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
install.packages("dplyr")
## Warning: package 'dplyr' is in use and will not be installed
library(dplyr)

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

q1 <- flights %>%
  filter(origin == "LGA", dest == "XNA") %>%
  left_join(airlines, by = "carrier") %>%    # Join with airlines to get airline names
  select(year, month, day, carrier, name, flight, tailnum, dep_time, arr_time)

print(q1)
## # A tibble: 745 × 9
##     year month   day carrier name      flight tailnum dep_time arr_time
##    <int> <int> <int> <chr>   <chr>      <int> <chr>      <int>    <int>
##  1  2013     1     1 MQ      Envoy Air   4534 N722MQ       656     1007
##  2  2013     1     1 MQ      Envoy Air   4525 N719MQ      1525     1934
##  3  2013     1     1 MQ      Envoy Air   4413 N739MQ      1740     2158
##  4  2013     1     2 MQ      Envoy Air   4534 N719MQ       656     1014
##  5  2013     1     2 MQ      Envoy Air   4525 N711MQ      1531     1846
##  6  2013     1     2 MQ      Envoy Air   4413 N723MQ      1740     2035
##  7  2013     1     3 MQ      Envoy Air   4534 N711MQ       703     1014
##  8  2013     1     3 MQ      Envoy Air   4525 N730MQ      1525     1802
##  9  2013     1     3 MQ      Envoy Air   4413 N722MQ      1737     1953
## 10  2013     1     4 MQ      Envoy Air   4534 N719MQ       701      934
## # ℹ 735 more rows

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

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

print(q2)
## # 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)

#Step One: Collect all data

q3_with_flights <- flights %>%
  select(origin, dest) %>%
  distinct() %>%
  rename(flight_airport = origin) %>%
  bind_rows(rename(flights, flight_airport = dest) %>% select(flight_airport)) %>%
  distinct()

#Step Two: Identify Airports without flights

q3_no_flights <- airports %>%
  anti_join(q3_with_flights, by = c("faa" = "flight_airport")) %>%
  select(faa, name, lat, lon, tz, alt)


print(q3_no_flights)
## # A tibble: 1,355 × 6
##    faa   name                             lat    lon    tz   alt
##    <chr> <chr>                          <dbl>  <dbl> <dbl> <dbl>
##  1 04G   Lansdowne Airport               41.1  -80.6    -5  1044
##  2 06A   Moton Field Municipal Airport   32.5  -85.7    -6   264
##  3 06C   Schaumburg Regional             42.0  -88.1    -6   801
##  4 06N   Randall Airport                 41.4  -74.4    -5   523
##  5 09J   Jekyll Island Airport           31.1  -81.4    -5    11
##  6 0A9   Elizabethton Municipal Airport  36.4  -82.2    -5  1593
##  7 0G6   Williams County Airport         41.5  -84.5    -5   730
##  8 0G7   Finger Lakes Regional Airport   42.9  -76.8    -5   492
##  9 0P2   Shoestring Aviation Airfield    39.8  -76.6    -5  1000
## 10 0S9   Jefferson County Intl           48.1 -123.     -8   108
## # 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

#Step one: Filter Data

high_wind_weather <- weather %>%
  filter(wind_speed > 30)

#Step two: Join High Wind Data with Airports

q4 <- high_wind_weather %>%
  select(origin) %>%
  distinct() %>%
  left_join(airports, by = c("origin" = "faa")) %>%
  select(name) %>%
  distinct()

print(q4)
## # A tibble: 3 × 1
##   name               
##   <chr>              
## 1 Newark Liberty Intl
## 2 John F Kennedy Intl
## 3 La Guardia