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(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>jan1 <- filter(flights, month == 1, day == 1)(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>5.2.4 Exercises 1. Find all flights that 1.Had an arrival delay of two or more hours
filter(flights, arr_delay >= 120)## # A tibble: 10,200 × 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 1 811 630 101 1047 830
## 2 2013 1 1 848 1835 853 1001 1950
## 3 2013 1 1 957 733 144 1056 853
## 4 2013 1 1 1114 900 134 1447 1222
## 5 2013 1 1 1505 1310 115 1638 1431
## 6 2013 1 1 1525 1340 105 1831 1626
## 7 2013 1 1 1549 1445 64 1912 1656
## 8 2013 1 1 1558 1359 119 1718 1515
## 9 2013 1 1 1732 1630 62 2028 1825
## 10 2013 1 1 1803 1620 103 2008 1750
## # ℹ 10,190 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: 10,200 x 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 1 811 630 101 1047 830
#> 2 2013 1 1 848 1835 853 1001 1950
#> 3 2013 1 1 957 733 144 1056 853
#> 4 2013 1 1 1114 900 134 1447 1222
#> 5 2013 1 1 1505 1310 115 1638 1431
#> 6 2013 1 1 1525 1340 105 1831 1626
#> # … with 10,194 more rows, and 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>2.Flew to Houston (IAH or HOU)
filter(flights, dest == "IAH" | dest == "HOU")## # A tibble: 9,313 × 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 1 623 627 -4 933 932
## 4 2013 1 1 728 732 -4 1041 1038
## 5 2013 1 1 739 739 0 1104 1038
## 6 2013 1 1 908 908 0 1228 1219
## 7 2013 1 1 1028 1026 2 1350 1339
## 8 2013 1 1 1044 1045 -1 1352 1351
## 9 2013 1 1 1114 900 134 1447 1222
## 10 2013 1 1 1205 1200 5 1503 1505
## # ℹ 9,303 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: 9,313 x 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 1 623 627 -4 933 932
#> 4 2013 1 1 728 732 -4 1041 1038
#> 5 2013 1 1 739 739 0 1104 1038
#> 6 2013 1 1 908 908 0 1228 1219
#> # … with 9,307 more rows, and 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>3.Were operated by United, American, or Delta
airlines## # A tibble: 16 × 2
## carrier name
## <chr> <chr>
## 1 9E Endeavor Air Inc.
## 2 AA American Airlines Inc.
## 3 AS Alaska Airlines Inc.
## 4 B6 JetBlue Airways
## 5 DL Delta Air Lines Inc.
## 6 EV ExpressJet Airlines Inc.
## 7 F9 Frontier Airlines Inc.
## 8 FL AirTran Airways Corporation
## 9 HA Hawaiian Airlines Inc.
## 10 MQ Envoy Air
## 11 OO SkyWest Airlines Inc.
## 12 UA United Air Lines Inc.
## 13 US US Airways Inc.
## 14 VX Virgin America
## 15 WN Southwest Airlines Co.
## 16 YV Mesa Airlines Inc.#> # A tibble: 16 x 2
#> carrier name
#> <chr> <chr>
#> 1 9E Endeavor Air Inc.
#> 2 AA American Airlines Inc.
#> 3 AS Alaska Airlines Inc.
#> 4 B6 JetBlue Airways
#> 5 DL Delta Air Lines Inc.
#> 6 EV ExpressJet Airlines Inc.
