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

R Markdown

Including Plots

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

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

flights_planes <- flights %>%
  inner_join(planes, by = "tailnum")
lga_to_xna_flights <- flights_planes %>%
  filter(origin == "LGA", dest == "XNA") %>%
  select(tailnum, manufacturer, model, year = year.y) %>% 
  distinct()
# View the result
lga_to_xna_flights
## # A tibble: 4 × 4
##   tailnum manufacturer         model        year
##   <chr>   <chr>                <chr>       <int>
## 1 N711MQ  GULFSTREAM AEROSPACE G1159B       1976
## 2 N737MQ  CESSNA               172N         1977
## 3 N840MQ  CANADAIR LTD         CF-5D        1974
## 4 N713EV  BOMBARDIER INC       CL-600-2C10  2003

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

flights_with_airline <- flights %>%
  inner_join(airlines, by = "carrier") %>%
  select(flight, carrier, name, everything())  # 'name' is the airline name

# View the result
flights_with_airline
## # A tibble: 336,776 × 20
##    flight carrier name        year month   day dep_time sched_dep_time dep_delay
##     <int> <chr>   <chr>      <int> <int> <int>    <int>          <int>     <dbl>
##  1   1545 UA      United Ai…  2013     1     1      517            515         2
##  2   1714 UA      United Ai…  2013     1     1      533            529         4
##  3   1141 AA      American …  2013     1     1      542            540         2
##  4    725 B6      JetBlue A…  2013     1     1      544            545        -1
##  5    461 DL      Delta Air…  2013     1     1      554            600        -6
##  6   1696 UA      United Ai…  2013     1     1      554            558        -4
##  7    507 B6      JetBlue A…  2013     1     1      555            600        -5
##  8   5708 EV      ExpressJe…  2013     1     1      557            600        -3
##  9     79 B6      JetBlue A…  2013     1     1      557            600        -3
## 10    301 AA      American …  2013     1     1      558            600        -2
## # ℹ 336,766 more rows
## # ℹ 11 more variables: arr_time <int>, sched_arr_time <int>, arr_delay <dbl>,
## #   tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
## #   hour <dbl>, minute <dbl>, time_hour <dttm>

3. join + select + distinct() - Which airports have no commercial flights (1 POINT)

commercial_airports <- flights %>%
  select(origin, dest) %>%
  pivot_longer(cols = c(origin, dest), values_to = "faa") %>%  # Combine origin and dest into one column
  distinct(faa)

airports_no_flights <- airports %>%
  anti_join(commercial_airports, by = "faa")  # Keep airports not in commercial_airports
# View the resulting table
airports_no_flights
## # A tibble: 1,355 × 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/…
##  2 06A   Moton Field Municipal Airport   32.5  -85.7   264    -6 A     America/…
##  3 06C   Schaumburg Regional             42.0  -88.1   801    -6 A     America/…
##  4 06N   Randall Airport                 41.4  -74.4   523    -5 A     America/…
##  5 09J   Jekyll Island Airport           31.1  -81.4    11    -5 A     America/…
##  6 0A9   Elizabethton Municipal Airport  36.4  -82.2  1593    -5 A     America/…
##  7 0G6   Williams County Airport         41.5  -84.5   730    -5 A     America/…
##  8 0G7   Finger Lakes Regional Airport   42.9  -76.8   492    -5 A     America/…
##  9 0P2   Shoestring Aviation Airfield    39.8  -76.6  1000    -5 U     America/…
## 10 0S9   Jefferson County Intl           48.1 -123.    108    -8 A     America/…
## # 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

windy_weather <- weather %>%
  filter(wind_speed > 30) %>%
  distinct(origin)  # Select distinct origins with wind_speed > 30

windy_airports <- windy_weather %>%
  inner_join(airports, by = c("origin" = "faa")) %>%
  select(name) %>%
  distinct()  # Ensure no duplicate rows
# View the resulting table
windy_airports
## # A tibble: 3 × 1
##   name               
##   <chr>              
## 1 Newark Liberty Intl
## 2 John F Kennedy Intl
## 3 La Guardia