Jacob Stoughton and Jakub Kepa
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 1.5.2
## ✔ 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 errors
Create the code makes a table for each of the below questions.
1. join + filter - Which airplanes fly LGA to XNA (1 POINT)
planes_LGAXNA <- flights %>%
filter(origin == "LGA", dest == "XNA")
flights_planes <- planes_LGAXNA %>%
left_join(planes, by = "tailnum")
flights_planes %>%
select(year.x, month, day, dep_time, arr_time)
## # A tibble: 745 × 5
## year.x month day dep_time arr_time
## <int> <int> <int> <int> <int>
## 1 2013 1 1 656 1007
## 2 2013 1 1 1525 1934
## 3 2013 1 1 1740 2158
## 4 2013 1 2 656 1014
## 5 2013 1 2 1531 1846
## 6 2013 1 2 1740 2035
## 7 2013 1 3 703 1014
## 8 2013 1 3 1525 1802
## 9 2013 1 3 1737 1953
## 10 2013 1 4 701 934
## # ℹ 735 more rows
head(flights_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 1 656 705 -9 1007 940
## 2 2013 1 1 1525 1530 -5 1934 1805
## 3 2013 1 1 1740 1745 -5 2158 2020
## 4 2013 1 2 656 705 -9 1014 940
## 5 2013 1 2 1531 1530 1 1846 1805
## 6 2013 1 2 1740 1745 -5 2035 2020
## # 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_airlines <- flights %>%
left_join(airlines, by = "carrier")
flights_airlines %>%
select(year, month, day, dep_time, arr_time, name)
## # A tibble: 336,776 × 6
## year month day dep_time arr_time name
## <int> <int> <int> <int> <int> <chr>
## 1 2013 1 1 517 830 United Air Lines Inc.
## 2 2013 1 1 533 850 United Air Lines Inc.
## 3 2013 1 1 542 923 American Airlines Inc.
## 4 2013 1 1 544 1004 JetBlue Airways
## 5 2013 1 1 554 812 Delta Air Lines Inc.
## 6 2013 1 1 554 740 United Air Lines Inc.
## 7 2013 1 1 555 913 JetBlue Airways
## 8 2013 1 1 557 709 ExpressJet Airlines Inc.
## 9 2013 1 1 557 838 JetBlue Airways
## 10 2013 1 1 558 753 American Airlines Inc.
## # ℹ 336,766 more rows
head(flights_airlines)
## # 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_flights <- flights %>%
select(origin, dest) %>%
distinct()
airports_no_flights <- airports %>%
anti_join(airports_flights, by = c("faa" = "origin")) %>%
anti_join(airports_flights, by = c("faa" = "dest"))
airports_no_flights %>%
select(faa, name, lat, lon)
## # A tibble: 1,355 × 4
## faa name lat lon
## <chr> <chr> <dbl> <dbl>
## 1 04G Lansdowne Airport 41.1 -80.6
## 2 06A Moton Field Municipal Airport 32.5 -85.7
## 3 06C Schaumburg Regional 42.0 -88.1
## 4 06N Randall Airport 41.4 -74.4
## 5 09J Jekyll Island Airport 31.1 -81.4
## 6 0A9 Elizabethton Municipal Airport 36.4 -82.2
## 7 0G6 Williams County Airport 41.5 -84.5
## 8 0G7 Finger Lakes Regional Airport 42.9 -76.8
## 9 0P2 Shoestring Aviation Airfield 39.8 -76.6
## 10 0S9 Jefferson County Intl 48.1 -123.
## # ℹ 1,345 more rows
head(airports_no_flights)
## # A tibble: 6 × 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/Ne…
## 2 06A Moton Field Municipal Airport 32.5 -85.7 264 -6 A America/Ch…
## 3 06C Schaumburg Regional 42.0 -88.1 801 -6 A America/Ch…
## 4 06N Randall Airport 41.4 -74.4 523 -5 A America/Ne…
## 5 09J Jekyll Island Airport 31.1 -81.4 11 -5 A America/Ne…
## 6 0A9 Elizabethton Municipal Airport 36.4 -82.2 1593 -5 A America/Ne…
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) %>%
left_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