#> # … with 10 more rowsfilter(flights, carrier %in% c("AA", "DL", "UA"))## # A tibble: 139,504 × 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 1 554 600 -6 812 837
## 5 2013 1 1 554 558 -4 740 728
## 6 2013 1 1 558 600 -2 753 745
## 7 2013 1 1 558 600 -2 924 917
## 8 2013 1 1 558 600 -2 923 937
## 9 2013 1 1 559 600 -1 941 910
## 10 2013 1 1 559 600 -1 854 902
## # ℹ 139,494 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: 139,504 x 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 1 554 600 -6 812 837
#> 5 2013 1 1 554 558 -4 740 728
#> 6 2013 1 1 558 600 -2 753 745
#> # … with 139,498 more rows, and 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>4.Departed in summer (July, August, and September)
filter(flights, month >= 7, month <= 9)## # A tibble: 86,326 × 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 7 1 1 2029 212 236 2359
## 2 2013 7 1 2 2359 3 344 344
## 3 2013 7 1 29 2245 104 151 1
## 4 2013 7 1 43 2130 193 322 14
## 5 2013 7 1 44 2150 174 300 100
## 6 2013 7 1 46 2051 235 304 2358
## 7 2013 7 1 48 2001 287 308 2305
## 8 2013 7 1 58 2155 183 335 43
## 9 2013 7 1 100 2146 194 327 30
## 10 2013 7 1 100 2245 135 337 135
## # ℹ 86,316 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: 86,326 x 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 7 1 1 2029 212 236 2359
#> 2 2013 7 1 2 2359 3 344 344
#> 3 2013 7 1 29 2245 104 151 1
#> 4 2013 7 1 43 2130 193 322 14
#> 5 2013 7 1 44 2150 174 300 100
#> 6 2013 7 1 46 2051 235 304 2358
#> # … with 86,320 more rows, and 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>5.Arrived more than two hours late, but didn’t leave late
filter(flights, arr_delay > 120, dep_delay <= 0)## # A tibble: 29 × 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 27 1419 1420 -1 1754 1550
## 2 2013 10 7 1350 1350 0 1736 1526
## 3 2013 10 7 1357 1359 -2 1858 1654
## 4 2013 10 16 657 700 -3 1258 1056
## 5 2013 11 1 658 700 -2 1329 1015
## 6 2013 3 18 1844 1847 -3 39 2219
## 7 2013 4 17 1635 1640 -5 2049 1845
## 8 2013 4 18 558 600 -2 1149 850
## 9 2013 4 18 655 700 -5 1213 950
## 10 2013 5 22 1827 1830 -3 2217 2010
## # ℹ 19 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: 29 x 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 27 1419 1420 -1 1754 1550
#> 2 2013 10 7 1350 1350 0 1736 1526
#> 3 2013 10 7 1357 1359 -2 1858 1654
#> 4 2013 10 16 657 700 -3 1258 1056
#> 5 2013 11 1 658 700 -2 1329 1015
#> 6 2013 3 18 1844 1847 -3 39 2219
#> # … with 23 more rows, and 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>6.Were delayed by at least an hour, but made up over 30 minutes in flight
filter(flights, dep_delay >= 60, dep_delay - arr_delay > 30)## # A tibble: 1,844 × 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 2205 1720 285 46 2040
## 2 2013 1 1 2326 2130 116 131 18
## 3 2013 1 3 1503 1221 162 1803 1555
## 4 2013 1 3 1839 1700 99 2056 1950
## 5 2013 1 3 1850 1745 65 2148 2120
## 6 2013 1 3 1941 1759 102 2246 2139
## 7 2013 1 3 1950 1845 65 2228 2227
## 8 2013 1 3 2015 1915 60 2135 2111
## 9 2013 1 3 2257 2000 177 45 2224
## 10 2013 1 4 1917 1700 137 2135 1950
## # ℹ 1,834 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: 1,844 x 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 2205 1720 285 46 2040
#> 2 2013 1 1 2326 2130 116 131 18
#> 3 2013 1 3 1503 1221 162 1803 1555
#> 4 2013 1 3 1839 1700 99 2056 1950
#> 5 2013 1 3 1850 1745 65 2148 2120
#> 6 2013 1 3 1941 1759 102 2246 2139
#> # … with 1,838 more rows, and 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>7.Departed between midnight and 6am (inclusive)
filter(flights, dep_time <= 600 | dep_time == 2400)## # A tibble: 9,373 × 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 9,363 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: 9,373 x 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
#> # … with 9,367 more rows, and 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>2.Another useful dplyr filtering helper is between(). What does it do? Can you use it to simplify the code needed to answer the previous challenges? The expression between(x, left, right) is equivalent to x >= left & x <= right. Of the answers in the previous question, we could simplify the statement of departed in summer (month >= 7 & month <= 9) using the between() function.
