Data 3210 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)

q1 <- flights %>%
filter(origin == "LGA", dest == "XNA") %>%
  select(tailnum) %>% 
  left_join( planes, by = "tailnum") %>% 
  select(tailnum, model, manufacturer) %>% 
  distinct()

head(q1)

## # A tibble: 6 × 3
##   tailnum model  manufacturer        
##   <chr>   <chr>  <chr>               
## 1 N722MQ  <NA>   <NA>                
## 2 N719MQ  <NA>   <NA>                
## 3 N739MQ  <NA>   <NA>                
## 4 N711MQ  G1159B GULFSTREAM AEROSPACE
## 5 N723MQ  <NA>   <NA>                
## 6 N730MQ  <NA>   <NA>

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

q2 <- flights %>%
    left_join(airlines, by = "carrier")

head(q2)

## # 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)

q3 <- airports %>% 
  anti_join(flights , by = c('faa' = 'origin')) %>% 
  anti_join(flights , by = c('faa' = 'dest'))

head (q3)

## # 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…