R for Data Science
Keagan Moore
5-29-2025
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>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>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>filter(flights, month == 1 | day == 1)## # A tibble: 37,198 × 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 37,188 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(flights, month %in% c(11, 12))## # A tibble: 55,403 × 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 11 1 5 2359 6 352 345
## 2 2013 11 1 35 2250 105 123 2356
## 3 2013 11 1 455 500 -5 641 651
## 4 2013 11 1 539 545 -6 856 827
## 5 2013 11 1 542 545 -3 831 855
## 6 2013 11 1 549 600 -11 912 923
## 7 2013 11 1 550 600 -10 705 659
## 8 2013 11 1 554 600 -6 659 701
## 9 2013 11 1 554 600 -6 826 827
## 10 2013 11 1 554 600 -6 749 751
## # ℹ 55,393 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, desc(month), desc(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 12 31 13 2359 14 439 437
## 2 2013 12 31 18 2359 19 449 444
## 3 2013 12 31 26 2245 101 129 2353
## 4 2013 12 31 459 500 -1 655 651
## 5 2013 12 31 514 515 -1 814 812
## 6 2013 12 31 549 551 -2 925 900
## 7 2013 12 31 550 600 -10 725 745
## 8 2013 12 31 552 600 -8 811 826
## 9 2013 12 31 553 600 -7 741 754
## 10 2013 12 31 554 550 4 1024 1027
## # 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>Select columns
select(flights, year:dep_time)## # A tibble: 336,776 × 4
## year month day dep_time
## <int> <int> <int> <int>
## 1 2013 1 1 517
## 2 2013 1 1 533
## 3 2013 1 1 542
## 4 2013 1 1 544
## 5 2013 1 1 554
## 6 2013 1 1 554
## 7 2013 1 1 555
## 8 2013 1 1 557
## 9 2013 1 1 557
## 10 2013 1 1 558
## # ℹ 336,766 more rowsselect(flights, year, month, day, dep_time)## # A tibble: 336,776 × 4
## year month day dep_time
## <int> <int> <int> <int>
## 1 2013 1 1 517
## 2 2013 1 1 533
## 3 2013 1 1 542
## 4 2013 1 1 544
## 5 2013 1 1 554
## 6 2013 1 1 554
## 7 2013 1 1 555
## 8 2013 1 1 557
## 9 2013 1 1 557
## 10 2013 1 1 558
## # ℹ 336,766 more rowsselect(flights, year, month, day, dep_time, dep_delay)## # A tibble: 336,776 × 5
## year month day dep_time dep_delay
## <int> <int> <int> <int> <dbl>
## 1 2013 1 1 517 2
## 2 2013 1 1 533 4
## 3 2013 1 1 542 2
## 4 2013 1 1 544 -1
## 5 2013 1 1 554 -6
## 6 2013 1 1 554 -4
## 7 2013 1 1 555 -5
## 8 2013 1 1 557 -3
## 9 2013 1 1 557 -3
## 10 2013 1 1 558 -2
## # ℹ 336,766 more rowsselect(flights, year, month, day, starts_with("dep"))## # A tibble: 336,776 × 5
## year month day dep_time dep_delay
## <int> <int> <int> <int> <dbl>
## 1 2013 1 1 517 2
## 2 2013 1 1 533 4
## 3 2013 1 1 542 2
## 4 2013 1 1 544 -1
## 5 2013 1 1 554 -6
## 6 2013 1 1 554 -4
## 7 2013 1 1 555 -5
## 8 2013 1 1 557 -3
## 9 2013 1 1 557 -3
## 10 2013 1 1 558 -2
## # ℹ 336,766 more rowsselect(flights, year, month, day, contains("time"))## # A tibble: 336,776 × 9
## year month day dep_time sched_dep_time arr_time sched_arr_time air_time
## <int> <int> <int> <int> <int> <int> <int> <dbl>
## 1 2013 1 1 517 515 830 819 227
## 2 2013 1 1 533 529 850 830 227
## 3 2013 1 1 542 540 923 850 160
## 4 2013 1 1 544 545 1004 1022 183
## 5 2013 1 1 554 600 812 837 116
## 6 2013 1 1 