Chapter5_dplyr
Jesse Surry
2/29/2020
Chapter 5 Assignment
library(nycflights13)
library(tidyverse)## -- Attaching packages ------------------------------------------------------------------------ tidyverse 1.3.0 --## v ggplot2 3.2.1 v purrr 0.3.3
## v tibble 2.1.3 v dplyr 0.8.3
## v tidyr 1.0.0 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.4.0## -- Conflicts --------------------------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()flights## # 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 1 517 515 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
## # ... with 336,766 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>Dyplyr Basics
Pick observations by their values (filter()). Reorder the rows (arrange()). Pick variables by their names (select()). Create new variables with functions of existing variables (mutate()). Collapse many values down to a single summary (summarise()All verbs work similarly:
The first argument is a data frame. The subsequent arguments describe what to do with the data frame, using the variable names (without quotes). The result is a new data frame.
filter(flights, month == 1, day == 1)## # A tibble: 842 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
## 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
## # ... with 832 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>jan1 <- filter(flights, month == 1, day == 1)(dec25 <- filter(flights, month == 12, day == 25))## # A tibble: 719 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 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
## # ... with 709 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>near(sqrt(2) ^ 2, 2)## [1] TRUEfilter(flights, month == 11 | month == 12)## # A tibble: 55,403 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 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
## # ... with 55,393 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>nov_dec <- filter(flights, month %in% c(11, 12))filter(flights, !(arr_delay > 120 | dep_delay > 120))## # A tibble: 316,050 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
## 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
## # ... with 316,040 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>5.24 Excercises
1a Arrival Delay of more than 2 hours
filter(flights, arr_delay > 2)## # A tibble: 123,096 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 1 554 558 -4 740 728
## 5 2013 1 1 555 600 -5 913 854
## 6 2013 1 1 558 600 -2 753 745
## 7 2013 1 1 558 600 -2 924 917
## 8 2013 1 1 559 600 -1 941 910
## 9 2013 1 1 600 600 0 837 825
## 10 2013 1 1 602 605 -3 821 805
## # ... with 123,086 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>1b Flew to Houston (IAH or HOU)
filter(flights, dest == 'IAH' | dest == 'HOU' )## # 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
## 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
## # ... with 9,303 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>1c Were operated by United, American, or Delta
filter(flights, carrier == 'UA' | carrier == 'DL'| carrier == 'AA' )## # 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
## 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
## # ... with 139,494 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>1d Departed in summer (July, August, and September)
filter(flights, month == 7 | month == 8 | month == 9 )## # 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
## 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
## # ... with 86,316 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>1f Arrived more than two hours late, but didn’t leave late
filter(flights, (arr_time - sched_arr_time > 2) & (dep_delay == 0) )## # A tibble: 4,371 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 1 600 600 0 837 825
## 2 2013 1 1 635 635 0 1028 940
## 3 2013 1 1 739 739 0 1104 1038
## 4 2013 1 1 745 745 0 1135 1125
## 5 2013 1 1 800 800 0 1022 1014
## 6 2013 1 1 805 805 0 1015 1005
## 7 2013 1 1 810 810 0 1048 1037
## 8 2013 1 1 823 823 0 1151 1135
## 9 2013 1 1 830 830 0 1018 1015
## 10 2013 1 1 835 835 0 1210 1150
## # ... with 4,361 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>1g 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 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
## 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
## # ... with 1,834 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>1h Departed between midnight and 6am (inclusive)
filter(flights, dep_time >= 2400 | dep_time <= 600)## # 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
## 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
## # ... with 9,363 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?
filter(flights, between(dep_time, 601, 2359))## # A tibble: 319,148 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 1 601 600 1 844 850
## 2 2013 1 1 602 610 -8 812 820
## 3 2013 1 1 602 605 -3 821 805
## 4 2013 1 1 606 610 -4 858 910
## 5 2013 1 1 606 610 -4 837 845
## 6 2013 1 1 607 607 0 858 915
## 7 2013 1 1 608 600 8 807 735
## 8 2013 1 1 611 600 11 945 931
## 9 2013 1 1 613 610 3 925 921
## 10 2013 1 1 615 615 0 1039 1100
## # ... with 319,138 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 How many flights have a missing dep_time? What other variables are missing? What might these rows represent?
They may represent cancelled flights.
sum(is.na(flights$dep_time))## [1] 82554 Why is NA ^ 0 not missing? Why is NA | TRUE not missing? Why is FALSE & NA not missing? Can you figure out the general rule? (NA * 0 is a tricky counterexample!)