filter(flights, between(month, 7, 9))## # A tibble: 86,326 × 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 7 1 1 2029 212 236 2359
## 2 2013 7 1 2 2359 3 344 344
## 3 2013 7 1 29 2245 104 151 1
## 4 2013 7 1 43 2130 193 322 14
## 5 2013 7 1 44 2150 174 300 100
## 6 2013 7 1 46 2051 235 304 2358
## 7 2013 7 1 48 2001 287 308 2305
## 8 2013 7 1 58 2155 183 335 43
## 9 2013 7 1 100 2146 194 327 30
## 10 2013 7 1 100 2245 135 337 135
## # ℹ 86,316 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: 86,326 x 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 7 1 1 2029 212 236 2359
#> 2 2013 7 1 2 2359 3 344 344
#> 3 2013 7 1 29 2245 104 151 1
#> 4 2013 7 1 43 2130 193 322 14
#> 5 2013 7 1 44 2150 174 300 100
#> 6 2013 7 1 46 2051 235 304 2358
#> # … with 86,320 more rows, and 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, is.na(dep_time))## # A tibble: 8,255 × 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 NA 1630 NA NA 1815
## 2 2013 1 1 NA 1935 NA NA 2240
## 3 2013 1 1 NA 1500 NA NA 1825
## 4 2013 1 1 NA 600 NA NA 901
## 5 2013 1 2 NA 1540 NA NA 1747
## 6 2013 1 2 NA 1620 NA NA 1746
## 7 2013 1 2 NA 1355 NA NA 1459
## 8 2013 1 2 NA 1420 NA NA 1644
## 9 2013 1 2 NA 1321 NA NA 1536
## 10 2013 1 2 NA 1545 NA NA 1910
## # ℹ 8,245 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: 8,255 x 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 NA 1630 NA NA 1815
#> 2 2013 1 1 NA 1935 NA NA 2240
#> 3 2013 1 1 NA 1500 NA NA 1825
#> 4 2013 1 1 NA 600 NA NA 901
#> 5 2013 1 2 NA 1540 NA NA 1747
#> 6 2013 1 2 NA 1620 NA NA 1746
#> # … with 8,249 more rows, and 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>summary(flights)## year month day dep_time sched_dep_time
## Min. :2013 Min. : 1.000 Min. : 1.00 Min. : 1 Min. : 106
## 1st Qu.:2013 1st Qu.: 4.000 1st Qu.: 8.00 1st Qu.: 907 1st Qu.: 906
## Median :2013 Median : 7.000 Median :16.00 Median :1401 Median :1359
## Mean :2013 Mean : 6.549 Mean :15.71 Mean :1349 Mean :1344
## 3rd Qu.:2013 3rd Qu.:10.000 3rd Qu.:23.00 3rd Qu.:1744 3rd Qu.:1729
## Max. :2013 Max. :12.000 Max. :31.00 Max. :2400 Max. :2359
## NA's :8255
## dep_delay arr_time sched_arr_time arr_delay
## Min. : -43.00 Min. : 1 Min. : 1 Min. : -86.000
## 1st Qu.: -5.00 1st Qu.:1104 1st Qu.:1124 1st Qu.: -17.000
## Median : -2.00 Median :1535 Median :1556 Median : -5.000
## Mean : 12.64 Mean :1502 Mean :1536 Mean : 6.895
## 3rd Qu.: 11.00 3rd Qu.:1940 3rd Qu.:1945 3rd Qu.: 14.000
## Max. :1301.00 Max. :2400 Max. :2359 Max. :1272.000
## NA's :8255 NA's :8713 NA's :9430
## carrier flight tailnum origin
## Length:336776 Min. : 1 Length:336776 Length:336776
## Class :character 1st Qu.: 553 Class :character Class :character
## Mode :character Median :1496 Mode :character Mode :character
## Mean :1972
## 3rd Qu.:3465
