library(tidyverse)── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
✔ ggplot2 3.4.0 ✔ purrr 1.0.1
✔ tibble 3.1.8 ✔ dplyr 1.1.0
✔ tidyr 1.3.0 ✔ stringr 1.5.0
✔ readr 2.1.4 ✔ forcats 1.0.0
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag() masks stats::lag()library(nycflights13)
library(RColorBrewer)
data(flights)First, I removed NA values from the departure times and delay times.
flights_nona <- flights %>%
filter(!is.na(dep_time) & !is.na(arr_delay))Using group_by, and summarize
by_tailnum <- flights_nona %>%
group_by(tailnum, month) %>%
summarise(count = n(),
deptime = mean(dep_time),
delay = mean(arr_delay))`summarise()` has grouped output by 'tailnum'. You can override using the
`.groups` argument.delay <- filter(by_tailnum, count > 20)delay$month <- as.factor(delay$month)
delay2 <- delay %>%
filter(month %in% c(1, 2, 3))ggplot(delay2, aes(deptime, delay, color = month)) +
geom_point(aes(size = count), alpha = 1/2) +
ggtitle("Delay of flights according to the time of departure") +
xlab("Departure time (hhmm)") +
ylab("Delay time (minutes)") +
geom_smooth() +
scale_size_area() `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
In this visualization, we can see the delay times according to the departure times. Notice that many flights between 10 am and 4 pm tend to have up to 30 minutes of delays. This is interesting consider that it is a very convenient time to fly because one does not have to wake up very early or stay up until late at night. I have also considered the first three months of the year to filter this data frame, so that we can visualize it better. I would also like to highlight that, while the period of time between 10 am and 4 pm have more delays, it also has a considerable concentration of flights that depart earlier than expected.