Import data
flights
## # A tibble: 336,776 × 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
## # ℹ 336,766 more rows
## # ℹ 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 × 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
#> # ℹ 336,770 more rows
#> # ℹ 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>
Filter rows
filter(flights, month == 1, day == 1)
## # A tibble: 842 × 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
## # ℹ 832 more rows
## # ℹ 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: 842 × 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
#> # ℹ 836 more rows
#> # ℹ 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>
(dec25 <- filter(flights, month == 12, day == 25))
## # A tibble: 719 × 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 12 25 456 500 -4 649 651
## 2 2013 12 25 524 515 9 805 814
## 3 2013 12 25 542 540 2 832 850
## 4 2013 12 25 546 550 -4 1022 1027
## 5 2013 12 25 556 600 -4 730 745
## 6 2013 12 25 557 600 -3 743 752
## 7 2013 12 25 557 600 -3 818 831
## 8 2013 12 25 559 600 -1 855 856
## 9 2013 12 25 559 600 -1 849 855
## 10 2013 12 25 600 600 0 850 846
## # ℹ 709 more rows
## # ℹ 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: 719 × 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 12 25 456 500 -4 649 651
#> 2 2013 12 25 524 515 9 805 814
#> 3 2013 12 25 542 540 2 832 850
#> 4 2013 12 25 546 550 -4 1022 1027
#> 5 2013 12 25 556 600 -4 730 745
#> 6 2013 12 25 557 600 -3 743 752
#> # ℹ 713 more rows
#> # ℹ 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>
Arrange rows
arrange(flights, year, month, day)
## # A tibble: 336,776 × 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
## # ℹ 336,766 more rows
## # ℹ 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 × 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
#> # ℹ 336,770 more rows
#> # ℹ 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>
arrange(flights, desc(dep_delay))
## # A tibble: 336,776 × 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 9 641 900 1301 1242 1530
## 2 2013 6 15 1432 1935 1137 1607 2120
## 3 2013 1 10 1121 1635 1126 1239 1810
## 4 2013 9 20 1139 1845 1014 1457 2210
## 5 2013 7 22 845 1600 1005 1044 1815
## 6 2013 4 10 1100 1900 960 1342 2211
## 7 2013 3 17 2321 810 911 135 1020
## 8 2013 6 27 959 1900 899 1236 2226
## 9 2013 7 22 2257 759 898 121 1026
## 10 2013 12 5 756 1700 896 1058 2020
## # ℹ 336,766 more rows
## # ℹ 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 × 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 9 641 900 1301 1242 1530
#> 2 2013 6 15 1432 1935 1137 1607 2120
#> 3 2013 1 10 1121 1635 1126 1239 1810
#> 4 2013 9 20 1139 1845 1014 1457 2210
#> 5 2013 7 22 845 1600 1005 1044 1815
#> 6 2013 4 10 1100 1900 960 1342 2211
#> # ℹ 336,770 more rows
#> # ℹ 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>
Select columns
# Select columns by name
select(flights, year, month, day)
## # A tibble: 336,776 × 3
## year month day
## <int> <int> <int>
## 1 2013 1 1
## 2 2013 1 1
## 3 2013 1 1
## 4 2013 1 1
## 5 2013 1 1
## 6 2013 1 1
## 7 2013 1 1
## 8 2013 1 1
## 9 2013 1 1
## 10 2013 1 1
## # ℹ 336,766 more rows
#> # A tibble: 336,776 × 3
#> year month day
#> <int> <int> <int>
#> 1 2013 1 1
#> 2 2013 1 1
#> 3 2013 1 1
#> 4 2013 1 1
#> 5 2013 1 1
#> 6 2013 1 1
#> # ℹ 336,770 more rows
# Select all columns between year and day (inclusive)
select(flights, year:day)
## # A tibble: 336,776 × 3
## year month day
## <int> <int> <int>
## 1 2013 1 1
## 2 2013 1 1
## 3 2013 1 1
## 4 2013 1 1
## 5 2013 1 1
## 6 2013 1 1
## 7 2013 1 1
## 8 2013 1 1
## 9 2013 1 1
## 10 2013 1 1
## # ℹ 336,766 more rows
#> # A tibble: 336,776 × 3
#> year month day
#> <int> <int> <int>
#> 1 2013 1 1
#> 2 2013 1 1
#> 3 2013 1 1
#> 4 2013 1 1
#> 5 2013 1 1
#> 6 2013 1 1
#> # ℹ 336,770 more rows
# Select all columns except those from year to day (inclusive)
select(flights, -(year:day))
## # A tibble: 336,776 × 16
## dep_time sched_dep_time dep_delay arr_time sched_arr_time arr_delay carrier
## <int> <int> <dbl> <int> <int> <dbl> <chr>
## 1 517 515 2 830 819 11 UA
## 2 533 529 4 850 830 20 UA
## 3 542 540 2 923 850 33 AA
## 4 544 545 -1 1004 1022 -18 B6
## 5 554 600 -6 812 837 -25 DL
## 6 554 558 -4 740 728 12 UA
## 7 555 600 -5 913 854 19 B6
## 8 557 600 -3 709 723 -14 EV
## 9 557 600 -3 838 846 -8 B6
## 10 558 600 -2 753 745 8 AA
## # ℹ 336,766 more rows
## # ℹ 9 more variables: flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>
#> # A tibble: 336,776 × 16
#> dep_time sched_dep_time dep_delay arr_time sched_arr_time arr_delay carrier
#> <int> <int> <dbl> <int> <int> <dbl> <chr>
#> 1 517 515 2 830 819 11 UA
#> 2 533 529 4 850 830 20 UA
#> 3 542 540 2 923 850 33 AA
#> 4 544 545 -1 1004 1022 -18 B6
#> 5 554 600 -6 812 837 -25 DL
#> 6 554 558 -4 740 728 12 UA
#> # ℹ 336,770 more rows
#> # ℹ 9 more variables: flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
#> # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>
rename(flights, tail_num = tailnum)
## # A tibble: 336,776 × 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
## # ℹ 336,766 more rows
## # ℹ 11 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
## # tail_num <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
## # hour <dbl>, minute <dbl>, time_hour <dttm>
#> # A tibble: 336,776 × 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
#> # ℹ 336,770 more rows
#> # ℹ 11 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
#> # tail_num <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
#> # hour <dbl>, minute <dbl>, time_hour <dttm>
Add columns
flights_sml <- select(flights,
year:day,
ends_with("delay"),
distance,
air_time
)
mutate(flights_sml,
gain = dep_delay - arr_delay,
speed = distance / air_time * 60
)