## Max. :8500
##
## dest air_time distance hour
## Length:336776 Min. : 20.0 Min. : 17 Min. : 1.00
## Class :character 1st Qu.: 82.0 1st Qu.: 502 1st Qu.: 9.00
## Mode :character Median :129.0 Median : 872 Median :13.00
## Mean :150.7 Mean :1040 Mean :13.18
## 3rd Qu.:192.0 3rd Qu.:1389 3rd Qu.:17.00
## Max. :695.0 Max. :4983 Max. :23.00
## NA's :9430
## minute time_hour
## Min. : 0.00 Min. :2013-01-01 05:00:00.00
## 1st Qu.: 8.00 1st Qu.:2013-04-04 13:00:00.00
## Median :29.00 Median :2013-07-03 10:00:00.00
## Mean :26.23 Mean :2013-07-03 05:22:54.64
## 3rd Qu.:44.00 3rd Qu.:2013-10-01 07:00:00.00
## Max. :59.00 Max. :2013-12-31 23:00:00.00
## #> year month day dep_time sched_dep_time
#> Min. :2013 Min. : 1.00 Min. : 1.0 Min. : 1 Min. : 106
#> 1st Qu.:2013 1st Qu.: 4.00 1st Qu.: 8.0 1st Qu.: 907 1st Qu.: 906
#> Median :2013 Median : 7.00 Median :16.0 Median :1401 Median :1359
#> Mean :2013 Mean : 6.55 Mean :15.7 Mean :1349 Mean :1344
#> 3rd Qu.:2013 3rd Qu.:10.00 3rd Qu.:23.0 3rd Qu.:1744 3rd Qu.:1729
#> Max. :2013 Max. :12.00 Max. :31.0 Max. :2400 Max. :2359
#> NA's :8255
#> dep_delay arr_time sched_arr_time arr_delay carrier
#> Min. : -43 Min. : 1 Min. : 1 Min. : -86 Length:336776
#> 1st Qu.: -5 1st Qu.:1104 1st Qu.:1124 1st Qu.: -17 Class :character
#> Median : -2 Median :1535 Median :1556 Median : -5 Mode :character
#> Mean : 13 Mean :1502 Mean :1536 Mean : 7
#> 3rd Qu.: 11 3rd Qu.:1940 3rd Qu.:1945 3rd Qu.: 14
#> Max. :1301 Max. :2400 Max. :2359 Max. :1272
#> NA's :8255 NA's :8713 NA's :9430
#> flight tailnum origin dest
#> Min. : 1 Length:336776 Length:336776 Length:336776
#> 1st Qu.: 553 Class :character Class :character Class :character
#> Median :1496 Mode :character Mode :character Mode :character
#> Mean :1972
#> 3rd Qu.:3465
#> Max. :8500
#>
#> air_time distance hour minute
#> Min. : 20 Min. : 17 Min. : 1.0 Min. : 0.0
#> 1st Qu.: 82 1st Qu.: 502 1st Qu.: 9.0 1st Qu.: 8.0
#> Median :129 Median : 872 Median :13.0 Median :29.0
#> Mean :151 Mean :1040 Mean :13.2 Mean :26.2
#> 3rd Qu.:192 3rd Qu.:1389 3rd Qu.:17.0 3rd Qu.:44.0
#> Max. :695 Max. :4983 Max. :23.0 Max. :59.0
#> NA's :9430
#> time_hour
#> Min. :2013-01-01 05:00:00
#> 1st Qu.:2013-04-04 13:00:00
#> Median :2013-07-03 10:00:00
#> Mean :2013-07-03 05:22:54
#> 3rd Qu.:2013-10-01 07:00:00
#> Max. :2013-12-31 23:00:00
#> NA | TRUE is TRUE because anything or TRUE is TRUE. If the missing value were TRUE, then TRUE | TRUE == TRUE, and if the missing value was FALSE, then FALSE | TRUE == TRUE.
The value of NA & FALSE is FALSE because anything and FALSE is always FALSE. If the missing value were TRUE, then TRUE & FALSE == FALSE, and if the missing value was FALSE, then FALSE & FALSE == FALSE.
For NA | FALSE, the value is unknown since TRUE | FALSE == TRUE, but FALSE | FALSE == FALSE.
