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 1.9.4     ✔ 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

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

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

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

flights%>%
  left_join(airlines, by = 'carrier')

## # 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 %>% 
  left_join(flights, by = c('faa'= 'origin'))%>%
  filter(is.na(flight))%>%
  select(name) %>%
  distinct()

## # A tibble: 1,437 × 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
##  7 Williams County Airport       
##  8 Finger Lakes Regional Airport 
##  9 Shoestring Aviation Airfield  
## 10 Jefferson County Intl         
## # ℹ 1,427 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) %>%
  group_by (origin) %>%
  summarise (wind_count =n()) %>%
  left_join(airports, by =c ('origin'= 'faa'))%>%
  distinct()

## # A tibble: 3 × 9
##   origin wind_count name                  lat   lon   alt    tz dst   tzone     
##   <chr>       <int> <chr>               <dbl> <dbl> <dbl> <dbl> <chr> <chr>     
## 1 EWR            14 Newark Liberty Intl  40.7 -74.2    18    -5 A     America/N…
## 2 JFK            37 John F Kennedy Intl  40.6 -73.8    13    -5 A     America/N…
## 3 LGA            20 La Guardia           40.8 -73.9    22    -5 A     America/N…