R for Data Science
Daniel Lee / Owen Kihslinger
2026-09-10
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
mutate(flights,
gain = dep_delay - arr_delay) %>%
# Select year, month, day, and gain
select(year:day, gain)## # A tibble: 336,776 × 4
## year month day gain
## <int> <int> <int> <dbl>
## 1 2013 1 1 -9
## 2 2013 1 1 -16
## 3 2013 1 1 -31
## 4 2013 1 1 17
## 5 2013 1 1 19
## 6 2013 1 1 -16
## 7 2013 1 1 -24
## 8 2013 1 1 11
## 9 2013 1 1 5
## 10 2013 1 1 -10
## # ℹ 336,766 more rows# 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# Alternative Using Transmute()
transmute(flights,
gain = dep_delay - arr_delay)## # 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# 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
Collapsing Data to 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
summarize(flights, delay = mean(dep_delay, na.rm = TRUE))## # A tibble: 1 × 1
## delay
## <dbl>
## 1 12.6Summarize by Group
flights %>%
# Group by Airlines
group_by(carrier) %>%
# Calculate Average Departure Delay
summarize(delay = mean(dep_delay, na.rm = TRUE)) %>%
# Sort it
arrange(delay)## # A tibble: 16 × 2
## carrier delay
## <chr> <dbl>
## 1 US 3.78
## 2 HA 4.90
## 3 AS 5.80
## 4 AA 8.59
## 5 DL 9.26
## 6 MQ 10.6
## 7 UA 12.1
## 8 OO 12.6
## 9 VX 12.9
## 10 B6 13.0
## 11 9E 16.7
## 12 WN 17.7
## 13 FL 18.7
## 14 YV 19.0
## 15 EV 20.0
## 16 F9 20.2Delays increase with distance up to ~750 miles, then decreases
flights %>%
group_by(dest) %>%
summarize(count = n(),
dist = mean(distance, na.rm = TRUE),
delay = mean(arr_delay, na.rm = TRUE)) %>%
# Plot
ggplot(mapping = aes(x = dist, y = delay)) +
geom_point(aes(size = count), alpha = 0.3) +
geom_smooth(se = FALSE)## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'## Warning: Removed 1 row containing non-finite outside the scale range
## (`stat_smooth()`).## Warning: Removed 1 row containing missing values or values outside the scale range
## (`geom_point()`).
Missing Values
flights %>%
# Remove Missing Values
filter(!is.na(dep_delay))## # A tibble: 328,521 × 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 328,511 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>Counts Wow, there are some planes that have an average delay of 5 hours (300 minutes)!
delays <- flights %>%
group_by(tailnum) %>%
summarize(delay = mean(arr_delay, na.rm = TRUE))
ggplot(data = delays, mapping = aes(x = delay)) +
geom_freqpoly(binwidth = 10)## Warning: Removed 7 rows containing non-finite outside the scale range
## (`stat_bin()`).
We can get more insight if we draw a scatterplot of a number of flights vs. average delay:
delays <- flights %>%
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) +
xlim(0, 600)## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_point()`).
Useful Summary Functions
flights %>%
group_by(year, month, day) %>%
summarize(
avg_delay1 = mean(arr_delay, na.rm = TRUE),
avg_delay2 = mean(arr_delay[arr_delay > 0], na.rm = TRUE))## `summarise()` has regrouped the output.
