R for Data Science
Bella Kalinyak
2024-06-02
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 ==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>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>filter(flights, !(arr_delay > 120 | dep_delay > 120))## # A tibble: 316,050 × 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 316,040 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, carrier == "UA")## # A tibble: 58,665 × 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 1 554 558 -4 740 728
## 4 2013 1 1 558 600 -2 924 917
## 5 2013 1 1 558 600 -2 923 937
## 6 2013 1 1 559 600 -1 854 902
## 7 2013 1 1 607 607 0 858 915
## 8 2013 1 1 611 600 11 945 931
## 9 2013 1 1 623 627 -4 933 932
## 10 2013 1 1 628 630 -2 1016 947
## # ℹ 58,655 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, dest == "IAH", dest == "HOU")## # A tibble: 0 × 19
## # ℹ 19 variables: year <int>, month <int>, day <int>, dep_time <int>,
## # sched_dep_time <int>, dep_delay <dbl>, arr_time <int>,
## # sched_arr_time <int>, 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 == 7, month == 8, month == 9)## # A tibble: 0 × 19
## # ℹ 19 variables: year <int>, month <int>, day <int>, dep_time <int>,
## # sched_dep_time <int>, dep_delay <dbl>, arr_time <int>,
## # sched_arr_time <int>, 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>arrange(flights, desc(dep_delay), desc(arr_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>arrange(flights, desc(air_time))## # 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 3 17 1337 1335 2 1937 1836
## 2 2013 2 6 853 900 -7 1542 1540
## 3 2013 3 15 1001 1000 1 1551 1530
## 4 2013 3 17 1006 1000 6 1607 1530
## 5 2013 3 16 1001 1000 1 1544 1530
## 6 2013 2 5 900 900 0 1555 1540
## 7 2013 11 12 936 930 6 1630 1530
## 8 2013 3 14 958 1000 -2 1542 1530
## 9 2013 11 20 1006 1000 6 1639 1555
## 10 2013 3 15 1342 1335 7 1924 1836
## # 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>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>select(flights, time_hour, air_time, everything())## # A tibble: 336,776 × 19
## time_hour air_time year month day dep_time sched_dep_time
## <dttm> <dbl> <int> <int> <int> <int> <int>
## 1 2013-01-01 05:00:00 227 2013 1 1 517 515
## 2 2013-01-01 05:00:00 227 2013 1 1 533 529
## 3 2013-01-01 05:00:00 160 2013 1 1 542 540
## 4 2013-01-01 05:00:00 183 2013 1 1 544 545
## 5 2013-01-01 06:00:00 116 2013 1 1 554 600
## 6 2013-01-01 05:00:00 150 2013 1 1 554 558
## 7 2013-01-01 06:00:00 158 2013 1 1 555 600
## 8 2013-01-01 06:00:00 53 2013 1 1 557 600
## 9 2013-01-01 06:00:00 140 2013 1 1 557 600
## 10 2013-01-01 06:00:00 138 2013 1 1 558 600
## # ℹ 336,766 more rows
## # ℹ 12 more variables: dep_delay <dbl>, arr_time <int>, sched_arr_time <int>,
## # arr_delay <dbl>, carrier <chr>, flight <int>, tailnum <chr>, origin <chr>,
## # dest <chr>, distance <dbl>, hour <dbl>, minute <dbl>select(flights, time_hour, time_hour )## # A tibble: 336,776 × 1
## time_hour
## <dttm>
## 1 2013-01-01 05:00:00
## 2 2013-01-01 05:00:00
## 3 2013-01-01 05:00:00
## 4 2013-01-01 05:00:00
## 5 2013-01-01 06:00:00
## 6 2013-01-01 05:00:00
## 7 2013-01-01 06:00:00
## 8 2013-01-01 06:00:00
## 9 2013-01-01 06:00:00
## 10 2013-01-01 06:00:00
## # ℹ 336,766 more rowsAdd 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
summarise(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
summarise(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 20.2by_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")Delays increase with distance up to ~750 miles and then decrease
flights %>%
group_by(dest) %>%
summarise(
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()`).
Grouping multiple variables and Ungrouping
flights %>%
group_by(year, month, day)%>%
summarise(count = n()) %>%
ungroup()## `summarise()` has grouped output by 'year', 'month'. You can override using the
## `.groups` argument.## # 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 rowsMissing 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>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)
)
# Performance of batters in baseball
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: 20,469 × 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 20,459 more rowsMutate by groups
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>popular_dests <- flights %>%
group_by(dest) %>%
filter(n() > 365)
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