#Chapter 12
library(tidyverse)## ── Attaching packages ─────────────────────────────────────────────── tidyverse 1.3.0 ──## ✓ ggplot2 3.2.1 ✓ purrr 0.3.3
## ✓ tibble 2.1.3 ✓ dplyr 0.8.3
## ✓ tidyr 1.0.0 ✓ stringr 1.4.0
## ✓ readr 1.3.1 ✓ forcats 0.4.0## ── Conflicts ────────────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(nycflights13)table1## # A tibble: 6 x 4
## country year cases population
## <chr> <int> <int> <int>
## 1 Afghanistan 1999 745 19987071
## 2 Afghanistan 2000 2666 20595360
## 3 Brazil 1999 37737 172006362
## 4 Brazil 2000 80488 174504898
## 5 China 1999 212258 1272915272
## 6 China 2000 213766 1280428583table2## # A tibble: 12 x 4
## country year type count
## <chr> <int> <chr> <int>
## 1 Afghanistan 1999 cases 745
## 2 Afghanistan 1999 population 19987071
## 3 Afghanistan 2000 cases 2666
## 4 Afghanistan 2000 population 20595360
## 5 Brazil 1999 cases 37737
## 6 Brazil 1999 population 172006362
## 7 Brazil 2000 cases 80488
## 8 Brazil 2000 population 174504898
## 9 China 1999 cases 212258
## 10 China 1999 population 1272915272
## 11 China 2000 cases 213766
## 12 China 2000 population 1280428583table3## # A tibble: 6 x 3
## country year rate
## * <chr> <int> <chr>
## 1 Afghanistan 1999 745/19987071
## 2 Afghanistan 2000 2666/20595360
## 3 Brazil 1999 37737/172006362
## 4 Brazil 2000 80488/174504898
## 5 China 1999 212258/1272915272
## 6 China 2000 213766/1280428583table4a## # A tibble: 3 x 3
## country `1999` `2000`
## * <chr> <int> <int>
## 1 Afghanistan 745 2666
## 2 Brazil 37737 80488
## 3 China 212258 213766table4b## # A tibble: 3 x 3
## country `1999` `2000`
## * <chr> <int> <int>
## 1 Afghanistan 19987071 20595360
## 2 Brazil 172006362 174504898
## 3 China 1272915272 1280428583# Compute rate per 10,000
table1 %>%
mutate(rate = cases / population * 10000)## # A tibble: 6 x 5
## country year cases population rate
## <chr> <int> <int> <int> <dbl>
## 1 Afghanistan 1999 745 19987071 0.373
## 2 Afghanistan 2000 2666 20595360 1.29
## 3 Brazil 1999 37737 172006362 2.19
## 4 Brazil 2000 80488 174504898 4.61
## 5 China 1999 212258 1272915272 1.67
## 6 China 2000 213766 1280428583 1.67# Compute cases per year
table1 %>%
count(year, wt = cases)## # A tibble: 2 x 2
## year n
## <int> <int>
## 1 1999 250740
## 2 2000 296920#12.2.1 Exercises 1. For table1, the four variables are in columns and each observation is in a row. For table2, there are two variables combined into one, showing that there are actually double the amount of observations in table1. For table3, the count variable is changed to rate. Inside the rate variable is the count variable we created earlier, which includes cases and population. For table4, the tables are split into two, so that cases and population can be analyzed seperatley. 2.
