Ch6

library(tidyverse)
library(openintro)
data("nycflights")

Exercise 1

names(nycflights)
ggplot(data = nycflights, aes(x = dep_delay)) +
  geom_histogram()
ggplot(data = nycflights, aes(x = dep_delay)) +
  geom_histogram(binwidth = 15)
ggplot(data = nycflights, aes(x = dep_delay)) +
  geom_histogram(binwidth = 150)

Exercise 2

sfo_feb_flights <- nycflights %>%
  filter(dest == "SFO", month == 2)
glimpse(sfo_feb_flights)

Exercise 3

ggplot(data = sfo_feb_flights, aes(x = arr_delay)) +
  geom_histogram(binwidth=10)
sfo_feb_flights %>%
  summarise(mean_ad = mean(arr_delay), median_ad = median(arr_delay), iqr_ad = IQR(arr_delay), n_flights = n())

Exercise 4

sfo_feb_flights %>%
  group_by(carrier) %>%
  summarise(median_ad = median(arr_delay), iqr_ad = IQR(arr_delay), n_flights = n())

Exercise 5

nycflights <- nycflights %>%
  mutate(dep_type = ifelse(dep_delay < 5, "on time", "delayed"))
nycflights %>%
  group_by(origin) %>%
  summarise(ot_dep_rate = sum(dep_type == "on time") / n()) %>%
  arrange(desc(ot_dep_rate))

Exercise 6

ggplot(data = nycflights, aes(x = origin, fill = dep_type)) +
  geom_bar()

Exercise 7

nycflights <- nycflights %>%
  mutate(avg_speed = 60*(distance / air_time))
glimpse(nycflights)

Exercise 8

ggplot(data = nycflights, aes(x = distance, y = avg_speed)) + geom_point()

Exercise 9

nycflights_3carriers <- nycflights %>%
  filter(carrier == "AA" | carrier == "DL" | carrier == "UA")
ggplot(data = nycflights_3carriers, aes(x = dep_delay, y = arr_delay, color= carrier)) + geom_point()