Create flight_times

flight_times

@@ -0,0 +1,73 @@
+library(tidyverse)
+library(lubridate)
+library(nycflights13)
+
+flights %>% select(year, month, day, hour, minute)
+
+flights %>% select(year, month, day, hour, minute) %>%
+        mutate(departure = make_date(year, month, day))
+
+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)
+
+flights_dt %>% filter(dep_time < ymd(20130102)) %>%
+        ggplot(aes(dep_time)) +
+        geom_freqpoly(binwidth = 600)
+
+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) %>%
+        summarize(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) %>%
+        summarize(avg_delay = mean(arr_delay, na.rm = TRUE),
+                  n = n())
+
+ggplot(sched_dep, aes(minute, avg_delay)) + geom_line ()
+
+ggplot(sched_dep, aes(minute, n)) + geom_line()
+
+flights_dt %>%
+        count(week = floor_date(dep_time, "week")) %>%
+        ggplot(aes(week, n)) + geom_line()
+
+flights_dt %>%
+        filter(arr_time < dep_time)
+
+flights_dt <- flights_dt %>%
+        mutate(
+        overnight = arr_time < dep_time,
+        arr_time = arr_time + days(overnight * 1),
+        sched_arr_time = sched_arr_time + days(overnight * 1)
+)
+
+flights_dt
+
+flights_dt %>% filter(overnight, arr_time < dep_time)
+