Wprowadzenie do środowiska R - grafika z ggplot2

¹ Zakład Bioinformatyki, Instytut Informatyki, Uniwersytet w Białymstoku

^✉ Correspondence: Jarosław Kotowicz <j.kotowicz@uwb.edu.pl>

1 Książki i inne rzeczy

1. R for Data Science
2. ggplot2: Elegant Graphics for Data Analysis
3. Colors in R

2 Praca ggplot2

2.1 Czyścimy środowisko

rm(list=ls())

3 R for Data Science (rozdział 28)

library(tidyverse)

Rysunki w oparciu o kody z książki R for Data Science.

3.1 Wykonywanie map (prostych)

library(maps)

3.1.1 Rozciągnięcie mapy i zapobieganie rozciągnięciu

nz <- map_data("nz")
ggplot(nz, aes(long, lat, group = group)) +
  geom_polygon(fill = "white", colour = "black")

ggplot(nz, aes(long, lat, group = group)) +
  geom_polygon(fill = "white", colour = "black") +
  coord_quickmap()

3.1.2 Mapa świata

world <- map_data("world")
ggplot(world, aes(long, lat, group = group)) +
  geom_polygon(fill = "white", colour = "black") +
  coord_quickmap()

3.2 Trochę wykresów ze se statystyki

bar <- ggplot(data = diamonds) + 
  geom_bar(
    mapping = aes(x = cut, fill = cut), 
    show.legend = FALSE,
    width = 1
  ) + 
  theme(aspect.ratio = 1) +
  labs(x = NULL, y = NULL)

3.2.1 Słupkowe

bar

bar + coord_flip()

3.2.2 Kołowe

bar + coord_polar()

3.3 Estetyka wykresów (co dorobić do wykresu, aby był czytelny)

3.3.1 Tytuł

ggplot(mpg, aes(displ, hwy)) +
  geom_point(aes(color = class)) +
  geom_smooth(se = FALSE) +
  labs(title = "Fuel efficiency generally decreases with engine size")

3.3.2 Podtytuł i podpis

ggplot(mpg, aes(displ, hwy)) +
  geom_point(aes(color = class)) +
  geom_smooth(se = FALSE) +
  labs(
    title = "Fuel efficiency generally decreases with engine size",
    subtitle = "Two seaters (sports cars) are an exception because of their light weight",
    caption = "Data from fueleconomy.gov"
  )

3.3.3 Osie

ggplot(mpg, aes(displ, hwy)) +
  geom_point(aes(colour = class)) +
  geom_smooth(se = FALSE) +
  labs(
    title = "Fuel efficiency generally decreases with engine size",
    subtitle = "Two seaters (sports cars) are an exception because of their light weight",
    caption = "Data from fueleconomy.gov",
    x = "Engine displacement (L)",
    y = "Highway fuel economy (mpg)",
    colour = "Car type"
  )

3.3.4 Jak używać symboli i wzorów np. w nazwach osi

set.seed(2020)
df <- tibble(
  x = runif(10),
  y = runif(10)
)

ggplot(df, aes(x, y)) +
  geom_point() +
  labs(
    x = quote(sum(x[i] ^ 2, i == 1, n)),
    y = quote(alpha + beta + frac(delta, theta))
  )

3.3.5 Umieszczanie textu na rysunku

best_in_class <- mpg %>%
  group_by(class) %>%
  filter(row_number(desc(hwy)) == 1)
ggplot(mpg, aes(displ, hwy)) +
  geom_point(aes(colour = class)) +
  geom_text(aes(label = model), data = best_in_class)

3.3.5.1 Lepszy sposób umieszczania textu na rysunku

ggplot(mpg, aes(displ, hwy)) +
  geom_point(aes(colour = class)) +
  geom_label(aes(label = model), data = best_in_class, nudge_y = 2, alpha = 0.5)