## # A tibble: 336,776 × 9
## year month day dep_delay arr_delay distance air_time gain speed
## <int> <int> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2013 1 1 2 11 1400 227 -9 370.
## 2 2013 1 1 4 20 1416 227 -16 374.
## 3 2013 1 1 2 33 1089 160 -31 408.
## 4 2013 1 1 -1 -18 1576 183 17 517.
## 5 2013 1 1 -6 -25 762 116 19 394.
## 6 2013 1 1 -4 12 719 150 -16 288.
## 7 2013 1 1 -5 19 1065 158 -24 404.
## 8 2013 1 1 -3 -14 229 53 11 259.
## 9 2013 1 1 -3 -8 944 140 5 405.
## 10 2013 1 1 -2 8 733 138 -10 319.
## # ℹ 336,766 more rows
#> # A tibble: 336,776 × 9
#> year month day dep_delay arr_delay distance air_time gain speed
#> <int> <int> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 2013 1 1 2 11 1400 227 -9 370.
#> 2 2013 1 1 4 20 1416 227 -16 374.
#> 3 2013 1 1 2 33 1089 160 -31 408.
#> 4 2013 1 1 -1 -18 1576 183 17 517.
#> 5 2013 1 1 -6 -25 762 116 19 394.
#> 6 2013 1 1 -4 12 719 150 -16 288.
#> # ℹ 336,770 more rows
transmute(flights,
gain = dep_delay - arr_delay,
hours = air_time / 60,
gain_per_hour = gain / hours
)
## # A tibble: 336,776 × 3
## gain hours gain_per_hour
## <dbl> <dbl> <dbl>
## 1 -9 3.78 -2.38
## 2 -16 3.78 -4.23
## 3 -31 2.67 -11.6
## 4 17 3.05 5.57
## 5 19 1.93 9.83
## 6 -16 2.5 -6.4
## 7 -24 2.63 -9.11
## 8 11 0.883 12.5
## 9 5 2.33 2.14
## 10 -10 2.3 -4.35
## # ℹ 336,766 more rows
#> # A tibble: 336,776 × 3
#> gain hours gain_per_hour
#> <dbl> <dbl> <dbl>
#> 1 -9 3.78 -2.38
#> 2 -16 3.78 -4.23
#> 3 -31 2.67 -11.6
#> 4 17 3.05 5.57
#> 5 19 1.93 9.83
#> 6 -16 2.5 -6.4
#> # ℹ 336,770 more rows
Summarize by groups
summarise(flights, delay = mean(dep_delay, na.rm = TRUE))
## # A tibble: 1 × 1
## delay
## <dbl>
## 1 12.6
#> # A tibble: 1 × 1
#> delay
#> <dbl>
#> 1 12.6
by_day <- group_by(flights, year, month, day)
summarise(by_day, delay = mean(dep_delay, na.rm = TRUE))
## `summarise()` has grouped output by 'year', 'month'. You can override using the
## `.groups` argument.
## # A tibble: 365 × 4
## # Groups: year, month [12]
## year month day delay
## <int> <int> <int> <dbl>
## 1 2013 1 1 11.5
## 2 2013 1 2 13.9
## 3 2013 1 3 11.0
## 4 2013 1 4 8.95
## 5 2013 1 5 5.73
## 6 2013 1 6 7.15
## 7 2013 1 7 5.42
## 8 2013 1 8 2.55
## 9 2013 1 9 2.28
## 10 2013 1 10 2.84
## # ℹ 355 more rows
#> `summarise()` has grouped output by 'year', 'month'. You can override using the
#> `.groups` argument.
#> # A tibble: 365 × 4
#> # Groups: year, month [12]
#> year month day delay
#> <int> <int> <int> <dbl>
#> 1 2013 1 1 11.5
#> 2 2013 1 2 13.9
#> 3 2013 1 3 11.0
#> 4 2013 1 4 8.95
#> 5 2013 1 5 5.73
#> 6 2013 1 6 7.15
#> # ℹ 359 more rows
by_dest <- group_by(flights, dest)
delay <- summarise(by_dest,
count = n(),
dist = mean(distance, na.rm = TRUE),
delay = mean(arr_delay, na.rm = TRUE)
)
delay <- filter(delay, count > 20, dest != "HNL")
# It looks like delays increase with distance up to ~750 miles
# and then decrease. Maybe as flights get longer there's more
# ability to make up delays in the air?
ggplot(data = delay, mapping = aes(x = dist, y = delay)) +
geom_point(aes(size = count), alpha = 1/3) +
geom_smooth(se = FALSE)
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
#> `geom_smooth()` using method = 'loess' and formula = 'y ~ x'