R Markdown
library(nycflights13)
## Warning: package 'nycflights13' was built under R version 4.4.2
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") %>%
inner_join(planes, by = "tailnum") %>%
select(tailnum, manufacturer, model, engine)
print(q1)
## # A tibble: 66 × 4
## tailnum manufacturer model engine
## <chr> <chr> <chr> <chr>
## 1 N711MQ GULFSTREAM AEROSPACE G1159B Turbo-jet
## 2 N711MQ GULFSTREAM AEROSPACE G1159B Turbo-jet
## 3 N711MQ GULFSTREAM AEROSPACE G1159B Turbo-jet
## 4 N711MQ GULFSTREAM AEROSPACE G1159B Turbo-jet
## 5 N711MQ GULFSTREAM AEROSPACE G1159B Turbo-jet
## 6 N737MQ CESSNA 172N Reciprocating
## 7 N737MQ CESSNA 172N Reciprocating
## 8 N711MQ GULFSTREAM AEROSPACE G1159B Turbo-jet
## 9 N711MQ GULFSTREAM AEROSPACE G1159B Turbo-jet
## 10 N840MQ CANADAIR LTD CF-5D Turbo-jet
## # ℹ 56 more rows
2. join - Add the airline name to the flights table (1 POINT)
q2 <- flights %>%
inner_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)
q3a <- flights %>%
select(origin) %>%
distinct() %>%
rename(faa = origin)
print(q3a)
## # A tibble: 3 × 1
## faa
## <chr>
## 1 EWR
## 2 LGA
## 3 JFK
q3b <- airports %>%
anti_join(q3a, by = "faa")
print(q3b)
## # A tibble: 1,455 × 8
## faa name lat lon alt tz dst tzone
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <chr> <chr>
## 1 04G Lansdowne Airport 41.1 -80.6 1044 -5 A America/…
## 2 06A Moton Field Municipal Airport 32.5 -85.7 264 -6 A America/…
## 3 06C Schaumburg Regional 42.0 -88.1 801 -6 A America/…
## 4 06N Randall Airport 41.4 -74.4 523 -5 A America/…
## 5 09J Jekyll Island Airport 31.1 -81.4 11 -5 A America/…
## 6 0A9 Elizabethton Municipal Airport 36.4 -82.2 1593 -5 A America/…
## 7 0G6 Williams County Airport 41.5 -84.5 730 -5 A America/…
## 8 0G7 Finger Lakes Regional Airport 42.9 -76.8 492 -5 A America/…
## 9 0P2 Shoestring Aviation Airfield 39.8 -76.6 1000 -5 U America/…
## 10 0S9 Jefferson County Intl 48.1 -123. 108 -8 A America/…
## # ℹ 1,445 more rows