3.3.5.2 Pakiet ggrepel i jego warstwa geom_label_repel - jeszcze lepszy sposób umieszczania textu na rysunku

ggplot(mpg, aes(displ, hwy)) +
  geom_point(aes(colour = class), position = "jitter") +
  geom_point(size = 3, shape = 1, data = best_in_class) +
  ggrepel::geom_label_repel(aes(label = model), data = best_in_class)

3.3.5.3 Text na rysunku zamiast legendy do niego plus funkcja theme

class_avg <- mpg %>%
  group_by(class) %>%
  summarise(
    displ = median(displ),
    hwy = median(hwy)
  )
ggplot(mpg, aes(displ, hwy, colour = class)) +
  ggrepel::geom_label_repel(aes(label = class),
                            data = class_avg,
                            size = 6,
                            label.size = 0,
                            segment.color = NA
  ) +
  geom_point() +
  theme(legend.position = "none")

3.3.5.4 Umieszczanie dłuższych napisów

label <- mpg %>%
  summarise(
    displ = max(displ),
    hwy = max(hwy),
    label = "Increasing engine size is \nrelated to decreasing fuel economy."
  )
ggplot(mpg, aes(displ, hwy)) +
  geom_point() +
  geom_text(aes(label = label), data = label, vjust = "top", hjust = "right")

label <- tibble(
  displ = Inf,
  hwy = Inf,
  label = "Increasing engine size is \nrelated to decreasing fuel economy."
)
ggplot(mpg, aes(displ, hwy)) +
  geom_point() +
  geom_text(aes(label = label), data = label, vjust = "top", hjust = "right")

3.3.6 Ustawianie parametrów osi

ggplot(mpg, aes(displ, hwy)) +
  geom_point()

ggplot(mpg, aes(displ, hwy)) +
  geom_point() +
  scale_y_continuous(breaks = seq(15, 40, by = 5))

ggplot(mpg, aes(displ, hwy)) +
  geom_point() +
  scale_x_continuous(labels = NULL) +
  scale_y_continuous(labels = NULL)

3.3.6.1 oraz geometria odcinków geom_segment

library(DT)

presidential %>% datatable

presidential %>%
  mutate(id = 33 + row_number()) %>%
  ggplot(aes(start, id)) +
  geom_point() +
  geom_segment(aes(xend = end, yend = id)) +
  scale_x_date(NULL, breaks = presidential$start, date_labels = "'%y")

base <- ggplot(mpg, aes(displ, hwy)) +
  geom_point(aes(colour = class))

3.3.7 Gdzie chcemy legendę?

base + theme(legend.position = "left")

base + theme(legend.position = "top")

base + theme(legend.position = "bottom")

base + theme(legend.position = "right") # the default

3.3.7.1 Funcja guides do pracy z legendą

ggplot(mpg, aes(displ, hwy)) +
  geom_point(aes(colour = class)) +
  geom_smooth(se = FALSE) +
  theme(legend.position = "bottom") +
  guides(colour = guide_legend(nrow = 1, override.aes = list(size = 4)))

ggplot(mpg, aes(displ, hwy)) +
  geom_point(aes(colour = class)) +
  geom_smooth(se = FALSE) +
  theme(legend.position = "bottom") +
  guides(colour = guide_legend(nrow = 1))

3.3.8 Geometria geom_bind2

ggplot(diamonds, aes(carat, price)) +
  geom_bin2d()

ggplot(diamonds, aes(log10(carat), log10(price))) +
  geom_bin2d()

3.3.8.1 wraz ze skalowaniem logarytmicznym osi

ggplot(diamonds, aes(carat, price)) +
  geom_bin2d() + 
  scale_x_log10() + 
  scale_y_log10()

3.3.9 Zmiana wybieranych kolorów do mapowania zmiennych czynnikowych

ggplot(mpg, aes(displ, hwy)) +
  geom_point(aes(color = drv))

library(RColorBrewer)

display.brewer.all()

