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)

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

planes_lga_xna

## # A tibble: 4 × 3
##   tailnum manufacturer         model      
##   <chr>   <chr>                <chr>      
## 1 N711MQ  GULFSTREAM AEROSPACE G1159B     
## 2 N737MQ  CESSNA               172N       
## 3 N840MQ  CANADAIR LTD         CF-5D      
## 4 N713EV  BOMBARDIER INC       CL-600-2C10

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

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

flights_with_airline_names

## # 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)

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

airports_no_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 - (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

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

airports_high_winds

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