int>, arr_delay <dbl>,
## #   carrier <chr>, tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>,
## #   distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>

Question 3

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

airports_no_flights

## # A tibble: 1,437 × 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         
## # ℹ 1,427 more rows

head(airports_no_flights)

## # A tibble: 6 × 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

Question 4 Extra Credit

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

windy_airports

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

head(windy_airports)

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