554 558 740 728 150
## 7 2013 1 1 555 600 913 854 158
## 8 2013 1 1 557 600 709 723 53
## 9 2013 1 1 557 600 838 846 140
## 10 2013 1 1 558 600 753 745 138
## # ℹ 336,766 more rows
## # ℹ 1 more variable: time_hour <dttm>select(flights, year, month, day, ends_with("time"))## # A tibble: 336,776 × 8
## year month day dep_time sched_dep_time arr_time sched_arr_time air_time
## <int> <int> <int> <int> <int> <int> <int> <dbl>
## 1 2013 1 1 517 515 830 819 227
## 2 2013 1 1 533 529 850 830 227
## 3 2013 1 1 542 540 923 850 160
## 4 2013 1 1 544 545 1004 1022 183
## 5 2013 1 1 554 600 812 837 116
## 6 2013 1 1 554 558 740 728 150
## 7 2013 1 1 555 600 913 854 158
## 8 2013 1 1 557 600 709 723 53
## 9 2013 1 1 557 600 838 846 140
## 10 2013 1 1 558 600 753 745 138
## # ℹ 336,766 more rowsselect(flights, year, month, day, contains("time"), everything())## # A tibble: 336,776 × 19
## year month day dep_time sched_dep_time arr_time sched_arr_time air_time
## <int> <int> <int> <int> <int> <int> <int> <dbl>
## 1 2013 1 1 517 515 830 819 227
## 2 2013 1 1 533 529 850 830 227
## 3 2013 1 1 542 540 923 850 160
## 4 2013 1 1 544 545 1004 1022 183
## 5 2013 1 1 554 600 812 837 116
## 6 2013 1 1 554 558 740 728 150
## 7 2013 1 1 555 600 913 854 158
## 8 2013 1 1 557 600 709 723 53
## 9 2013 1 1 557 600 838 846 140
## 10 2013 1 1 558 600 753 745 138
## # ℹ 336,766 more rows
## # ℹ 11 more variables: time_hour <dttm>, dep_delay <dbl>, arr_delay <dbl>,
## # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## # distance <dbl>, hour <dbl>, minute <dbl>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 rowsmutate(flights_sml,
gain = dep_delay - arr_delay,
hours = air_time / 60,
gain_per_hour = gain / hours
)## # A tibble: 336,776 × 10
## year month day dep_delay arr_delay distance air_time gain hours
## <int> <int> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2013 1 1 2 11 1400 227 -9 3.78
## 2 2013 1 1 4 20 1416 227 -16 3.78
## 3 2013 1 1 2 33 1089 160 -31 2.67
## 4 2013 1 1 -1 -18 1576 183 17 3.05
## 5 2013 1 1 -6 -25 762 116 19 1.93
## 6 2013 1 1 -4 12 719 150 -16 2.5
## 7 2013 1 1 -5 19 1065 158 -24 2.63
## 8 2013 1 1 -3 -14 229 53 11 0.883
## 9 2013 1 1 -3 -8 944 140 5 2.33
## 10 2013 1 1 -2 8 733 138 -10 2.3
## # ℹ 336,766 more rows
## # ℹ 1 more variable: gain_per_hour <dbl>#just keep gain
mutate(flights,
gain = dep_delay - arr_delay) %>%
#select year, month, day, and gain
select(gain)## # A tibble: 336,776 × 1
## gain
## <dbl>
## 1 -9
## 2 -16
## 3 -31
## 4 17
## 5 19
## 6 -16
## 7 -24
## 8 11
## 9 5
## 10 -10
## # ℹ 336,766 more rows#alternate using transmute()
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#lag()
select(flights, dep_time) %>%
mutate(dep_time_lag1 = lag(dep_time))## # A tibble: 336,776 × 2
## dep_time dep_time_lag1
## <int> <int>
## 1 517 NA
## 2 533 517
## 3 542 533
## 4 544 542
## 5 554 544
## 6 554 554
## 7 555 554
## 8 557 555
## 9 557 557
## 10 558 557
## # ℹ 336,766 more rows#cumsum()
select(flights, minute) %>%
mutate(minute_cumsum = cumsum(minute))## # A tibble: 336,776 × 2
## minute minute_cumsum
## <dbl> <dbl>
## 1 15 15
## 2 29 44
## 3 40 84
## 4 45 129
## 5 0 129
## 6 58 187
## 7 0 187
## 8 0 187
## 9 0 187
## 10 0 187
## # ℹ 336,766 more rowsSummarize by groups
Collasping data in a single row