This is the case because anything raised to 0 = 1. NA | True is not missing because it is saying one of the two is true and the second one is true. False & NA is not missing because atleast one of the conditions can be tested
The gerneral rule is that if there is a logical solution where if one side of the expression can be tested than the result will not be NA.
Arrange rows with arrange()
arrange(flights, year, month, day)## # 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 1 517 515 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
## # ... with 336,766 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>Descending Order
arrange(flights, desc(dep_delay))## # 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
## 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
## # ... with 336,766 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>df <- tibble(x = c(5, 2, NA))
arrange(df, x)## # A tibble: 3 x 1
## x
## <dbl>
## 1 2
## 2 5
## 3 NA5.31 Excercises
1.How could you use arrange() to sort all missing values to the start? (Hint: use is.na()).
df <- tibble(x = c(5, 2, NA),
y = c(2, NA, 2))
rowSums(df)## [1] 7 NA NAarrange(df, desc(is.na(x)))## # A tibble: 3 x 2
## x y
## <dbl> <dbl>
## 1 NA 2
## 2 5 2
## 3 2 NAarrange(df, -(is.na(x)))## # A tibble: 3 x 2
## x y
## <dbl> <dbl>
## 1 NA 2
## 2 5 2
## 3 2 NA2.Sort flights to find the most delayed flights. Find the flights that left earliest.
arrange(flights, dep_delay)## # 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
## 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
## # ... with 336,766 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 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
## 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
## # ... with 336,766 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.Sort flights to find the fastest (highest speed) flights.
arrange(flights, air_time)## # 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
## 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
## # ... with 336,766 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.Which flights travelled the farthest? Which travelled the shortest?
# Shortest
flights %>%
arrange(air_time) %>%
select(carrier, flight, air_time)## # A tibble: 336,776 x 3
## carrier flight air_time
## <chr> <int> <dbl>
## 1 EV 4368 20
## 2 EV 4631 20
## 3 EV 4276 21
## 4 EV 4619 21
## 5 EV 4368 21
## 6 EV 4619 21
## 7 US 2132 21
## 8 9E 3650 21
## 9 EV 4118 21
## 10 EV 4276 21
## # ... with 336,766 more rows# Fastest
flights %>%
arrange(-air_time) %>%
select(carrier, flight, air_time)## # A tibble: 336,776 x 3
## carrier flight air_time
## <chr> <int> <dbl>
## 1 UA 15 695
## 2 HA 51 691
## 3 HA 51 686
## 4 HA 51 686
## 5 HA 51 683
## 6 HA 51 679
## 7 UA 15 676
## 8 HA 51 676
## 9 HA 51 675
## 10 UA 15 671
## # ... with 336,766 more rows5.4 Select columns using select()
# Select columns by name
select(flights, year, month, day)## # 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
## 7 2013 1 1
## 8 2013 1 1
## 9 2013 1 1
## 10 2013 1 1
## # ... with 336,766 more rows# Select all columns between year and day (inclusive)
select(flights, year:day)## # 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
## 7 2013 1 1
## 8 2013 1 1
## 9 2013 1 1
## 10 2013 1 1
## # ... with 336,766 more rows# Select all columns except those from year to day (inclusive)
select(flights, -(year:day))## # A tibble: 336,776 x 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
## # ... with 336,766 more rows, and 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 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
## 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
## # ... with 336,766 more rows, and 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 x 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
## # ... with 336,766 more rows, and 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>5.41 Excercises
1.Brainstorm as many ways as possible to select dep_time, dep_delay, arr_time, and arr_delay from flights.
select(flights, dep_time, dep_delay, arr_time, arr_delay)## # 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
## 7 555 -5 913 19
## 8 557 -3 709 -14
## 9 557 -3 838 -8
## 10 558 -2 753 8
## # ... with 336,766 more rowsselect(flights, starts_with("dep"), starts_with("arr"))## # 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
## 7 555 -5 913 19
## 8 557 -3 709 -14
## 9 557 -3 838 -8
## 10 558 -2 753 8
## # ... with 336,766 more rowsselect_(flights, "dep_time", "dep_delay", "arr_time", "arr_delay")## Warning: select_() is deprecated.
## Please use select() instead
##
## The 'programming' vignette or the tidyeval book can help you
## to program with select() : https://tidyeval.tidyverse.org
## This warning is displayed once per session.## # 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
## 7 555 -5 913 19
## 8 557 -3 709 -14
## 9 557 -3 838 -8
## 10 558 -2 753 8
## # ... with 336,766 more rows2,What happens if you include the name of a variable multiple times in a select() call? Nothing else changes it just returns one time.
