1. join + filter - Which airplanes fly LGA to XNA (1 POINT)
q1 <- flights %>%
inner_join(planes, by = "tailnum") %>%
filter(origin == "LGA" & dest == "XNA")
head(q1)
## # 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 2 1531 1530 1 1846 1805
## 2 2013 1 3 703 705 -2 1014 940
## 3 2013 1 7 1737 1745 -8 2009 2020
## 4 2013 1 9 1736 1745 -9 2008 2020
## 5 2013 1 13 1741 1745 -4 2028 2020
## 6 2013 1 14 1530 1530 0 1914 1805
## # 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)
q2 <- flights %>%
inner_join(airlines, by = "carrier")
head(q2)
## # 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)
q3 <- airports %>%
left_join(flights, by = c("faa" = "origin"))%>%
filter(is.na(carrier))%>%
select(name)%>%
distinct()
head(q3)
## # A tibble: 6 × 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
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
q4 <- flights %>%
inner_join(weather, by = c("year", "month", "day", "hour", "origin")) %>%
filter(wind_speed > 30) %>%
inner_join(airports, by = c("origin" = "faa")) %>%
select(name) %>%
distinct()
head(q4)
## # A tibble: 3 × 1
## name
## <chr>
## 1 John F Kennedy Intl
## 2 Newark Liberty Intl
## 3 La Guardia