table2case <- filter(table2, type=="cases") %>%
rename(cases = count) %>%
arrange(country, year)
table2population <- filter(table2, type =="population") %>%
rename(population = count) %>%
arrange(country, year)table2casespercapita <- tibble(
year = table2case$year,
country = table2case$country,
cases = table2case$cases,
population = table2population$population
) %>%
mutate(cases_per_capita = (cases / population) * 10000) %>%
select(country,year, cases_per_capita)table2casespercapita <- table2casespercapita %>%
mutate(type="cases_per_capita") %>%
rename(count = cases_per_capita)bind_rows(table2, table2casespercapita) %>%
arrange (country, year, type, count)## # A tibble: 18 x 4
## country year type count
## <chr> <int> <chr> <dbl>
## 1 Afghanistan 1999 cases 7.45e+2
## 2 Afghanistan 1999 cases_per_capita 3.73e-1
## 3 Afghanistan 1999 population 2.00e+7
## 4 Afghanistan 2000 cases 2.67e+3
## 5 Afghanistan 2000 cases_per_capita 1.29e+0
## 6 Afghanistan 2000 population 2.06e+7
## 7 Brazil 1999 cases 3.77e+4
## 8 Brazil 1999 cases_per_capita 2.19e+0
## 9 Brazil 1999 population 1.72e+8
## 10 Brazil 2000 cases 8.05e+4
## 11 Brazil 2000 cases_per_capita 4.61e+0
## 12 Brazil 2000 population 1.75e+8
## 13 China 1999 cases 2.12e+5
## 14 China 1999 cases_per_capita 1.67e+0
## 15 China 1999 population 1.27e+9
## 16 China 2000 cases 2.14e+5
## 17 China 2000 cases_per_capita 1.67e+0
## 18 China 2000 population 1.28e+9table4c<-tibble(
country = table4a$country,
`1999` = table4a[["1999"]] / table4b[["1999"]] * 10000,
`2000` = table4a[["1999"]] / table4b[["2000"]] * 10000
)table4c## # A tibble: 3 x 3
## country `1999` `2000`
## <chr> <dbl> <dbl>
## 1 Afghanistan 0.373 0.362
## 2 Brazil 2.19 2.16
## 3 China 1.67 1.66Since there are more labeled varibales, table2 is easier to interperet. Table 4c does not have cases and population split, so it is harder to read.
table4a %>%
pivot_longer(c(`1999`, `2000`), names_to = "year", values_to = "cases")## # A tibble: 6 x 3
## country year cases
## <chr> <chr> <int>
## 1 Afghanistan 1999 745
## 2 Afghanistan 2000 2666
## 3 Brazil 1999 37737
## 4 Brazil 2000 80488
## 5 China 1999 212258
## 6 China 2000 213766table4b %>%
pivot_longer(c(`1999`, `2000`), names_to = "year", values_to = "population")## # A tibble: 6 x 3
## country year population
## <chr> <chr> <int>
## 1 Afghanistan 1999 19987071
## 2 Afghanistan 2000 20595360
## 3 Brazil 1999 172006362
## 4 Brazil 2000 174504898
## 5 China 1999 1272915272
## 6 China 2000 1280428583tidy4a <- table4a %>%
pivot_longer(c(`1999`, `2000`), names_to = "year", values_to = "cases")tidy4b <- table4b %>%
pivot_longer(c(`1999`, `2000`), names_to = "year", values_to = "population")left_join(tidy4a, tidy4b)## Joining, by = c("country", "year")## # A tibble: 6 x 4