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>#average departure delay
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 rowsby_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")
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'
delays <- flights %>%
group_by(dest) %>%
summarise(
count = n(),
dist = mean(distance, na.rm = TRUE),
delay = mean(arr_delay, na.rm = TRUE)
) %>%
filter(count > 20, dest != "HNL")
flights %>%
group_by(year, month, day) %>%
summarise(mean = mean(dep_delay))## `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 mean
## <int> <int> <int> <dbl>
## 1 2013 1 1 NA
## 2 2013 1 2 NA
## 3 2013 1 3 NA
## 4 2013 1 4 NA
## 5 2013 1 5 NA
## 6 2013 1 6 NA
## 7 2013 1 7 NA
## 8 2013 1 8 NA
## 9 2013 1 9 NA
## 10 2013 1 10 NA
## # ℹ 355 more rowsflights %>%
group_by(year, month, day) %>%
summarise(mean = 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 mean
## <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 rowsnot_cancelled <- flights %>%
filter(!is.na(dep_delay), !is.na(arr_delay))
not_cancelled %>%
group_by(year, month, day) %>%
summarise(mean = mean(dep_delay))## `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 mean
## <int> <int> <int> <dbl>
## 1 2013 1 1 11.4
## 2 2013 1 2 13.7
## 3 2013 1 3 10.9
## 4 2013 1 4 8.97
## 5 2013 1 5 5.73
## 6 2013 1 6 7.15
## 7 2013 1 7 5.42
## 8 2013 1 8 2.56
## 9 2013 1 9 2.30
## 10 2013 1 10 2.84
## # ℹ 355 more rowsCounts
delays <- not_cancelled %>%
group_by(tailnum) %>%
summarise(
delay = mean(arr_delay)
)
ggplot(data = delays, mapping = aes(x = delay)) +
geom_freqpoly(binwidth = 10)
delays <- not_cancelled %>%
group_by(tailnum) %>%
summarise(
delay = mean(arr_delay, na.rm = TRUE),
n = n()
)
ggplot(data = delays, mapping = aes(x = n, y = delay)) +
geom_point(alpha = 1/10)
delays %>%
filter(n > 25) %>%
ggplot(mapping = aes(x = n, y = delay)) +
geom_point(alpha = 1/10)
batting <- as_tibble(Lahman::Batting)
batters <- batting %>%
group_by(playerID) %>%
summarise(
ba = sum(H, na.rm = TRUE) / sum(AB, na.rm = TRUE),
ab = sum(AB, na.rm = TRUE)
)
batters %>%
filter(ab > 100) %>%
ggplot(mapping = aes(x = ab, y = ba)) +
geom_point() +
geom_smooth(se = FALSE)## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
batters %>%
arrange(desc(ba))## # A tibble: 20,730 × 3
## playerID ba ab
## <chr> <dbl> <int>
## 1 abramge01 1 1
## 2 alberan01 1 1
## 3 banisje01 1 1
## 4 bartocl01 1 1
## 5 bassdo01 1 1
## 6 birasst01 1 2
## 7 bruneju01 1 1
## 8 burnscb01 1 1
## 9 cammaer01 1 1
## 10 campsh01 1 1
## # ℹ 20,720 more rowsSummary Functions
not_cancelled %>%
group_by(year, month, day) %>%
summarise(
avg_delay1 = mean(arr_delay),
avg_delay2 = mean(arr_delay[arr_delay > 0]) # the average positive delay
)## `summarise()` has grouped output by 'year', 'month'. You can override using the
## `.groups` argument.## # A tibble: 365 × 5
## # Groups: year, month [12]
## year month day avg_delay1 avg_delay2
## <int> <int> <int> <dbl> <dbl>
## 1 2013 1 1 12.7 32.5
## 2 2013 1 2 12.7 32.0
## 3 2013 1 3 5.73 27.7
## 4 2013 1 4 -1.93 28.3
## 5 2013 1 5 -1.53 22.6
## 6 2013 1 6 4.24 24.4
## 7 2013 1 7 -4.95 27.8
## 8 2013 1 8 -3.23 20.8
## 9 2013 1 9 -0.264 25.6
## 10 2013 1 10 -5.90 27.3
## # ℹ 355 more rowsnot_cancelled %>%
group_by(dest) %>%
