A5

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

1. Join + Filter - Which airplanes fly LGA to XNA

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

lga_to_xna

## # A tibble: 70 × 1
##    tailnum
##    <chr>  
##  1 N722MQ 
##  2 N719MQ 
##  3 N739MQ 
##  4 N711MQ 
##  5 N723MQ 
##  6 N730MQ 
##  7 N734MQ 
##  8 N725MQ 
##  9 N736MQ 
## 10 N737MQ 
## # ℹ 60 more rows

2. Join - Add the airline name to the flights table

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

flights_with_airlines

## # 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

commercial_flight_airports <- flights %>%
  select(origin, dest) %>%
  pivot_longer(cols = c(origin, dest), names_to = "type", values_to = "faa") %>%
  distinct(faa)

airports_with_no_commercial_flights <- airports %>%
  anti_join(commercial_flight_airports, by = "faa") %>%
  select(faa, name)

airports_with_no_commercial_flights

## # A tibble: 1,355 × 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 1,345 more rows

4. EXTRA CREDIT - Names of airports with the most winds (wind_speed > 30)

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

airports_with_high_winds

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