## country year cases population
## <chr> <chr> <int> <int>
## 1 Afghanistan 1999 745 19987071
## 2 Afghanistan 2000 2666 20595360
## 3 Brazil 1999 37737 172006362
## 4 Brazil 2000 80488 174504898
## 5 China 1999 212258 1272915272
## 6 China 2000 213766 1280428583table2 %>%
pivot_wider(names_from = type, values_from = count)## # A tibble: 6 x 4
## country year cases population
## <chr> <int> <int> <int>
## 1 Afghanistan 1999 745 19987071
## 2 Afghanistan 2000 2666 20595360
## 3 Brazil 1999 37737 172006362
## 4 Brazil 2000 80488 174504898
## 5 China 1999 212258 1272915272
## 6 China 2000 213766 1280428583#12.3.3 Exercises 1.
stocks <- tibble(
year = c(2015, 2015, 2016, 2016),
half = c( 1, 2, 1, 2),
return = c(1.88, 0.59, 0.92, 0.17)
)
stocks %>%
pivot_wider(names_from = year, values_from = return) %>%
pivot_longer(`2015`:`2016`, names_to = "year", values_to = "return")## # A tibble: 4 x 3
## half year return
## <dbl> <chr> <dbl>
## 1 1 2015 1.88
## 2 1 2016 0.92
## 3 2 2015 0.59
## 4 2 2016 0.17table3 %>%
separate(rate, into = c("cases", "population"))## # A tibble: 6 x 4
## country year cases population
## <chr> <int> <chr> <chr>
## 1 Afghanistan 1999 745 19987071
## 2 Afghanistan 2000 2666 20595360
## 3 Brazil 1999 37737 172006362
## 4 Brazil 2000 80488 174504898
## 5 China 1999 212258 1272915272
## 6 China 2000 213766 1280428583table3 %>%
separate(rate, into = c("cases", "population"), convert = TRUE)## # A tibble: 6 x 4
## country year cases population
## <chr> <int> <int> <int>
## 1 Afghanistan 1999 745 19987071
## 2 Afghanistan 2000 2666 20595360
## 3 Brazil 1999 37737 172006362
## 4 Brazil 2000 80488 174504898
## 5 China 1999 212258 1272915272
## 6 China 2000 213766 1280428583table3 %>%
separate(year, into = c("century", "year"), sep = 2)## # A tibble: 6 x 4
## country century year rate
## <chr> <chr> <chr> <chr>
## 1 Afghanistan 19 99 745/19987071
## 2 Afghanistan 20 00 2666/20595360
## 3 Brazil 19 99 37737/172006362
## 4 Brazil 20 00 80488/174504898
## 5 China 19 99 212258/1272915272
## 6 China 20 00 213766/1280428583table5 %>%
unite(new, century, year)## # A tibble: 6 x 3
## country new rate
## <chr> <chr> <chr>
## 1 Afghanistan 19_99 745/19987071
## 2 Afghanistan 20_00 2666/20595360
## 3 Brazil 19_99 37737/172006362
## 4 Brazil 20_00 80488/174504898
## 5 China 19_99 212258/1272915272
## 6 China 20_00 213766/1280428583table5 %>%
unite(new, century, year, sep = "")## # A tibble: 6 x 3
## country new rate
## <chr> <chr> <chr>
## 1 Afghanistan 1999 745/19987071
## 2 Afghanistan 2000 2666/20595360
## 3 Brazil 1999 37737/172006362
## 4 Brazil 2000 80488/174504898
## 5 China 1999 212258/1272915272
## 6 China 2000 213766/1280428583stocks <- tibble(
year = c(2015, 2015, 2015, 2015, 2016, 2016, 2016),
qtr = c( 1, 2, 3, 4, 2, 3, 4),
return = c(1.88, 0.59, 0.35, NA, 0.92, 0.17, 2.66)
)stocks %>%
pivot_wider(names_from = year, values_from = return)## # A tibble: 4 x 3
## qtr `2015` `2016`
## <dbl> <dbl> <dbl>
## 1 1 1.88 NA
## 2 2 0.59 0.92
## 3 3 0.35 0.17
## 4 4 NA 2.66stocks %>%
pivot_wider(names_from = year, values_from = return) %>%
pivot_longer(
cols = c(`2015`, `2016`),
names_to = "year",
values_to = "return",
values_drop_na = TRUE
)## # A tibble: 6 x 3
## qtr year return
## <dbl> <chr> <dbl>
## 1 1 2015 1.88
## 2 2 2015 0.59
## 3 2 2016 0.92
## 4 3 2015 0.35
## 5 3 2016 0.17
## 6 4 2016 2.66stocks %>%
complete(year, qtr)## # A tibble: 8 x 3
## year qtr return
## <dbl> <dbl> <dbl>
## 1 2015 1 1.88
## 2 2015 2 0.59
## 3 2015 3 0.35
## 4 2015 4 NA
## 5 2016 1 NA
## 6 2016 2 0.92
## 7 2016 3 0.17
## 8 2016 4 2.66treatment <- tribble(
~ person, ~ treatment, ~response,
