Sebelum kita mencari data penerbangan di bawah ini. Mari Kita Install dulu Libary nya
library(tidyverse)## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --## v ggplot2 3.3.3 v purrr 0.3.4
## v tibble 3.0.6 v dplyr 1.0.4
## v tidyr 1.1.2 v stringr 1.4.0
## v readr 1.4.0 v forcats 0.5.1## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(nycflights13)
library(tidyverse)Kita Cari data penerbangannya
flights## # A tibble: 336,776 x 19
## 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
## # ... with 336,766 more rows, and 11 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>#> # A tibble: 336,776 x 19
#> 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
#> # . with 336,770 more rows, and 11 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>Jika sudah muncul data penerbangan di atas.
sekarang mengurutkan penerbangan untuk menemukan penerbangan yang paling terlambat. Temukan penerbangan yang berangkat paling awal.
arrange(flights, desc(dep_time))## # A tibble: 336,776 x 19
## 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 10 30 2400 2359 1 327 337
## 2 2013 11 27 2400 2359 1 515 445
## 3 2013 12 5 2400 2359 1 427 440
## 4 2013 12 9 2400 2359 1 432 440
## 5 2013 12 9 2400 2250 70 59 2356
## 6 2013 12 13 2400 2359 1 432 440
## 7 2013 12 19 2400 2359 1 434 440
## 8 2013 12 29 2400 1700 420 302 2025
## 9 2013 2 7 2400 2359 1 432 436
## 10 2013 2 7 2400 2359 1 443 444
## # ... with 336,766 more rows, and 11 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>Penerbangan mana yang bepergian paling jauh?
select(flights, dep_time, dep_delay, arr_time, arr_delay, origin, dest, hour, minute, time_hour, air_time)## # A tibble: 336,776 x 10
## dep_time dep_delay arr_time arr_delay origin dest hour minute
## <int> <dbl> <int> <dbl> <chr> <chr> <dbl> <dbl>
## 1 517 2 830 11 EWR IAH 5 15
## 2 533 4 850 20 LGA IAH 5 29
## 3 542 2 923 33 JFK MIA 5 40
## 4 544 -1 1004 -18 JFK BQN 5 45
## 5 554 -6 812 -25 LGA ATL 6 0
## 6 554 -4 740 12 EWR ORD 5 58
## 7 555 -5 913 19 EWR FLL 6 0
## 8 557 -3 709 -14 LGA IAD 6 0
## 9 557 -3 838 -8 JFK MCO 6 0
## 10 558 -2 753 8 LGA ORD 6 0
## # ... with 336,766 more rows, and 2 more variables: time_hour <dttm>,
## # air_time <dbl>filter(flights, hour >=23)## # A tibble: 1,061 x 19
## 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 2353 2359 -6 425 445
## 2 2013 1 1 2353 2359 -6 418 442
## 3 2013 1 1 2356 2359 -3 425 437
## 4 2013 1 2 42 2359 43 518 442
## 5 2013 1 2 2351 2359 -8 427 445
## 6 2013 1 2 2354 2359 -5 413 437
## 7 2013 1 3 32 2359 33 504 442
## 8 2013 1 3 235 2359 156 700 437
## 9 2013 1 3 2349 2359 -10 434 445
## 10 2013 1 4 25 2359 26 505 442
## # ... with 1,051 more rows, and 11 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>