install.packages(“nycflights13”) install.packages(“tidyverse”)
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.2
## ✔ ggplot2 4.0.0 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.1.0
## ── 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 errorslibrary(nycflights13)# 1. Planes that fly from LGA to XNA
lga_to_xna_planes <- flights %>%
filter(origin == "LGA", dest == "XNA") %>%
select(tailnum) %>%
distinct()
lga_to_xna_planes## # A tibble: 70 × 1
## tailnum
## <chr>
## 1 N722MQ
## 2 N719MQ
## 3 N739MQ
## 4 N711MQ
## 5 N723MQ
## 6 N730MQ
## 7 N734MQ
## 8 N725MQ
## 9 N736MQ
## 10 N737MQ
## # ℹ 60 more rows# 2. Join airline names to flights
flights_with_airline <- flights %>%
left_join(airlines, by = "carrier")
flights_with_airline## # 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. Airports with no commercial flights
airports_with_flights <- flights %>%
select(origin) %>%
distinct() %>%
rename(faa = origin)
airports_no_flights <- airports %>%
anti_join(airports_with_flights, by = "faa") %>%
select(name) %>%
distinct()
airports_no_flights## # 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. Airports with wind speeds greater than 30
high_wind_airports <- weather %>%
filter(wind_speed > 30) %>%
select(origin) %>%
distinct() %>%
left_join(airports, by = c("origin" = "faa")) %>%
select(name) %>%
distinct()
high_wind_airports## # A tibble: 3 × 1
## name
## <chr>
## 1 Newark Liberty Intl
## 2 John F Kennedy Intl
## 3 La Guardia