Create the code makes a table for each of the below questions.
1. join + filter - Which airplanes fly LGA to XNA (1 POINT)
lga_to_xna <- flights %>%
filter(origin == "LGA", dest == "XNA") %>%
left_join(planes, by = "tailnum")
lga_to_xna
## # A tibble: 745 × 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
## 7 2013 1 3 703 705 -2 1014 940
## 8 2013 1 3 1525 1530 -5 1802 1805
## 9 2013 1 3 1737 1745 -8 1953 2020
## 10 2013 1 4 701 705 -4 934 940
## # ℹ 735 more rows
## # 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")
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. join + select + distinct() - Which airports have no commercial
flights (1 POINT)
airports_with_flights <- flights %>%
distinct(origin) %>%
rename(faa = origin)
airports_with_no_flights <- airports %>%
anti_join(airports_with_flights, by = "faa") %>%
select(faa, name)
airports_with_no_flights
## # A tibble: 1,455 × 2
## faa name
## <chr> <chr>
## 1 04G Lansdowne Airport
## 2 06A Moton Field Municipal Airport
## 3 06C Schaumburg Regional
## 4 06N Randall Airport
## 5 09J Jekyll Island Airport
## 6 0A9 Elizabethton Municipal Airport
## 7 0G6 Williams County Airport
## 8 0G7 Finger Lakes Regional Airport
## 9 0P2 Shoestring Aviation Airfield
## 10 0S9 Jefferson County Intl
## # ℹ 1,445 more rows
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
airports_with_high_wind <- weather %>%
filter(wind_speed > 30) %>%
left_join(airports, by = c("origin" = "faa")) %>%
select(name) %>%
distinct()
airports_with_high_wind
## # A tibble: 3 × 1
## name
## <chr>
## 1 Newark Liberty Intl
## 2 John F Kennedy Intl
## 3 La Guardia