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

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

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

lga_to_xna_planes <- flights %>%
  filter(origin == "LGA", dest == "XNA") %>%
  left_join(planes, by = "tailnum") %>% 
  select(tailnum, manufacturer, model, origin, dest) %>% 
  distinct()

lga_to_xna_planes

## # A tibble: 70 × 5
##    tailnum manufacturer         model  origin dest 
##    <chr>   <chr>                <chr>  <chr>  <chr>
##  1 N722MQ  <NA>                 <NA>   LGA    XNA  
##  2 N719MQ  <NA>                 <NA>   LGA    XNA  
##  3 N739MQ  <NA>                 <NA>   LGA    XNA  
##  4 N711MQ  GULFSTREAM AEROSPACE G1159B LGA    XNA  
##  5 N723MQ  <NA>                 <NA>   LGA    XNA  
##  6 N730MQ  <NA>                 <NA>   LGA    XNA  
##  7 N734MQ  <NA>                 <NA>   LGA    XNA  
##  8 N725MQ  <NA>                 <NA>   LGA    XNA  
##  9 N736MQ  <NA>                 <NA>   LGA    XNA  
## 10 N737MQ  CESSNA               172N   LGA    XNA  
## # ℹ 60 more rows

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

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

flights_with_airline

## # 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)

# Get a list of all airports with flights
airports_with_flights <- flights %>%
  distinct(origin) %>%
  bind_rows(flights %>% distinct(dest) %>% rename(origin = dest))

# Find airports with no commercial flights
airports_no_flights <- airports %>%
  filter(!faa %in% airports_with_flights$origin) %>%
  select(name, faa) %>%
  distinct()

airports_no_flights

## # A tibble: 1,355 × 2
##    name                           faa  
##    <chr>                          <chr>
##  1 Lansdowne Airport              04G  
##  2 Moton Field Municipal Airport  06A  
##  3 Schaumburg Regional            06C  
##  4 Randall Airport                06N  
##  5 Jekyll Island Airport          09J  
##  6 Elizabethton Municipal Airport 0A9  
##  7 Williams County Airport        0G6  
##  8 Finger Lakes Regional Airport  0G7  
##  9 Shoestring Aviation Airfield   0P2  
## 10 Jefferson County Intl          0S9  
## # ℹ 1,345 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

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

airports_high_wind

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