Lista dplyr
Guilherme Ziegler Trintinalia
28/08/2022
suppressMessages(library(dplyr))
library(nycflights13)## Warning: package 'nycflights13' was built under R version 4.1.3Exercício 1
Utilizando o mesmo conjunto de dados para flights usado na aula, encontre todos os vôos que:
voos <- nycflights13::flights
voos## # 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>- Tiveram um atraso na chegada (arrival) de duas horas ou mais
La <- filter(voos, arr_delay >= 120)
La## # 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
## 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
## # ... with 10,190 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>hist(voos$arr_delay, main = "Histograma de Vôos em atraso", xlab = "Intervalos", ylab= "Frequência")
(b) Voaram com destino a Houston (IAH ou HOU).
Lb <- filter(voos, dest == c("IAH", "HOU"))
Lb## # A tibble: 4,655 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 1 623 627 -4 933 932
## 3 2013 1 1 1028 1026 2 1350 1339
## 4 2013 1 1 1114 900 134 1447 1222
## 5 2013 1 1 1208 1158 10 1540 1502
## 6 2013 1 1 1306 1300 6 1622 1610
## 7 2013 1 1 1527 1515 12 1854 1810
## 8 2013 1 1 1620 1620 0 1945 1922
## 9 2013 1 1 1725 1720 5 2045 2021
## 10 2013 1 1 1855 1848 7 2203 2200
## # ... with 4,645 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>- Foram realizados pelas companhias aéreas United, American ou Delta Airlines.
Lc <- filter(voos, carrier == c("UA","AA","DL"))## Warning in carrier == c("UA", "AA", "DL"): comprimento do objeto maior não é
## múltiplo do comprimento do objeto menorLc## # A tibble: 46,913 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 1 558 600 -2 924 917
## 3 2013 1 1 602 610 -8 812 820
## 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 1 615 615 0 833 842
## 8 2013 1 1 623 610 13 920 915
## 9 2013 1 1 643 646 -3 922 940
## 10 2013 1 1 653 700 -7 936 1009
## # ... with 46,903 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>- Partiram no verão (julho, agosto e setembro).
Ld <- filter(voos, month == c(6 & 7 & 8))
Ld## # A tibble: 27,004 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 26,994 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>- Não partiram atrasados, porém chegaram com mais de duas horas de atraso ao destino.
le <- filter(voos, dep_delay <= 0 & arr_delay >= 120)
le## # 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
## 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
## # ... with 19 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>Partiram entre meia noite e 6 h da manhã (inclusive).
lf <- filter(voos, dep_time == 0000 : 600)## Warning in dep_time == 0:600: comprimento do objeto maior não é múltiplo do
## comprimento do objeto menorlf## # A tibble: 25 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 30 556 600 -4 709 658
## 2 2013 1 30 557 600 -3 711 709
## 3 2013 1 30 559 601 -2 739 725
## 4 2013 12 11 542 545 -3 841 832
## 5 2013 12 11 544 550 -6 1021 1027
## 6 2013 12 11 557 600 -3 853 846
## 7 2013 2 20 557 600 -3 733 745
## 8 2013 2 24 556 600 -4 914 909
## 9 2013 3 30 550 600 -10 721 759
## 10 2013 3 30 555 600 -5 804 829
## # ... with 15 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>Exerício 2
Classifique os vôos para encontrar os vôos mais atrasados.
# Basta ordenar de Z a A ou do maior para o menor a coluna arr_delay
exe2 <- arrange(voos, desc(dep_delay)) # pruneura ordenação para partida.
# ordenando para quem chegou mais atrasado agora
# %>% is called the forward pipe operator in R. It provides a mechanism for chaining commands with a new forward-pipe operator, %>%. This operator will forward a value, or the result of an expression, into the next function call/expression. It is defined by the package magrittr (CRAN) and is heavily used by dplyr (CRAN).
voos%>% arrange(desc(arr_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 7 22 2257 759 898 121 1026
## 9 2013 12 5 756 1700 896 1058 2020
## 10 2013 5 3 1133 2055 878 1250 2215
## # ... 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>exe2## # 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>Exercício 3
Classifique os vˆoos de forma a encontrar os mais rápidos (velocidade mais alta)
exe3 <- mutate(voos, vel = distance/air_time*60) # km/hora
exe3 <- arrange(exe3, desc(vel)) # é comum alterar uma variável em sequência reatribuindo um valor a ela.
exe3 # plotando a variável## # A tibble: 336,776 x 20
## 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
## 7 2013 2 21 2355 2358 -3 412 438
## 8 2013 11 17 759 800 -1 1212 1255
## 9 2013 11 16 2003 1925 38 17 36
## 10 2013 11 16 2349 2359 -10 402 440
## # ... with 336,766 more rows, and 12 more variables: arr_delay <dbl>,
## # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>,
## # vel <dbl>Exercício 4
O que acontece se você incluir o nome de uma variável várias vezes dentro de select()?
exe4 <- voos %>% select(day, day, day)
exe4## # A tibble: 336,776 x 1
## day
## <int>
## 1 1
## 2 1
## 3 1
## 4 1
## 5 1
## 6 1
## 7 1
## 8 1
## 9 1
## 10 1
## # ... with 336,766 more rows# Aparece a variável uma vez só!Exercício 5
Encontre os 10 vôos mais atrados usando arrange() e a função min rank().
ex5 <- arrange(voos, min_rank(desc(dep_delay))) # ordena do maior par ao menor dep_delay e pega o atribui um número para o elemento com base se ele é maior que os outros elementos na tabela. Exemplo: Se o elemento 10 esta acima do elemnto 3 então, 3 recebe ranking 1 e 10 recebe ranking 2, porém, se houvesse um 15, entre eles, 15, receberia 3, 10 receberia 2 e 3 receberia o ranking 1.
ex5 <- mutate(ex5, voosatrasados = dep_delay) # cria uma coluna com o resultado acima
ex5## # A tibble: 336,776 x 20
## 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 12 more variables: arr_delay <dbl>,
## # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>,
## # voosatrasados <dbl>Exercício 6
Usando mutate() crie uma coluna com a média da variável tempo em ar (air time).
ex6= mutate(voos, médiatemponoar = mean(air_time, na.rm = TRUE))
ex6## # A tibble: 336,776 x 20
## 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 12 more variables: arr_delay <dbl>,
## # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>,
## # médiatemponoar <dbl>Obrigado