Stat 450 Dates and Times

Chapter 16 Dates and Times

library(tidyverse)
library(lubridate)

Attaching package: ‘lubridate’

The following object is masked from ‘package:igraph’:

    %--%

The following object is masked from ‘package:base’:

    date

library(nycflights13)

today()

[1] "2018-12-03"

now()

[1] "2018-12-03 10:23:15 PST"

Dates from strings

ymd("2017-01-31")

[1] "2017-01-31"

mdy("January 31st, 2017")

[1] "2017-01-31"

dmy("31-Jan-2017")

[1] "2017-01-31"

Dates with times

ymd_hms("2017-01-31 20:11:59")

[1] "2017-01-31 20:11:59 UTC"

mdy_hm("01/31/2017 08:01")

[1] "2017-01-31 08:01:00 UTC"

flights %>% 
  select(year, month, day, hour, minute)

flights %>% 
  select(year, month, day, hour, minute) %>% 
  mutate(departure = make_datetime(year, month, day, hour, minute))

make_datetime_100 <- function(year, month, day, time) {
  make_datetime(year, month, day, time %/% 100, time %% 100)
}
flights_dt <- flights %>% 
  filter(!is.na(dep_time), !is.na(arr_time)) %>% 
  mutate(
    dep_time = make_datetime_100(year, month, day, dep_time),
    arr_time = make_datetime_100(year, month, day, arr_time),
    sched_dep_time = make_datetime_100(year, month, day, sched_dep_time),
    sched_arr_time = make_datetime_100(year, month, day, sched_arr_time)
  ) %>% 
  select(origin, dest, ends_with("delay"), ends_with("time"))
flights_dt

flights_dt %>% 
  ggplot(aes(dep_time)) + 
  geom_freqpoly(binwidth = 86400) # 86400 seconds = 1 day

flights_dt %>% 
  filter(dep_time < ymd(20130102)) %>% 
  ggplot(aes(dep_time)) + 
  geom_freqpoly(binwidth = 600) # 600 s = 10 minutes

Getting the components

datetime <- ymd_hms("2016-07-08 12:34:56")
year(datetime)

[1] 2016

month(datetime)

[1] 7

mday(datetime)

[1] 8

yday(datetime)

[1] 190

wday(datetime)

[1] 6

flights_dt %>% 
  mutate(wday = wday(dep_time, label = TRUE)) %>% 
  ggplot(aes(x = wday)) +
    geom_bar()

flights_dt %>% 
  mutate(minute = minute(dep_time)) %>% 
  group_by(minute) %>% 
  summarise(
    avg_delay = mean(arr_delay, na.rm = TRUE),
    n = n()) %>% 
  ggplot(aes(minute, avg_delay)) +
    geom_line()

sched_dep <- flights_dt %>% 
  mutate(minute = minute(sched_dep_time)) %>% 
  group_by(minute) %>% 
  summarise(
    avg_delay = mean(arr_delay, na.rm = TRUE),
    n = n())
ggplot(sched_dep, aes(minute, avg_delay)) +
  geom_line()

Time zones

Sys.timezone()

[1] "America/Los_Angeles"

All of the time zones

length(OlsonNames())

[1] 606

head(OlsonNames())

[1] "Africa/Abidjan"     "Africa/Accra"       "Africa/Addis_Ababa" "Africa/Algiers"     "Africa/Asmara"     
[6] "Africa/Asmera"     

(x1 <- ymd_hms("2015-06-01 12:00:00", tz = "America/New_York"))

[1] "2015-06-01 12:00:00 EDT"

(x2 <- ymd_hms("2015-06-01 18:00:00", tz = "Europe/Copenhagen"))

[1] "2015-06-01 18:00:00 CEST"

(x3 <- ymd_hms("2015-06-02 04:00:00", tz = "Pacific/Auckland"))

[1] "2015-06-02 04:00:00 NZST"