3.What does the one_of() function do? Why might it be helpful in conjunction with this vector? vars <- c(“year”, “month”, “day”, “dep_delay”, “arr_delay”) Select only accepts variables without quotes, using one_of() allows the use of character names and returns all of the variable names that yuo ask for.
4.Does the result of running the following code surprise you? How do the select helpers deal with case by default? How can you change that default? No, select helpers ignore case by default
5.5 Add New Variables with mutate()
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 x 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.
## # ... with 336,766 more rowsmutate(flights_sml,
gain = dep_delay - arr_delay,
hours = air_time / 60,
gain_per_hour = gain / hours
)## # A tibble: 336,776 x 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
## # ... with 336,766 more rows, and 1 more variable: gain_per_hour <dbl># Use to only keep new variables
transmute(flights,
gain = dep_delay - arr_delay,
hours = air_time / 60,
gain_per_hour = gain / hours
)## # A tibble: 336,776 x 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
## # ... with 336,766 more rowstransmute(flights,
dep_time,
hour = dep_time %/% 100,
minute = dep_time %% 100
)## # A tibble: 336,776 x 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
## # ... with 336,766 more rows5.52 Excercises
Currently dep_time and sched_dep_time are convenient to look at, but hard to compute with because they’re not really continuous numbers. Convert them to a more convenient representation of number of minutes since midnight.
mutate(flights,
dep_time = 60 * floor(dep_time/100) + (dep_time - floor(dep_time/100) * 100),
sched_dep_time = 60 * floor(sched_dep_time/100) + (sched_dep_time - floor(sched_dep_time/100) * 100))## # A tibble: 336,776 x 19
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <dbl> <dbl> <dbl> <int> <int>
## 1 2013 1 1 317 315 2 830 819
## 2 2013 1 1 333 329 4 850 830
## 3 2013 1 1 342 340 2 923 850
## 4 2013 1 1 344 345 -1 1004 1022
## 5 2013 1 1 354 360 -6 812 837
## 6 2013 1 1 354 358 -4 740 728
## 7 2013 1 1 355 360 -5 913 854
## 8 2013 1 1 357 360 -3 709 723
## 9 2013 1 1 357 360 -3 838 846
## 10 2013 1 1 358 360 -2 753 745
## # ... with 336,766 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>Compare air_time with arr_time - dep_time. What do you expect to see? What do you see? What do you need to do to fix it?
You would expect air_time and arr_time - dep_time to be the same, however they are different because arr_time and dep_time are not continous numbers. This can be fixed by converting arr_time to minutes since midnight and then recalculating
flights_sml <- select(flights, dep_time, arr_time, air_time)
mutate(flights_sml,
arr_min = (arr_time %/% 100)*60 + (arr_time %% 100),
dep_min = (dep_time %/% 100)*60 + (dep_time %% 100),
trip_min = arr_min - dep_min
)## # A tibble: 336,776 x 6
## dep_time arr_time air_time arr_min dep_min trip_min
## <int> <int> <dbl> <dbl> <dbl> <dbl>
## 1 517 830 227 510 317 193
## 2 533 850 227 530 333 197
## 3 542 923 160 563 342 221
## 4 544 1004 183 604 344 260
## 5 554 812 116 492 354 138
## 6 554 740 150 460 354 106
## 7 555 913 158 553 355 198
## 8 557 709 53 429 357 72
## 9 557 838 140 518 357 161
## 10 558 753 138 473 358 115
## # ... with 336,766 more rowsCompare dep_time, sched_dep_time, and dep_delay. How would you expect those three numbers to be related? You would expect them to be related in that the dep_delay would be the difference between dep_time and sched_dep_time.
select(flights, dep_time, sched_dep_time, dep_delay)## # A tibble: 336,776 x 3
## dep_time sched_dep_time dep_delay
## <int> <int> <dbl>
## 1 517 515 2
## 2 533 529 4
## 3 542 540 2
## 4 544 545 -1
## 5 554 600 -6
## 6 554 558 -4
## 7 555 600 -5
## 8 557 600 -3
## 9 557 600 -3
## 10 558 600 -2
## # ... with 336,766 more rowsFind the 10 most delayed flights using a ranking function. How do you want to handle ties? Carefully read the documentation for min_rank().
head(arrange(flights, min_rank(desc(dep_delay))), 10)## # A tibble: 10 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
## 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
## # ... 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>What does 1:3 + 1:10 return? Why? It returns an error that lonnger object length is not a multiple of shorter object length
What trigonometric functions does R provide? You can use ?sin to discover the trignometric functions R provides.