"Derrick Whitmore", 1, 7,
NA, 2, 10,
NA, 3, 9,
"Katherine Burke", 1, 4
)treatment %>%
fill(person)## # A tibble: 4 x 3
## person treatment response
## <chr> <dbl> <dbl>
## 1 Derrick Whitmore 1 7
## 2 Derrick Whitmore 2 10
## 3 Derrick Whitmore 3 9
## 4 Katherine Burke 1 4who## # A tibble: 7,240 x 60
## country iso2 iso3 year new_sp_m014 new_sp_m1524 new_sp_m2534 new_sp_m3544
## <chr> <chr> <chr> <int> <int> <int> <int> <int>
## 1 Afghan… AF AFG 1980 NA NA NA NA
## 2 Afghan… AF AFG 1981 NA NA NA NA
## 3 Afghan… AF AFG 1982 NA NA NA NA
## 4 Afghan… AF AFG 1983 NA NA NA NA
## 5 Afghan… AF AFG 1984 NA NA NA NA
## 6 Afghan… AF AFG 1985 NA NA NA NA
## 7 Afghan… AF AFG 1986 NA NA NA NA
## 8 Afghan… AF AFG 1987 NA NA NA NA
## 9 Afghan… AF AFG 1988 NA NA NA NA
## 10 Afghan… AF AFG 1989 NA NA NA NA
## # … with 7,230 more rows, and 52 more variables: new_sp_m4554 <int>,
## # new_sp_m5564 <int>, new_sp_m65 <int>, new_sp_f014 <int>,
## # new_sp_f1524 <int>, new_sp_f2534 <int>, new_sp_f3544 <int>,
## # new_sp_f4554 <int>, new_sp_f5564 <int>, new_sp_f65 <int>,
## # new_sn_m014 <int>, new_sn_m1524 <int>, new_sn_m2534 <int>,
## # new_sn_m3544 <int>, new_sn_m4554 <int>, new_sn_m5564 <int>,
## # new_sn_m65 <int>, new_sn_f014 <int>, new_sn_f1524 <int>,
## # new_sn_f2534 <int>, new_sn_f3544 <int>, new_sn_f4554 <int>,
## # new_sn_f5564 <int>, new_sn_f65 <int>, new_ep_m014 <int>,
## # new_ep_m1524 <int>, new_ep_m2534 <int>, new_ep_m3544 <int>,
## # new_ep_m4554 <int>, new_ep_m5564 <int>, new_ep_m65 <int>,
## # new_ep_f014 <int>, new_ep_f1524 <int>, new_ep_f2534 <int>,
## # new_ep_f3544 <int>, new_ep_f4554 <int>, new_ep_f5564 <int>,
## # new_ep_f65 <int>, newrel_m014 <int>, newrel_m1524 <int>,
## # newrel_m2534 <int>, newrel_m3544 <int>, newrel_m4554 <int>,
## # newrel_m5564 <int>, newrel_m65 <int>, newrel_f014 <int>,
## # newrel_f1524 <int>, newrel_f2534 <int>, newrel_f3544 <int>,
## # newrel_f4554 <int>, newrel_f5564 <int>, newrel_f65 <int>who1 <- who %>%
pivot_longer(
cols = new_sp_m014:newrel_f65,
names_to = "key",
values_to = "cases",
values_drop_na = TRUE
)who1## # A tibble: 76,046 x 6
## country iso2 iso3 year key cases
## <chr> <chr> <chr> <int> <chr> <int>
## 1 Afghanistan AF AFG 1997 new_sp_m014 0
## 2 Afghanistan AF AFG 1997 new_sp_m1524 10
## 3 Afghanistan AF AFG 1997 new_sp_m2534 6
## 4 Afghanistan AF AFG 1997 new_sp_m3544 3
## 5 Afghanistan AF AFG 1997 new_sp_m4554 5
## 6 Afghanistan AF AFG 1997 new_sp_m5564 2
## 7 Afghanistan AF AFG 1997 new_sp_m65 0
## 8 Afghanistan AF AFG 1997 new_sp_f014 5
## 9 Afghanistan AF AFG 1997 new_sp_f1524 38
## 10 Afghanistan AF AFG 1997 new_sp_f2534 36
## # … with 76,036 more rowswho1 %>%
count(key)## # A tibble: 56 x 2
## key n
## <chr> <int>
## 1 new_ep_f014 1032
## 2 new_ep_f1524 1021
## 3 new_ep_f2534 1021
## 4 new_ep_f3544 1021
## 5 new_ep_f4554 1017
## 6 new_ep_f5564 1017
## 7 new_ep_f65 1014
## 8 new_ep_m014 1038
## 9 new_ep_m1524 1026
## 10 new_ep_m2534 1020
## # … with 46 more rowswho2 <- who1 %>%
mutate(names_from = stringr::str_replace(key, "newrel", "new_rel"))who3 <- who2 %>%
separate(key, c("new", "type", "sexage"), sep = "_")## Warning: Expected 3 pieces. Missing pieces filled with `NA` in 2580 rows [243,