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>Use desc() to re-order by a column in descending order:
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>Missing values are always sorted at the end:
df <- tibble(x = c(5, 2, NA))
arrange(df, x)## # A tibble: 3 × 1
## x
## <dbl>
## 1 2
## 2 5
## 3 NA#> # A tibble: 3 × 1
#> x
#> <dbl>
#> 1 2
#> 2 5
#> 3 NA
arrange(df, desc(x))## # A tibble: 3 × 1
## x
## <dbl>
## 1 5
## 2 2
## 3 NA#> # A tibble: 3 × 1
#> x
#> <dbl>
#> 1 5
#> 2 2
#> 3 NA5.3.1 Exercises 1. How could you use arrange() to sort all missing values to the start? (Hint: use is.na()).
arrange(flights, dep_time) %>%
tail()## # A tibble: 6 × 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 9 30 NA 1842 NA NA 2019
## 2 2013 9 30 NA 1455 NA NA 1634
## 3 2013 9 30 NA 2200 NA NA 2312
## 4 2013 9 30 NA 1210 NA NA 1330
## 5 2013 9 30 NA 1159 NA NA 1344
## 6 2013 9 30 NA 840 NA NA 1020
## # 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: 6 x 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 9 30 NA 1842 NA NA 2019
#> 2 2013 9 30 NA 1455 NA NA 1634
#> 3 2013 9 30 NA 2200 NA NA 2312
#> 4 2013 9 30 NA 1210 NA NA 1330
#> 5 2013 9 30 NA 1159 NA NA 1344
#> 6 2013 9 30 NA 840 NA NA 1020
#> # … with 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(is.na(dep_time)), dep_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 1 1 NA 1630 NA NA 1815
## 2 2013 1 1 NA 1935 NA NA 2240
## 3 2013 1 1 NA 1500 NA NA 1825
## 4 2013 1 1 NA 600 NA NA 901
## 5 2013 1 2 NA 1540 NA NA 1747
## 6 2013 1 2 NA 1620 NA NA 1746
## 7 2013 1 2 NA 1355 NA NA 1459
## 8 2013 1 2 NA 1420 NA NA 1644
## 9 2013 1 2 NA 1321 NA NA 1536
## 10 2013 1 2 NA 1545 NA NA 1910
## # 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 x 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 NA 1630 NA NA 1815
#> 2 2013 1 1 NA 1935 NA NA 2240
#> 3 2013 1 1 NA 1500 NA NA 1825
#> 4 2013 1 1 NA 600 NA NA 901
#> 5 2013 1 2 NA 1540 NA NA 1747
#> 6 2013 1 2 NA 1620 NA NA 1746
#> # … with 336,770 more rows, and 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 x 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
#> # … with 336,770 more rows, and 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, 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 12 7 2040 2123 -43 40 2352
## 2 2013 2 3 2022 2055 -33 2240 2338
## 3 2013 11 10 1408 1440 -32 1549 1559
## 4 2013 1 11 1900 1930 -30 2233 2243
## 5 2013 1 29 1703 1730 -27 1947 1957
## 6 2013 8 9 729 755 -26 1002 955
## 7 2013 10 23 1907 1932 -25 2143 2143
## 8 2013 3 30 2030 2055 -25 2213 2250
## 9 2013 3 2 1431 1455 -24 1601 1631
## 10 2013 5 5 934 958 -24 1225 1309
## # 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 x 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 7 2040 2123 -43 40 2352
#> 2 2013 2 3 2022 2055 -33 2240 2338
#> 3 2013 11 10 1408 1440 -32 1549 1559
#> 4 2013 1 11 1900 1930 -30 2233 2243
#> 5 2013 1 29 1703 1730 -27 1947 1957
#> 6 2013 8 9 729 755 -26 1002 955
#> # … with 336,770 more rows, and 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>head(arrange(flights, air_time))## # A tibble: 6 × 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 16 1355 1315 40 1442 1411