5.6 Grouped SUmmaries with summarise()
summarise(flights, delay = mean(dep_delay, na.rm = TRUE))## # A tibble: 1 x 1
## delay
## <dbl>
## 1 12.6Average delay per date
by_day <- group_by(flights, year, month, day)
summarise(by_day, delay = mean(dep_delay, na.rm = TRUE))## # A tibble: 365 x 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
## # ... with 355 more rowsdelays <- 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))## # A tibble: 365 x 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
## # ... with 355 more rowsflights %>%
group_by(year, month, day) %>%
summarise(mean = mean(dep_delay, na.rm = TRUE))## # A tibble: 365 x 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
## # ... with 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))## # A tibble: 365 x 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
## # ... with 355 more rowsdelays <- not_cancelled %>%
group_by(tailnum) %>%
summarise(
delay = mean(arr_delay)
)
ggplot(data = delays, mapping = aes(x = delay)) +
geom_freqpoly(binwidth = 10)
# Why is distance to some destinations more variable than to others?
not_cancelled %>%
group_by(dest) %>%
summarise(distance_sd = sd(distance)) %>%
arrange(desc(distance_sd))## # A tibble: 104 x 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
## # ... with 94 more rowsFinding first and last departure for each day
not_cancelled %>%
group_by(year, month, day) %>%
summarise(
first_dep = first(dep_time),
last_dep = last(dep_time))## # A tibble: 365 x 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
## # ... with 355 more rowsCount Distinct Values
not_cancelled %>%
group_by(dest) %>%
summarise(carriers = n_distinct(carrier)) %>%
arrange(desc(carriers))## # A tibble: 104 x 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
## # ... with 94 more rowsnot_cancelled %>%
count(tailnum, wt = distance)## # A tibble: 4,037 x 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
## # ... with 4,027 more rows# How many flights left before 5am? (these usually indicate delayed
# flights from the previous day)
not_cancelled %>%
group_by(year, month, day) %>%
summarise(n_early = sum(dep_time < 500))## # A tibble: 365 x 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
## # ... with 355 more rows# What proportion of flights are delayed by more than an hour?
not_cancelled %>%
group_by(year, month, day) %>%
summarise(hour_prop = mean(arr_delay > 60))## # A tibble: 365 x 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
## # ... with 355 more rows5.65 Grouping by multiple Variables
daily <- group_by(flights, year, month, day)
(per_day <- summarise(daily, flights = n()))## # A tibble: 365 x 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
## # ... with 355 more rows(per_month <- summarise(per_day, flights = sum(flights)))## # A tibble: 12 x 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 x 2
## year flights
## <int> <int>
## 1 2013 3367765.67 Excercises
1.Brainstorm at least 5 different ways to assess the typical delay characteristics of a group of flights. Consider the following scenarios:
A flight is 15 minutes early 50% of the time, and 15 minutes late 50% of the time.
A flight is always 10 minutes late.
A flight is 30 minutes early 50% of the time, and 30 minutes late 50% of the time.
99% of the time a flight is on time. 1% of the time it’s 2 hours late.
Which is more important: arrival delay or departure delay? I think that arrival delay is more important than departure delay because a plane can leave late but still reach its destiantion on time. Arrival is more important because it shows how much time the passgenger lost due to the delay.
2.Come up with another approach that will give you the same output as not_cancelled %>% count(dest) and not_cancelled %>% count(tailnum, wt = distance) (without using count()).
flights %>%
filter(!is.na(dep_delay), !is.na(arr_delay)) %>%
group_by(dest) %>% summarize(count = n())## # A tibble: 104 x 2
## dest count
## <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
## # ... with 94 more rows3.Our definition of cancelled flights (is.na(dep_delay) | is.na(arr_delay) ) is slightly suboptimal. Why? Which is the most important column? The chunk below shows that the NA counts are different for dep_time and arr_time, indicating that these planes could have taken off, but for unknown reasons did not land at their designated airport. I think that when deifining cancelled flights it depends whether the airplane never departed from the origin, which would make dep_time the most important column.
flights %>% select(starts_with("dep"), starts_with("arr")) %>%
sapply(function(x){sum(is.na(x))})## dep_time dep_delay arr_time arr_delay
## 8255 8255 8713 94304.Look at the number of cancelled flights per day. Is there a pattern? Is the proportion of cancelled flights related to the average delay?
