Assignment5DATA3210

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")

head(Q1)

## # A tibble: 6 × 19
##    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      656            705        -9     1007            940
## 2  2013     1     1     1525           1530        -5     1934           1805
## 3  2013     1     1     1740           1745        -5     2158           2020
## 4  2013     1     2      656            705        -9     1014            940
## 5  2013     1     2     1531           1530         1     1846           1805
## 6  2013     1     2     1740           1745        -5     2035           2020
## # ℹ 11 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>

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" = "dest")) %>% 
  select(name) %>% 
  distinct()

head(Q3)

## # A tibble: 6 × 1
##   name                          
##   <chr>                         
## 1 Lansdowne Airport             
## 2 Moton Field Municipal Airport 
## 3 Schaumburg Regional           
## 4 Randall Airport               
## 5 Jekyll Island Airport         
## 6 Elizabethton Municipal Airport

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

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

head(XTRA)

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