Proszę zobaczyć stronę z lepszym obrazowaniem kolorów z pakietu RColorBrewer

ggplot(mpg, aes(displ, hwy)) +
  geom_point(aes(color = drv)) +
  scale_colour_brewer(palette = "Set2")

presidential %>%
  mutate(id = 33 + row_number()) %>%
  ggplot(aes(start, id, colour = party)) +
  geom_point() +
  geom_segment(aes(xend = end, yend = id)) +
  scale_colour_manual(values = c(Republican = "red", Democratic = "blue"))

set.seed(2020)
df <- tibble(
  x = rnorm(10000),
  y = rnorm(10000)
)

3.3.10 Układ współrzędnych (nierówne skale na osich i co z tym zrobić)

ggplot(df, aes(x, y)) +
  geom_hex()

ggplot(df, aes(x, y)) +
  geom_hex() +
  coord_fixed()

3.3.10.1 Trochę poprawy kolorów wypełnienia z pakietem viridis

ggplot(df, aes(x, y)) +
  geom_hex() +
  viridis::scale_fill_viridis() +
  coord_fixed()

3.3.11 Zoom na rysunek, czyli wyświetlamy fragment rysunku

ggplot(mpg, mapping = aes(displ, hwy)) +
  geom_point(aes(color = class)) +
  geom_smooth() +
  coord_cartesian(xlim = c(5, 7), ylim = c(10, 30))

3.3.11.0.1 A to robi troszeczkę coś innego

mpg %>%
  filter(displ >= 5, displ <= 7, hwy >= 10, hwy <= 30) %>%
  ggplot(aes(displ, hwy)) +
  geom_point(aes(color = class)) +
  geom_smooth()

3.3.12 Zoom na dane, czyli ograniczenie wyświetlanych danych (filtrowanie na różne sposoby)

suv <- mpg %>% filter(class == "suv")
compact <- mpg %>% filter(class == "compact")

ggplot(suv, aes(displ, hwy, colour = drv)) +
  geom_point()

ggplot(compact, aes(displ, hwy, colour = drv)) +
  geom_point()

x_scale <- scale_x_continuous(limits = range(mpg$displ))
y_scale <- scale_y_continuous(limits = range(mpg$hwy))
col_scale <- scale_colour_discrete(limits = unique(mpg$drv))

ggplot(suv, aes(displ, hwy, colour = drv)) +
  geom_point() +
  x_scale +
  y_scale +
  col_scale

ggplot(compact, aes(displ, hwy, colour = drv)) +
  geom_point() +
  x_scale +
  y_scale +
  col_scale

3.3.13 Różne predefiniowane sposoby wyświetlania rysunków, czyli theme_XX

ggplot(mpg, aes(displ, hwy)) +
  geom_point(aes(color = class)) +
  geom_smooth(se = FALSE) +
  theme_bw()

ggplot(mpg, aes(displ, hwy)) +
  geom_point(aes(colour = class)) +
  geom_smooth(se = FALSE) +
  labs(
    title = "Fuel efficiency generally decreases with engine size",
    subtitle = "Two seaters (sports cars) are an exception because of their light weight",
    caption = "Data from fueleconomy.gov",
    x = "Engine displacement (L)",
    y = "Highway fuel economy (mpg)",
    colour = "Car type"
  )

3.3.14 Zapisywanie rysunku do zmiennych globalnych

rysunek <- ggplot(mpg, aes(displ, hwy)) +
  geom_point(aes(colour = class)) +
  geom_smooth(se = FALSE) +
  labs(
    title = "Fuel efficiency generally decreases with engine size",
    subtitle = "Two seaters (sports cars) are an exception because of their light weight",
    caption = "Data from fueleconomy.gov",
    x = "Engine displacement (L)",
    y = "Highway fuel economy (mpg)",
    colour = "Car type"
  )

4 Jakich blibliotek możemy jeszcze użyć

1. Predefiniowane tematy

• ggthemes
• hrbrthemes

2. Pomoc w modyfikowaniu parametr ów rysunku

• ggThemeAssist i ggThemeAssistGadget

3. Dla map

• ggmaps

itd.

5 Praca domowa z dnia 17 marca 2020r. (do wykładu)

Wypisz do 20 biblioteki ze strony projekty R, które rozszerzają działania pakietu ggplot2.