summarise(distance_sd = sd(distance)) %>%
arrange(desc(distance_sd))## # A tibble: 104 × 2
## dest distance_sd
## <chr> <dbl>
## 1 EGE 10.5
## 2 SAN 10.4
## 3 SFO 10.2
## 4 HNL 10.0
## 5 SEA 9.98
## 6 LAS 9.91
## 7 PDX 9.87
## 8 PHX 9.86
## 9 LAX 9.66
## 10 IND 9.46
## # ℹ 94 more rowsnot_cancelled %>%
group_by(year, month, day) %>%
summarise(
first = min(dep_time),
last = max(dep_time))## `summarise()` has grouped output by 'year', 'month'. You can override using the
## `.groups` argument.## # A tibble: 365 × 5
## # Groups: year, month [12]
## year month day first last
## <int> <int> <int> <int> <int>
## 1 2013 1 1 517 2356
## 2 2013 1 2 42 2354
## 3 2013 1 3 32 2349
## 4 2013 1 4 25 2358
## 5 2013 1 5 14 2357
## 6 2013 1 6 16 2355
## 7 2013 1 7 49 2359
## 8 2013 1 8 454 2351
## 9 2013 1 9 2 2252
## 10 2013 1 10 3 2320
## # ℹ 355 more rowsnot_cancelled %>%
group_by(year, month, day) %>%
summarise(
first_dep = first(dep_time),
last_dep = last(dep_time))## `summarise()` has grouped output by 'year', 'month'. You can override using the
## `.groups` argument.## # A tibble: 365 × 5
## # Groups: year, month [12]
## year month day first_dep last_dep
## <int> <int> <int> <int> <int>
## 1 2013 1 1 517 2356
## 2 2013 1 2 42 2354
## 3 2013 1 3 32 2349
## 4 2013 1 4 25 2358
## 5 2013 1 5 14 2357
## 6 2013 1 6 16 2355
## 7 2013 1 7 49 2359
## 8 2013 1 8 454 2351
## 9 2013 1 9 2 2252
## 10 2013 1 10 3 2320
## # ℹ 355 more rowsnot_cancelled %>%
group_by(year, month, day) %>%
mutate(r = min_rank(desc(dep_time))) %>%
filter(r %in% range(r))## # A tibble: 770 × 20
## # Groups: year, month, day [365]
## 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 2356 2359 -3 425 437
## 3 2013 1 2 42 2359 43 518 442
## 4 2013 1 2 2354 2359 -5 413 437
## 5 2013 1 3 32 2359 33 504 442
## 6 2013 1 3 2349 2359 -10 434 445
## 7 2013 1 4 25 2359 26 505 442
## 8 2013 1 4 2358 2359 -1 429 437
## 9 2013 1 4 2358 2359 -1 436 445
## 10 2013 1 5 14 2359 15 503 445
## # ℹ 760 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>, r <int>not_cancelled %>%
group_by(dest) %>%
summarise(carriers = n_distinct(carrier)) %>%
arrange(desc(carriers))## # A tibble: 104 × 2
## dest carriers
## <chr> <int>
## 1 ATL 7
## 2 BOS 7
## 3 CLT 7
## 4 ORD 7
## 5 TPA 7
## 6 AUS 6
## 7 DCA 6
## 8 DTW 6
## 9 IAD 6
## 10 MSP 6
## # ℹ 94 more rowsnot_cancelled %>%
count(dest)## # A tibble: 104 × 2
## dest n
## <chr> <int>
## 1 ABQ 254
## 2 ACK 264
## 3 ALB 418
## 4 ANC 8
## 5 ATL 16837
## 6 AUS 2411
## 7 AVL 261
## 8 BDL 412
## 9 BGR 358
## 10 BHM 269
## # ℹ 94 more rowsnot_cancelled %>%
count(tailnum, wt = distance)## # A tibble: 4,037 × 2
## tailnum n
## <chr> <dbl>
## 1 D942DN 3418
## 2 N0EGMQ 239143
## 3 N10156 109664
## 4 N102UW 25722
## 5 N103US 24619
## 6 N104UW 24616
## 7 N10575 139903
## 8 N105UW 23618
## 9 N107US 21677
## 10 N108UW 32070
## # ℹ 4,027 more rowsnot_cancelled %>%
group_by(year, month, day) %>%
summarise(n_early = sum(dep_time < 500))## `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 n_early
