Code from R for Data Science - Chapter 5

In this notebook we will take a look at some of the examples of ggplot2 from Chapter 5.

library(nycflights13)
library(tidyverse)

flights

Subsetting with filter().

All Janurary 1 days.

filter(flights, month == 1, day == 1)

Save, Save and Print.

jan1 <- filter(flights, month == 1, day == 1)
(dec25 <- filter(flights, month == 12, day == 25))

November and Decembers.

filter(flights, month == 11 | month == 12)

nov_dec <- filter(flights, month %in% c(11, 12))

filter(flights, !(arr_delay > 120 | dep_delay > 120))

filter(flights, arr_delay <= 120, dep_delay <= 120)

Reodering the rows with arrange().

arrange(flights, year, month, day)

arrange(flights, desc(arr_delay))

Subset variables with the select() function.

select(flights, year, month, day)

select(flights, year:day)

select(flights, -(year:day))

rename(flights, tail_num = tailnum)

select(flights, time_hour, air_time, everything())

Add new variables with mutate().

flights_sml <- select(flights, 
  year:day, 
  ends_with("delay"), 
  distance, 
  air_time
)
mutate(flights_sml,
  gain = arr_delay - dep_delay,
  speed = distance / air_time * 60
)

Only save new variables with transmute().

transmute(flights,
  gain = arr_delay - dep_delay,
  hours = air_time / 60,
  gain_per_hour = gain / hours
)

Summarize.

summarise(flights, delay = mean(dep_delay, na.rm = TRUE))

by_day <- group_by(flights, year, month, day)
summarise(by_day, delay = mean(dep_delay, na.rm = TRUE))

Piping.

Original:

by_dest <- group_by(flights, dest)
delay <- summarise(by_dest,
  count = n(),
  dist = mean(distance, na.rm = TRUE),
  delay = mean(arr_delay, na.rm = TRUE)
)
delay <- filter(delay, count > 20, dest != "HNL")
ggplot(data = delay, mapping = aes(x = dist, y = delay)) +
  geom_point(aes(size = count), alpha = 1/3) +
  geom_smooth(se = FALSE)

delays <- flights %>% 
  group_by(dest) %>% 
  summarise(
    count = n(),
    dist = mean(distance, na.rm = TRUE),
    delay = mean(arr_delay, na.rm = TRUE)
  ) %>% 
  filter(count > 20, dest != "HNL")
ggplot(data = delay, mapping = aes(x = dist, y = delay)) +
  geom_point(aes(size = count), alpha = 1/3) +
  geom_smooth(se = FALSE)

Missing data.

flights %>% 
  group_by(year, month, day) %>% 
  summarise(mean = mean(dep_delay))

flights %>% 
  group_by(year, month, day) %>% 
  summarise(mean = mean(dep_delay, na.rm = TRUE))

not_cancelled <- flights %>% 
  filter(!is.na(dep_delay), !is.na(arr_delay))
not_cancelled %>% 
  group_by(year, month, day) %>% 
  summarise(mean = mean(dep_delay))

delays <- not_cancelled %>% 
  group_by(tailnum) %>% 
  summarise(
    delay = mean(arr_delay)
  )
ggplot(data = delays, mapping = aes(x = delay)) + 
  geom_freqpoly(binwidth = 10)

delays <- not_cancelled %>% 
  group_by(tailnum) %>% 
  summarise(
    delay = mean(arr_delay, na.rm = TRUE),
    n = n()
  )
ggplot(data = delays, mapping = aes(x = n, y = delay)) + 
  geom_point(alpha = 1/10)

delays %>% 
  filter(n > 25) %>% 
  ggplot(mapping = aes(x = n, y = delay)) + 
    geom_point(alpha = 1/10)

not_cancelled %>% 
  group_by(year, month, day) %>% 
  summarise(
    avg_delay1 = mean(arr_delay),
    avg_delay2 = mean(arr_delay[arr_delay > 0]) # the average positive delay
  )

not_cancelled %>% 
  group_by(dest) %>% 
  summarise(distance_sd = sd(distance)) %>% 
  arrange(desc(distance_sd))

not_cancelled %>% 
  group_by(year, month, day) %>% 
  summarise(
    first = min(dep_time),
    last = max(dep_time)
  )

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Ctrl+Alt+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.