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   1.5.2
## ✔ ggplot2   4.0.0     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── 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 (1 POINT)

lga_xna_flights <- flights %>%
  filter(origin == "LGA", dest == "XNA")

lga_xna_planes <- lga_xna_flights %>%
  left_join(planes, by = "tailnum") %>% 
  select(tailnum) %>% 
  distinct()

head(lga_xna_planes)
## # A tibble: 6 × 1
##   tailnum
##   <chr>  
## 1 N722MQ 
## 2 N719MQ 
## 3 N739MQ 
## 4 N711MQ 
## 5 N723MQ 
## 6 N730MQ

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

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

flights_with_airline %>%
  select(carrier, name) %>%
  distinct()
## # A tibble: 16 × 2
##    carrier name                       
##    <chr>   <chr>                      
##  1 UA      United Air Lines Inc.      
##  2 AA      American Airlines Inc.     
##  3 B6      JetBlue Airways            
##  4 DL      Delta Air Lines Inc.       
##  5 EV      ExpressJet Airlines Inc.   
##  6 MQ      Envoy Air                  
##  7 US      US Airways Inc.            
##  8 WN      Southwest Airlines Co.     
##  9 VX      Virgin America             
## 10 FL      AirTran Airways Corporation
## 11 AS      Alaska Airlines Inc.       
## 12 9E      Endeavor Air Inc.          
## 13 F9      Frontier Airlines Inc.     
## 14 HA      Hawaiian Airlines Inc.     
## 15 YV      Mesa Airlines Inc.         
## 16 OO      SkyWest Airlines Inc.
head(flights_with_airline)
## # A tibble: 6 × 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
## # 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)

used_airports <- flights %>%
  select(origin, dest) %>%
  distinct() %>%
  rename(faa = origin)

unused_airports <- airports %>%
  anti_join(used_airports, by = "faa")

head(unused_airports)
## # A tibble: 6 × 8
##   faa   name                             lat   lon   alt    tz dst   tzone      
##   <chr> <chr>                          <dbl> <dbl> <dbl> <dbl> <chr> <chr>      
## 1 04G   Lansdowne Airport               41.1 -80.6  1044    -5 A     America/Ne…
## 2 06A   Moton Field Municipal Airport   32.5 -85.7   264    -6 A     America/Ch…
## 3 06C   Schaumburg Regional             42.0 -88.1   801    -6 A     America/Ch…
## 4 06N   Randall Airport                 41.4 -74.4   523    -5 A     America/Ne…
## 5 09J   Jekyll Island Airport           31.1 -81.4    11    -5 A     America/Ne…
## 6 0A9   Elizabethton Municipal Airport  36.4 -82.2  1593    -5 A     America/Ne…

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

high_wind_airports <- weather %>%
  filter(wind_speed > 30) %>%
  inner_join(airports, by = c("origin" = "faa")) %>%
  select(name) %>%
  distinct()
high_wind_airports
## # A tibble: 3 × 1
##   name               
##   <chr>              
## 1 Newark Liberty Intl
## 2 John F Kennedy Intl
## 3 La Guardia