Date & time

library("tidyverse")

## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --

## v ggplot2 3.3.3     v purrr   0.3.4
## v tibble  3.1.0     v dplyr   1.0.5
## v tidyr   1.1.3     v stringr 1.4.0
## v readr   1.4.0     v forcats 0.5.1

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library("lubridate")

## 
## Attaching package: 'lubridate'

## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

library("nycflights13")
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 %>%
  filter(!is.na(dep_time)) %>%
  mutate(dep_hour = update(dep_time, yday = 1)) %>%
  mutate(month = factor(month(dep_time))) %>%
  ggplot(aes(dep_hour, color = month)) +
  geom_freqpoly(aes(y = ..density..), binwidth = 60 * 60)

sched_dep <- flights_dt %>%
  mutate(minute = minute(sched_dep_time)) %>%
  group_by(minute) %>%
  summarise(
    avg_delay = mean(arr_delay, na.rm = TRUE),
    n = n()
  )
flights_dt %>%
  filter(!is.na(dep_time)) %>%
  mutate(dep_hour = update(dep_time, yday = 1)) %>%
  mutate(month = factor(month(dep_time))) %>%
  ggplot(aes(dep_hour, color = month)) +
  geom_freqpoly(binwidth = 60 * 60)

flights_dt %>%
  mutate(dep_time_ = sched_dep_time + dep_delay * 60) %>%
  filter(dep_time_ != dep_time) %>%
  select(dep_time_, dep_time, sched_dep_time, dep_delay)

## # A tibble: 1,205 x 4
##    dep_time_           dep_time            sched_dep_time      dep_delay
##    <dttm>              <dttm>              <dttm>                  <dbl>
##  1 2013-01-02 08:48:00 2013-01-01 08:48:00 2013-01-01 18:35:00       853
##  2 2013-01-03 00:42:00 2013-01-02 00:42:00 2013-01-02 23:59:00        43
##  3 2013-01-03 01:26:00 2013-01-02 01:26:00 2013-01-02 22:50:00       156
##  4 2013-01-04 00:32:00 2013-01-03 00:32:00 2013-01-03 23:59:00        33
##  5 2013-01-04 00:50:00 2013-01-03 00:50:00 2013-01-03 21:45:00       185
##  6 2013-01-04 02:35:00 2013-01-03 02:35:00 2013-01-03 23:59:00       156
##  7 2013-01-05 00:25:00 2013-01-04 00:25:00 2013-01-04 23:59:00        26
##  8 2013-01-05 01:06:00 2013-01-04 01:06:00 2013-01-04 22:45:00       141
##  9 2013-01-06 00:14:00 2013-01-05 00:14:00 2013-01-05 23:59:00        15
## 10 2013-01-06 00:37:00 2013-01-05 00:37:00 2013-01-05 22:30:00       127
## # ... with 1,195 more rows