## 244, 679, 680, 681, 682, 683, 684, 685, 686, 687, 688, 689, 690, 691, 692, 903,
## 904, 905, 906, ...].who3## # A tibble: 76,046 x 9
## country iso2 iso3 year new type sexage cases names_from
## <chr> <chr> <chr> <int> <chr> <chr> <chr> <int> <chr>
## 1 Afghanistan AF AFG 1997 new sp m014 0 new_sp_m014
## 2 Afghanistan AF AFG 1997 new sp m1524 10 new_sp_m1524
## 3 Afghanistan AF AFG 1997 new sp m2534 6 new_sp_m2534
## 4 Afghanistan AF AFG 1997 new sp m3544 3 new_sp_m3544
## 5 Afghanistan AF AFG 1997 new sp m4554 5 new_sp_m4554
## 6 Afghanistan AF AFG 1997 new sp m5564 2 new_sp_m5564
## 7 Afghanistan AF AFG 1997 new sp m65 0 new_sp_m65
## 8 Afghanistan AF AFG 1997 new sp f014 5 new_sp_f014
## 9 Afghanistan AF AFG 1997 new sp f1524 38 new_sp_f1524
## 10 Afghanistan AF AFG 1997 new sp f2534 36 new_sp_f2534
## # … with 76,036 more rowswho3 %>%
count(new)## # A tibble: 2 x 2
## new n
## <chr> <int>
## 1 new 73466
## 2 newrel 2580who4 <- who3 %>%
select(-new, -iso2, -iso3)who5 <- who4 %>%
separate(sexage, c("sex", "age"), sep = 1)who5## # A tibble: 76,046 x 7
## country year type sex age cases names_from
## <chr> <int> <chr> <chr> <chr> <int> <chr>
## 1 Afghanistan 1997 sp m 014 0 new_sp_m014
## 2 Afghanistan 1997 sp m 1524 10 new_sp_m1524
## 3 Afghanistan 1997 sp m 2534 6 new_sp_m2534
## 4 Afghanistan 1997 sp m 3544 3 new_sp_m3544
## 5 Afghanistan 1997 sp m 4554 5 new_sp_m4554
## 6 Afghanistan 1997 sp m 5564 2 new_sp_m5564
## 7 Afghanistan 1997 sp m 65 0 new_sp_m65
## 8 Afghanistan 1997 sp f 014 5 new_sp_f014
## 9 Afghanistan 1997 sp f 1524 38 new_sp_f1524
## 10 Afghanistan 1997 sp f 2534 36 new_sp_f2534
## # … with 76,036 more rowswho %>%
pivot_longer(
cols = new_sp_m014:newrel_f65,
names_to = "key",
values_to = "cases",
values_drop_na = TRUE
) %>%
mutate(
key = stringr::str_replace(key, "newrel", "new_rel")
) %>%
separate(key, c("new", "var", "sexage")) %>%
select(-new, -iso2, -iso3) %>%
separate(sexage, c("sex", "age"), sep = 1)## # A tibble: 76,046 x 6
## country year var sex age cases
## <chr> <int> <chr> <chr> <chr> <int>
## 1 Afghanistan 1997 sp m 014 0
## 2 Afghanistan 1997 sp m 1524 10
## 3 Afghanistan 1997 sp m 2534 6
## 4 Afghanistan 1997 sp m 3544 3
## 5 Afghanistan 1997 sp m 4554 5
## 6 Afghanistan 1997 sp m 5564 2
## 7 Afghanistan 1997 sp m 65 0
## 8 Afghanistan 1997 sp f 014 5
## 9 Afghanistan 1997 sp f 1524 38
## 10 Afghanistan 1997 sp f 2534 36
## # … with 76,036 more rows#Chapter 5
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>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>filter(flights, month == 1)## # 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>sqrt(2) ^ 2 == 2## [1] FALSE1 / 49 * 49 == 1## [1] FALSEnear(sqrt(2) ^ 2, 2)## [1] TRUEnear(1 / 49 * 49, 1)## [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>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>NA > 5## [1] NA10 == NA## [1] NANA + 10## [1] NANA / 2## [1] NANA == NA## [1] NAx <- NA
y <- NAis.na(x)## [1] TRUEdf <- tibble(x = c(1, NA, 3))
filter(df, x > 1)## # A tibble: 1 x 1
## x
## <dbl>
## 1 3filter(df, is.na(x) | x > 1)## # A tibble: 2 x 1
## x
## <dbl>
## 1 NA
## 2 3arrange(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>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 NAarrange(df, desc(x))## # A tibble: 3 x 1
## x
## <dbl>
## 1 5
## 2 2
## 3 NAselect(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 rowsselect(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 rowsselect(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>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>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 rows(x <- 1:10)## [1] 1 2 3 4 5 6 7 8 9 10lag(x)## [1] NA 1 2 3 4 5 6 7 8 9lead(x)## [1] 2 3 4 5 6 7 8 9 10 NAx## [1] 1 2 3 4 5 6 7 8 9 10cumsum(x)## [1] 1 3 6 10 15 21 28 36 45 55cummean(x)## [1] 1.0 1.5 2.0 2.5 3.0 3.5 4.0 4.5 5.0 5.5y <- c(1, 2, 2, NA, 3, 4)
min_rank(y)## [1] 1 2 2 NA 4 5min_rank(desc(y))## [1] 5 3 3 NA 2 1row_number(y)## [1] 1 2 3 NA 4 5dense_rank(y)## [1] 1 2 2 NA 3 4percent_rank(y)## [1] 0.00 0.25 0.25 NA 0.75 1.00cume_dist(y)## [1] 0.2 0.6 0.6 NA 0.8 1.0summarise(flights, delay = mean(dep_delay, na.rm = TRUE))## # A tibble: 1 x 1
