AssignmentJoins

library(nycflights13) 
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.6
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.2     ✔ tibble    3.3.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.2
## ✔ purrr     1.2.1     
## ── 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_to_xna_planes <- flights %>%
  filter(origin == "LGA", dest == "XNA") %>%
  inner_join(planes, by = "tailnum")

head(lga_to_xna_planes)

## # A tibble: 6 × 27
##   year.x 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     2     1531           1530         1     1846           1805
## 2   2013     1     3      703            705        -2     1014            940
## 3   2013     1     7     1737           1745        -8     2009           2020
## 4   2013     1     9     1736           1745        -9     2008           2020
## 5   2013     1    13     1741           1745        -4     2028           2020
## 6   2013     1    14     1530           1530         0     1914           1805
## # ℹ 19 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>, year.y <int>, type <chr>,
## #   manufacturer <chr>, model <chr>, engines <int>, seats <int>, speed <int>,
## #   engine <chr>

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

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

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)

airports_no_flights <- airports %>%
  anti_join(flights, by = c("faa" = "dest")) %>%
  select(name) %>%
  distinct()

head(airports_no_flights)

## # 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

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

head(high_wind_airports)

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