As shown by the ggplotthere is a positice linear trend between the average departure delay and the proportion of flights cancelled.
flights %>% group_by(month, day) %>%
summarize(avg_dep_delay = mean(dep_delay, na.rm = TRUE),
prop_cancelled = sum(is.na(dep_time)/n())) %>%
ggplot(mapping = aes(x = avg_dep_delay, y = prop_cancelled)) +
geom_point() +
geom_smooth(method = 'lm', se = FALSE)
5.Which carrier has the worst delays? Challenge: can you disentangle the effects of bad airports vs. bad carriers? Why/why not? (Hint: think about flights %>% group_by(carrier, dest) %>% summarise(n()))
6.What does the sort argument to count() do. When might you use it? If the sort argument is set too true it will sort the ouput in descending order.
5.7 Grouped Mutates and Filters
Find the worst members of each group
popular_dests <- flights %>%
group_by(dest) %>%
filter(n() > 365)
popular_dests## # A tibble: 332,577 x 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
## # ... with 332,567 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>Standardizing to find metrics for each destiantion:
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 x 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
## # ... with 131,096 more rows5.71 Excercises
1.Refer back to the lists of useful mutate and filtering functions. Describe how each operation changes when you combine it with grouping. Combining grouping operations such as mean() or median() operate over an entire dataset, however when used in conjucntion with groupby they will only be performed on a certain group of data.
2.Which plane (tailnum) has the worst on-time record?
flights %>% group_by(tailnum) %>%
filter(dep_delay > 0) %>%
summarize(avg_delay = mean(dep_delay)) %>%
arrange(desc(avg_delay))## # A tibble: 3,885 x 2
## tailnum avg_delay
## <chr> <dbl>
## 1 N844MH 297
## 2 N452UW 291
## 3 N922EV 274
## 4 N587NW 272
## 5 N911DA 268
## 6 N665MQ 268.
## 7 N673MQ 257
## 8 N851NW 233
## 9 N654UA 227
## 10 N550NW 212.
## # ... with 3,875 more rows3.What time of day should you fly if you want to avoid delays as much as possible? 5.A.M is the best time to fly if you want to avoid delays as much as possible.
#Shows the average dealy time in miuntes for each hour of the day.
flights %>% filter (dep_delay > 0) %>%
group_by(hour) %>%
summarize(avg_delay = mean(dep_delay)) %>%
arrange(avg_delay)## # A tibble: 19 x 2
## hour avg_delay
## <dbl> <dbl>
## 1 5 15.3
## 2 7 24.1
## 3 6 24.2
## 4 9 29.7
## 5 8 29.9
## 6 12 32.3
## 7 11 32.5
## 8 10 32.6
## 9 13 33.5
## 10 14 37.1
## 11 23 38.0
## 12 15 38.8
## 13 16 43.4
## 14 17 45.3
## 15 18 46.5
## 16 22 46.5
## 17 20 49.6
## 18 21 50.3
## 19 19 51.14.For each destination, compute the total minutes of delay. For each flight, compute the proportion of the total delay for its destination.
flights %>% select(dest, arr_delay) %>% group_by(dest) %>%
filter(arr_delay > 0) %>%
mutate(total_delay = sum(arr_delay, na.rm = TRUE),
prop_delay = arr_delay / total_delay)## # A tibble: 133,004 x 4
## # Groups: dest [103]
## dest arr_delay total_delay prop_delay
## <chr> <dbl> <dbl> <dbl>
## 1 IAH 11 99391 0.000111
## 2 IAH 20 99391 0.000201
## 3 MIA 33 140424 0.000235
## 4 ORD 12 283046 0.0000424
## 5 FLL 19 202605 0.0000938
## 6 ORD 8 283046 0.0000283
## 7 LAX 7 203226 0.0000344
## 8 DFW 31 110009 0.000282
## 9 ATL 12 300299 0.0000400
## 10 DTW 16 138258 0.000116
## # ... with 132,994 more rows8.For each plane, count the number of flights before the first delay of greater than 1 hour.
flights %>% filter(!is.na(dep_delay)) %>% group_by(tailnum) %>%
mutate(max_delay = cummax(dep_delay),
less_one_hour = max_delay < 60) %>%
summarize(count = sum(less_one_hour)) %>%
arrange(desc(count))## # A tibble: 4,037 x 2
## tailnum count
## <chr> <int>
## 1 N952UW 215
## 2 N315NB 161
## 3 N705TW 160
## 4 N706TW 149
## 5 N961UW 139
## 6 N713TW 128
## 7 N346NB 127
## 8 N765US 122
## 9 N721TW 120
## 10 N5FAAA 117
## # ... with 4,027 more rows