## delay
## <dbl>
## 1 12.6by_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 rowsby_dest <- group_by(flights, dest)
delay <- summarise(by_dest,
count = n(),
dist = mean(distance, na.rm = TRUE),
delay = mean(arr_delay, na.rm = TRUE)
)
delay <- filter(delay, count > 20, dest != "HNL")delays <- 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)
)delays <- not_cancelled %>%
group_by(tailnum) %>%
summarise(
delay = mean(arr_delay, na.rm = TRUE),
n = n()
)not_cancelled %>%
group_by(year, month, day) %>%
summarise(
avg_delay1 = mean(arr_delay),
avg_delay2 = mean(arr_delay[arr_delay > 0]) # the average positive delay
)## # A tibble: 365 x 5
## # Groups: year, month [12]
## year month day avg_delay1 avg_delay2
## <int> <int> <int> <dbl> <dbl>
## 1 2013 1 1 12.7 32.5
## 2 2013 1 2 12.7 32.0
## 3 2013 1 3 5.73 27.7
## 4 2013 1 4 -1.93 28.3
## 5 2013 1 5 -1.53 22.6
## 6 2013 1 6 4.24 24.4
## 7 2013 1 7 -4.95 27.8
## 8 2013 1 8 -3.23 20.8
## 9 2013 1 9 -0.264 25.6
## 10 2013 1 10 -5.90 27.3
## # … with 355 more rowsnot_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 rowsnot_cancelled %>%
group_by(year, month, day) %>%
summarise(
first = min(dep_time),
last = max(dep_time)
)## # A tibble: 365 x 5
## # Groups: year, month [12]
## year month day first last
## <int> <int> <int> <int> <int>
## 1 2013 1 1 517 2356
## 2 2013 1 2 42 2354
## 3 2013 1 3 32 2349
## 4 2013 1 4 25 2358
## 5 2013 1 5 14 2357
## 6 2013 1 6 16 2355
## 7 2013 1 7 49 2359
## 8 2013 1 8 454 2351
## 9 2013 1 9 2 2252
## 10 2013 1 10 3 2320
## # … with 355 more rowsnot_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 rowsnot_cancelled %>%
group_by(year, month, day) %>%
mutate(r = min_rank(desc(dep_time))) %>%
filter(r %in% range(r))## # A tibble: 770 x 20
## # Groups: year, month, day [365]
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <int> <int> <dbl> <int> <int>
## 1 2013 1 1 517 515 2 830 819
## 2 2013 1 1 2356 2359 -3 425 437
## 3 2013 1 2 42 2359 43 518 442
## 4 2013 1 2 2354 2359 -5 413 437
## 5 2013 1 3 32 2359 33 504 442
## 6 2013 1 3 2349 2359 -10 434 445
## 7 2013 1 4 25 2359 26 505 442
## 8 2013 1 4 2358 2359 -1 429 437
## 9 2013 1 4 2358 2359 -1 436 445
## 10 2013 1 5 14 2359 15 503 445
## # … with 760 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>, r <int>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(dest)## # A tibble: 104 x 2
## dest n
## <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 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 rowsnot_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 rowsnot_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 rowsdaily <- 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 336776daily %>%
ungroup() %>%
summarise(flights = n())## # A tibble: 1 x 1
## flights
## <int>
## 1 336776flights_sml %>%
group_by(year, month, day) %>%
filter(rank(desc(arr_delay)) < 10)## # A tibble: 3,306 x 7
## # Groups: year, month, day [365]
## year month day dep_delay arr_delay distance air_time
## <int> <int> <int> <dbl> <dbl> <dbl> <dbl>
## 1 2013 1 1 853 851 184 41
## 2 2013 1 1 290 338 1134 213
## 3 2013 1 1 260 263 266 46
## 4 2013 1 1 157 174 213 60
## 5 2013 1 1 216 222 708 121
## 6 2013 1 1 255 250 589 115
## 7 2013 1 1 285 246 1085 146
## 8 2013 1 1 192 191 199 44
## 9 2013 1 1 379 456 1092 222
## 10 2013 1 2 224 207 550 94
## # … with 3,296 more rowspopular_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>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 rows