## 2 2013 4 13 537 527 10 622 628
## 3 2013 12 6 922 851 31 1021 954
## 4 2013 2 3 2153 2129 24 2247 2224
## 5 2013 2 5 1303 1315 -12 1342 1411
## 6 2013 2 12 2123 2130 -7 2211 2225
## # 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: 6 x 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 16 1355 1315 40 1442 1411
#> 2 2013 4 13 537 527 10 622 628
#> 3 2013 12 6 922 851 31 1021 954
#> 4 2013 2 3 2153 2129 24 2247 2224
#> 5 2013 2 5 1303 1315 -12 1342 1411
#> 6 2013 2 12 2123 2130 -7 2211 2225
#> # … with 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>head(arrange(flights, desc(distance / air_time)))## # A tibble: 6 × 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 5 25 1709 1700 9 1923 1937
## 2 2013 7 2 1558 1513 45 1745 1719
## 3 2013 5 13 2040 2025 15 2225 2226
## 4 2013 3 23 1914 1910 4 2045 2043
## 5 2013 1 12 1559 1600 -1 1849 1917
## 6 2013 11 17 650 655 -5 1059 1150
## # 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: 6 x 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 5 25 1709 1700 9 1923 1937
#> 2 2013 7 2 1558 1513 45 1745 1719
#> 3 2013 5 13 2040 2025 15 2225 2226
#> 4 2013 3 23 1914 1910 4 2045 2043
#> 5 2013 1 12 1559 1600 -1 1849 1917
#> 6 2013 11 17 650 655 -5 1059 1150
#> # … with 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(distance))## # 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 1 857 900 -3 1516 1530
## 2 2013 1 2 909 900 9 1525 1530
## 3 2013 1 3 914 900 14 1504 1530
## 4 2013 1 4 900 900 0 1516 1530
## 5 2013 1 5 858 900 -2 1519 1530
## 6 2013 1 6 1019 900 79 1558 1530
## 7 2013 1 7 1042 900 102 1620 1530
## 8 2013 1 8 901 900 1 1504 1530
## 9 2013 1 9 641 900 1301 1242 1530
## 10 2013 1 10 859 900 -1 1449 1530
## # 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 x 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 1 857 900 -3 1516 1530
#> 2 2013 1 2 909 900 9 1525 1530
#> 3 2013 1 3 914 900 14 1504 1530
#> 4 2013 1 4 900 900 0 1516 1530
#> 5 2013 1 5 858 900 -2 1519 1530
#> 6 2013 1 6 1019 900 79 1558 1530
#> # … with 336,770 more rows, and 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, distance)## # 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 7 27 NA 106 NA NA 245
## 2 2013 1 3 2127 2129 -2 2222 2224
## 3 2013 1 4 1240 1200 40 1333 1306
## 4 2013 1 4 1829 1615 134 1937 1721
## 5 2013 1 4 2128 2129 -1 2218 2224
## 6 2013 1 5 1155 1200 -5 1241 1306
## 7 2013 1 6 2125 2129 -4 2224 2224
## 8 2013 1 7 2124 2129 -5 2212 2224
## 9 2013 1 8 2127 2130 -3 2304 2225
## 10 2013 1 9 2126 2129 -3 2217 2224
## # 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 x 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 7 27 NA 106 NA NA 245
#> 2 2013 1 3 2127 2129 -2 2222 2224
#> 3 2013 1 4 1240 1200 40 1333 1306
#> 4 2013 1 4 1829 1615 134 1937 1721
#> 5 2013 1 4 2128 2129 -1 2218 2224
#> 6 2013 1 5 1155 1200 -5 1241 1306
#> # … with 336,770 more rows, and 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>#> # A tibble: 336,776 x 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
#> # … with 336,770 more rows, and 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, 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 1 16 1355 1315 40 1442 1411
