library(nycflights13)
library(tidyverse)── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
✔ ggplot2 3.4.0 ✔ purrr 0.3.5
✔ tibble 3.1.8 ✔ dplyr 1.0.10
✔ tidyr 1.2.1 ✔ stringr 1.4.1
✔ readr 2.1.3 ✔ forcats 0.5.2
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag() masks stats::lag()str(flights)tibble [336,776 × 19] (S3: tbl_df/tbl/data.frame)
$ year : int [1:336776] 2013 2013 2013 2013 2013 2013 2013 2013 2013 2013 ...
$ month : int [1:336776] 1 1 1 1 1 1 1 1 1 1 ...
$ day : int [1:336776] 1 1 1 1 1 1 1 1 1 1 ...
$ dep_time : int [1:336776] 517 533 542 544 554 554 555 557 557 558 ...
$ sched_dep_time: int [1:336776] 515 529 540 545 600 558 600 600 600 600 ...
$ dep_delay : num [1:336776] 2 4 2 -1 -6 -4 -5 -3 -3 -2 ...
$ arr_time : int [1:336776] 830 850 923 1004 812 740 913 709 838 753 ...
$ sched_arr_time: int [1:336776] 819 830 850 1022 837 728 854 723 846 745 ...
$ arr_delay : num [1:336776] 11 20 33 -18 -25 12 19 -14 -8 8 ...
$ carrier : chr [1:336776] "UA" "UA" "AA" "B6" ...
$ flight : int [1:336776] 1545 1714 1141 725 461 1696 507 5708 79 301 ...
$ tailnum : chr [1:336776] "N14228" "N24211" "N619AA" "N804JB" ...
$ origin : chr [1:336776] "EWR" "LGA" "JFK" "JFK" ...
$ dest : chr [1:336776] "IAH" "IAH" "MIA" "BQN" ...
$ air_time : num [1:336776] 227 227 160 183 116 150 158 53 140 138 ...
$ distance : num [1:336776] 1400 1416 1089 1576 762 ...
$ hour : num [1:336776] 5 5 5 5 6 5 6 6 6 6 ...
$ minute : num [1:336776] 15 29 40 45 0 58 0 0 0 0 ...
$ time_hour : POSIXct[1:336776], format: "2013-01-01 05:00:00" "2013-01-01 05:00:00" ...flights %>%
mutate(arr_type = ifelse(arr_delay < 5, "on time", "delayed")) %>%
group_by(dest) %>%
summarise(count=n(), ot_arr_rate = sum(arr_type == "on time", na.rm=TRUE) / n()*100, "%") %>%
arrange(desc(ot_arr_rate)) %>%
print(n=25)# A tibble: 105 × 4
dest count ot_arr_rate `"%"`
<chr> <int> <dbl> <chr>
1 LEX 1 100 %
2 PSP 19 78.9 %
3 SNA 825 74.2 %
4 STT 522 73.6 %
5 MVY 221 72.9 %
6 HNL 707 72.3 %
7 BOS 15508 71.2 %
8 SEA 3923 71.1 %
9 MIA 11728 70.9 %
10 SLC 2467 70.5 %
11 SBN 10 70 %
12 LAS 5997 69.5 %
13 LAX 16174 68.1 %
14 LGB 668 68.0 %
15 ACK 265 67.9 %
16 DFW 8738 67.7 %
17 SJC 329 67.5 %
18 SRQ 1211 67.5 %
19 SJU 5819 67.2 %
20 DTW 9384 67.1 %
21 SFO 13331 66.9 %
22 MTJ 15 66.7 %
23 MYR 59 66.1 %
24 MCO 14082 65.6 %
25 PHX 4656 65.5 %
# … with 80 more rowsflights %>%
group_by(month) %>%
summarize(count = n(),
avg_dep_delay = mean(dep_delay, na.rm = TRUE),
max_dep_delay = max(dep_delay, na.rm = TRUE),
min_dep_delay = min(dep_delay, na.rm = TRUE),
)# A tibble: 12 × 5
month count avg_dep_delay max_dep_delay min_dep_delay
<int> <int> <dbl> <dbl> <dbl>
1 1 27004 10.0 1301 -30
2 2 24951 10.8 853 -33
3 3 28834 13.2 911 -25
4 4 28330 13.9 960 -21
5 5 28796 13.0 878 -24
6 6 28243 20.8 1137 -21
7 7 29425 21.7 1005 -22
8 8 29327 12.6 520 -26
9 9 27574 6.72 1014 -24
10 10 28889 6.24 702 -25
11 11 27268 5.44 798 -32
12 12 28135 16.6 896 -43