## <int> <int> <int> <int>
## 1 2013 1 1 0
## 2 2013 1 2 3
## 3 2013 1 3 4
## 4 2013 1 4 3
## 5 2013 1 5 3
## 6 2013 1 6 2
## 7 2013 1 7 2
## 8 2013 1 8 1
## 9 2013 1 9 3
## 10 2013 1 10 3
## # ℹ 355 more rowsnot_cancelled %>%
group_by(year, month, day) %>%
summarise(hour_prop = mean(arr_delay > 60))## `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 hour_prop
## <int> <int> <int> <dbl>
## 1 2013 1 1 0.0722
## 2 2013 1 2 0.0851
## 3 2013 1 3 0.0567
## 4 2013 1 4 0.0396
## 5 2013 1 5 0.0349
## 6 2013 1 6 0.0470
## 7 2013 1 7 0.0333
## 8 2013 1 8 0.0213
## 9 2013 1 9 0.0202
## 10 2013 1 10 0.0183
## # ℹ 355 more rowsGrouping Multiple Variables
daily <- group_by(flights, year, month, day)
(per_day <- summarise(daily, flights = n()))## `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 flights
## <int> <int> <int> <int>
## 1 2013 1 1 842
## 2 2013 1 2 943
## 3 2013 1 3 914
## 4 2013 1 4 915
## 5 2013 1 5 720
## 6 2013 1 6 832
## 7 2013 1 7 933
## 8 2013 1 8 899
## 9 2013 1 9 902
## 10 2013 1 10 932
## # ℹ 355 more rows(per_month <- summarise(per_day, flights = sum(flights)))## `summarise()` has grouped output by 'year'. You can override using the
## `.groups` argument.## # A tibble: 12 × 3
## # Groups: year [1]
## year month flights
## <int> <int> <int>
## 1 2013 1 27004
## 2 2013 2 24951
## 3 2013 3 28834
## 4 2013 4 28330
## 5 2013 5 28796
## 6 2013 6 28243
## 7 2013 7 29425
## 8 2013 8 29327
## 9 2013 9 27574
## 10 2013 10 28889
## 11 2013 11 27268
## 12 2013 12 28135(per_year <- summarise(per_month, flights = sum(flights)))## # A tibble: 1 × 2
## year flights
## <int> <int>
## 1 2013 336776Ungrouping
daily %>%
ungroup() %>%
summarise(flights = n())## # A tibble: 1 × 1
## flights
## <int>
## 1 336776Group Mutates
flights_sml %>%
group_by(year, month, day) %>%
filter(rank(desc(arr_delay)) < 10)## # A tibble: 3,306 × 7
## # Groups: year, month, day [365]
## year month day dep_delay arr_delay distance air_time
## <int> <int> <int> <dbl> <dbl> <dbl> <dbl>
## 1 2013 1 1 853 851 184 41
## 2 2013 1 1 290 338 1134 213
## 3 2013 1 1 260 263 266 46
## 4 2013 1 1 157 174 213 60
## 5 2013 1 1 216 222 708 121
## 6 2013 1 1 255 250 589 115
## 7 2013 1 1 285 246 1085 146
## 8 2013 1 1 192 191 199 44
## 9 2013 1 1 379 456 1092 222
## 10 2013 1 2 224 207 550 94
## # ℹ 3,296 more rowspopular_dests <- flights %>%
group_by(dest) %>%
filter(n() > 365)
popular_dests## # A tibble: 332,577 × 19
## # Groups: dest [77]
## 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 332,567 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>popular_dests %>%
filter(arr_delay > 0) %>%
mutate(prop_delay = arr_delay / sum(arr_delay)) %>%
select(year:day, dest, arr_delay, prop_delay)## # A tibble: 131,106 × 6
## # Groups: dest [77]
## year month day dest arr_delay prop_delay
## <int> <int> <int> <chr> <dbl> <dbl>
## 1 2013 1 1 IAH 11 0.000111
## 2 2013 1 1 IAH 20 0.000201
## 3 2013 1 1 MIA 33 0.000235
## 4 2013 1 1 ORD 12 0.0000424
## 5 2013 1 1 FLL 19 0.0000938
## 6 2013 1 1 ORD 8 0.0000283
## 7 2013 1 1 LAX 7 0.0000344
## 8 2013 1 1 DFW 31 0.000282
## 9 2013 1 1 ATL 12 0.0000400
## 10 2013 1 1 DTW 16 0.000116
## # ℹ 131,096 more rows