## ℹ Summaries were computed grouped by year, month, and day.
## ℹ Output is grouped by year and month.
## ℹ Use `summarise(.groups = "drop_last")` to silence this message.
## ℹ Use `summarise(.by = c(year, month, day))` for per-operation grouping
## (`?dplyr::dplyr_by`) instead.## # 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 rows# Why is distance to some destinations more variable than to others
flights %>%
group_by(dest) %>%
summarize(distance_sd = sd(distance)) %>%
arrange(desc(distance_sd))## # A tibble: 105 × 2
## dest distance_sd
## <chr> <dbl>
## 1 EGE 10.5
## 2 SAN 10.3
## 3 SFO 10.2
## 4 HNL 10.0
## 5 SEA 9.98
## 6 LAS 9.91
## 7 PDX 9.88
## 8 PHX 9.86
## 9 LAX 9.66
## 10 IND 9.46
## # ℹ 95 more rows# When do the first and last flights leave each day?
flights %>%
group_by(year, month, day) %>%
summarize(
first = min(dep_time, na.rm = TRUE),
last = max(dep_time, na.rm = TRUE))## `summarise()` has regrouped the output.
## ℹ Summaries were computed grouped by year, month, and day.
## ℹ Output is grouped by year and month.
## ℹ Use `summarise(.groups = "drop_last")` to silence this message.
## ℹ Use `summarise(.by = c(year, month, day))` for per-operation grouping
## (`?dplyr::dplyr_by`) instead.## # 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 rows# Filtering
flights %>%
group_by(year, month, day) %>%
mutate(r = min_rank(desc(dep_time))) %>%
filter(r %in% range(r, na.rm = TRUE))## # 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># Which destinations have the most carriers?
flights %>%
group_by(dest) %>%
summarize(carriers = n_distinct(carrier)) %>%
arrange(desc(carriers))## # A tibble: 105 × 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 95 more rows# How many flights left before 5am? (these usually indicate delayed flights from the previous day)
flights %>%
group_by(year, month, day) %>%
summarize(n_early = sum(dep_time < 500, na.rm = TRUE))## `summarise()` has regrouped the output.
## ℹ Summaries were computed grouped by year, month, and day.
## ℹ Output is grouped by year and month.
## ℹ Use `summarise(.groups = "drop_last")` to silence this message.
## ℹ Use `summarise(.by = c(year, month, day))` for per-operation grouping
## (`?dplyr::dplyr_by`) instead.## # 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 rows# What proportion of flights are delayed by more than an hour?
flights %>%
group_by(year, month, day) %>%
summarize(hour_prop = mean(arr_delay > 60, na.rm = TRUE))## `summarise()` has regrouped the output.
## ℹ Summaries were computed grouped by year, month, and day.
## ℹ Output is grouped by year and month.
## ℹ Use `summarise(.groups = "drop_last")` to silence this message.
## ℹ Use `summarise(.by = c(year, month, day))` for per-operation grouping
## (`?dplyr::dplyr_by`) instead.## # 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 and Ungrouping
flights %>%
group_by(year, month, day) %>%
summarize(count = n()) %>%
ungroup()## `summarise()` has regrouped the output.
## ℹ Summaries were computed grouped by year, month, and day.
## ℹ Output is grouped by year and month.
## ℹ Use `summarise(.groups = "drop_last")` to silence this message.
## ℹ Use `summarise(.by = c(year, month, day))` for per-operation grouping
## (`?dplyr::dplyr_by`) instead.## # A tibble: 365 × 4
## year month day count
## <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 rowsMutate by Groups
# Worst members of each group
flights %>%
group_by(year, month, day) %>%
filter(rank(desc(arr_delay)) < 10)## # A tibble: 3,306 × 19
## # 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 1 848 1835 853 1001 1950
## 2 2013 1 1 1815 1325 290 2120 1542
## 3 2013 1 1 1842 1422 260 1958 1535
## 4 2013 1 1 1942 1705 157 2124 1830
## 5 2013 1 1 2006 1630 216 2230 1848
## 6 2013 1 1 2115 1700 255 2330 1920
## 7 2013 1 1 2205 1720 285 46 2040
## 8 2013 1 1 2312 2000 192 21 2110
## 9 2013 1 1 2343 1724 379 314 1938
## 10 2013 1 2 1244 900 224 1431 1104
## # ℹ 3,296 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># All groups larger than 365 (use any threshold you wish)
popular_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># Standardize to compute per group metrics
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