## 2 2013 4 13 537 527 10 622 628
## 3 2013 12 6 922 851 31 1021 954
## 4 2013 2 3 2153 2129 24 2247 2224
## 5 2013 2 5 1303 1315 -12 1342 1411
## 6 2013 2 12 2123 2130 -7 2211 2225
## 7 2013 3 2 1450 1500 -10 1547 1608
## 8 2013 3 8 2026 1935 51 2131 2056
## 9 2013 3 18 1456 1329 87 1533 1426
## 10 2013 3 19 2226 2145 41 2305 2246
## # 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 x 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 16 1355 1315 40 1442 1411
#> 2 2013 4 13 537 527 10 622 628
#> 3 2013 12 6 922 851 31 1021 954
#> 4 2013 2 3 2153 2129 24 2247 2224
#> 5 2013 2 5 1303 1315 -12 1342 1411
#> 6 2013 2 12 2123 2130 -7 2211 2225
#> # … with 336,770 more rows, and 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 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>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>#> # 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
#> # ℹ 336,770 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>5.4.1 Exercises 1. Brainstorm as many ways as possible to select dep_time, dep_delay, arr_time, and arr_delay from flights. There are a few ways to select columns: The first way is specify columns names as unquoted variable names
select(flights, dep_time, dep_delay, arr_time, arr_delay)## # A tibble: 336,776 × 4
## dep_time dep_delay arr_time arr_delay
## <int> <dbl> <int> <dbl>
## 1 517 2 830 11
## 2 533 4 850 20
## 3 542 2 923 33
## 4 544 -1 1004 -18
## 5 554 -6 812 -25
## 6 554 -4 740 12
## 7 555 -5 913 19
## 8 557 -3 709 -14
## 9 557 -3 838 -8
## 10 558 -2 753 8
## # ℹ 336,766 more rows#> # A tibble: 336,776 x 4
#> dep_time dep_delay arr_time arr_delay
#> <int> <dbl> <int> <dbl>
#> 1 517 2 830 11
#> 2 533 4 850 20
#> 3 542 2 923 33
#> 4 544 -1 1004 -18
#> 5 554 -6 812 -25
#> 6 554 -4 740 12
#> # … with 336,770 more rowsAnother way is specify column names as strings
select(flights, "dep_time", "dep_delay", "arr_time", "arr_delay")## # A tibble: 336,776 × 4
## dep_time dep_delay arr_time arr_delay
## <int> <dbl> <int> <dbl>
## 1 517 2 830 11
## 2 533 4 850 20
## 3 542 2 923 33
## 4 544 -1 1004 -18
## 5 554 -6 812 -25
## 6 554 -4 740 12
## 7 555 -5 913 19
## 8 557 -3 709 -14
## 9 557 -3 838 -8
## 10 558 -2 753 8
## # ℹ 336,766 more rows#> # A tibble: 336,776 x 4
#> dep_time dep_delay arr_time arr_delay
#> <int> <dbl> <int> <dbl>
#> 1 517 2 830 11
#> 2 533 4 850 20
#> 3 542 2 923 33
#> 4 544 -1 1004 -18
#> 5 554 -6 812 -25
#> 6 554 -4 740 12
#> # … with 336,770 more rowsAnother way is specify the column numbers of the variables
select(flights, 4, 6, 7, 9)## # A tibble: 336,776 × 4
## dep_time dep_delay arr_time arr_delay
## <int> <dbl> <int> <dbl>
## 1 517 2 830 11
## 2 533 4 850 20
## 3 542 2 923 33
## 4 544 -1 1004 -18
## 5 554 -6 812 -25
## 6 554 -4 740 12
## 7 555 -5 913 19
## 8 557 -3 709 -14
## 9 557 -3 838 -8
## 10 558 -2 753 8
## # ℹ 336,766 more rows#> # A tibble: 336,776 x 4
#> dep_time dep_delay arr_time arr_delay
#> <int> <dbl> <int> <dbl>
#> 1 517 2 830 11
#> 2 533 4 850 20
#> 3 542 2 923 33
#> 4 544 -1 1004 -18
#> 5 554 -6 812 -25
#> 6 554 -4 740 12
#> # … with 336,770 more rowsAnother way is Specify the names of the variables with character vector and any_of() or all_of()
select(flights, all_of(c("dep_time", "dep_delay", "arr_time", "arr_delay")))## # A tibble: 336,776 × 4
## dep_time dep_delay arr_time arr_delay
## <int> <dbl> <int> <dbl>
## 1 517 2 830 11
## 2 533 4 850 20
## 3 542 2 923 33
## 4 544 -1 1004 -18
## 5 554 -6 812 -25
## 6 554 -4 740 12
## 7 555 -5 913 19
## 8 557 -3 709 -14
## 9 557 -3 838 -8
## 10 558 -2 753 8
## # ℹ 336,766 more rows#> # A tibble: 336,776 x 4
#> dep_time dep_delay arr_time arr_delay
#> <int> <dbl> <int> <dbl>
#> 1 517 2 830 11
#> 2 533 4 850 20
#> 3 542 2 923 33
#> 4 544 -1 1004 -18
#> 5 554 -6 812 -25
#> 6 554 -4 740 12
#> # … with 336,770 more rowsselect(flights, any_of(c("dep_time", "dep_delay", "arr_time", "arr_delay")))## # A tibble: 336,776 × 4
## dep_time dep_delay arr_time arr_delay
## <int> <dbl> <int> <dbl>
## 1 517 2 830 11
## 2 533 4 850 20
## 3 542 2 923 33
## 4 544 -1 1004 -18
## 5 554 -6 812 -25
## 6 554 -4 740 12
## 7 555 -5 913 19
## 8 557 -3 709 -14
## 9 557 -3 838 -8
## 10 558 -2 753 8
## # ℹ 336,766 more rows#> # A tibble: 336,776 x 4
#> dep_time dep_delay arr_time arr_delay
#> <int> <dbl> <int> <dbl>
#> 1 517 2 830 11
#> 2 533 4 850 20
#> 3 542 2 923 33
#> 4 544 -1 1004 -18
#> 5 554 -6 812 -25
#> 6 554 -4 740 12
#> # … with 336,770 more rowsselect(flights, year, month, day, year, year)## # 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 x 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
#> # … with 336,770 more rowsvars <- c("year", "month", "day", "dep_delay", "arr_delay")
select(flights, one_of(vars))## # A tibble: 336,776 × 5
## year month day dep_delay arr_delay
## <int> <int> <int> <dbl> <dbl>
## 1 2013 1 1 2 11
## 2 2013 1 1 4 20
## 3 2013 1 1 2 33
## 4 2013 1 1 -1 -18
## 5 2013 1 1 -6 -25
## 6 2013 1 1 -4 12
## 7 2013 1 1 -5 19
## 8 2013 1 1 -3 -14
## 9 2013 1 1 -3 -8
## 10 2013 1 1 -2 8
## # ℹ 336,766 more rows#> # A tibble: 336,776 x 5
#> year month day dep_delay arr_delay
#> <int> <int> <int> <dbl> <dbl>
#> 1 2013 1 1 2 11
#> 2 2013 1 1 4 20
#> 3 2013 1 1 2 33
#> 4 2013 1 1 -1 -18
#> 5 2013 1 1 -6 -25
#> 6 2013 1 1 -4 12
#> # … with 336,770 more rowsselect(flights, contains("TIME"))## # A tibble: 336,776 × 6
## dep_time sched_dep_time arr_time sched_arr_time air_time time_hour
## <int> <int> <int> <int> <dbl> <dttm>
## 1 517 515 830 819 227 2013-01-01 05:00:00
## 2 533 529 850 830 227 2013-01-01 05:00:00
## 3 542 540 923 850 160 2013-01-01 05:00:00
## 4 544 545 1004 1022 183 2013-01-01 05:00:00
## 5 554 600 812 837 116 2013-01-01 06:00:00
## 6 554 558 740 728 150 2013-01-01 05:00:00
## 7 555 600 913 854 158 2013-01-01 06:00:00
## 8 557 600 709 723 53 2013-01-01 06:00:00
## 9 557 600 838 846 140 2013-01-01 06:00:00
## 10 558 600 753 745 138 2013-01-01 06:00:00
## # ℹ 336,766 more rows#> # A tibble: 336,776 x 6
#> dep_time sched_dep_time arr_time sched_arr_time air_time time_hour
#> <int> <int> <int> <int> <dbl> <dttm>
#> 1 517 515 830 819 227 2013-01-01 05:00:00
#> 2 533 529 850 830 227 2013-01-01 05:00:00
#> 3 542 540 923 850 160 2013-01-01 05:00:00
#> 4 544 545 1004 1022 183 2013-01-01 05:00:00
#> 5 554 600 812 837 116 2013-01-01 06:00:00
#> 6 554 558 740 728 150 2013-01-01 05:00:00
#> # … with 336,770 more rowstransmute(flights,
dep_time,
hour = dep_time %/% 100,
minute = dep_time %% 100
)## # A tibble: 336,776 × 3
## dep_time hour minute
## <int> <dbl> <dbl>
## 1 517 5 17
## 2 533 5 33
## 3 542 5 42
## 4 544 5 44
## 5 554 5 54
## 6 554 5 54
## 7 555 5 55
## 8 557 5 57
## 9 557 5 57
## 10 558 5 58
## # ℹ 336,766 more rows#> # A tibble: 336,776 × 3
#> dep_time hour minute
#> <int> <dbl> <dbl>
#> 1 517 5 17
#> 2 533 5 33
#> 3 542 5 42
#> 4 544 5 44
#> 5 554 5 54
#> 6 554 5 54
#> # ℹ 336,770 more rows