统计绘图 | 既能统计分析又能可视化绘制的技能

plot2 <- ggstatsplot::ggbetweenstats(
  data = datasets::morley,
  x = Expt,
  y = Speed,
  type = "nonparametric",
  plot.type = "box",
  title = "ggbetweenstats example02",
  xlab = "The experiment number",
  ylab = "Speed-of-light measurement",
  caption = "Visualization by DataCharm",
  pairwise.comparisons = TRUE,
  p.adjust.method = "fdr",
  outlier.tagging = TRUE,
  outlier.label = Run,
  ggtheme = hrbrthemes::theme_ipsum(base_family = "Roboto Condensed"),
  ggstatsplot.layer = FALSE
)

# for reproducibility and data
set.seed(123)
library(WRS2)

# plot
plot3 <- ggwithinstats(
  data = WineTasting,
  x = Wine,
  y = Taste,
  title = "Wine tasting",
  caption = "Data source: `WRS2` R package",
  ggtheme = hrbrthemes::theme_ipsum(base_family = "Roboto Condensed"),
  ggstatsplot.layer = FALSE
)

# for reproducibility
set.seed(123)

# plot
plot4 <- gghistostats(
  data = ggplot2::msleep, # dataframe from which variable is to be taken
  x = awake, # numeric variable whose distribution is of interest
  title = "Amount of time spent awake", # title for the plot
  caption = substitute(paste(italic("Source: "), "Mammalian sleep data set")),
  test.value = 12, # default value is 0
  binwidth = 1, # binwidth value (experiment)
  ggtheme = hrbrthemes::theme_ipsum(base_family = "Roboto Condensed"), # choosing a different theme
  ggstatsplot.layer = FALSE # turn off ggstatsplot theme layer
)

# for reproducibility
set.seed(123)

# plot
plot5 <- grouped_gghistostats(
  data = dplyr::filter(
    .data = movies_long,
    genre %in% c("Action", "Action Comedy", "Action Drama", "Comedy")
  ),
  x = budget,
  test.value = 50,
  type = "nonparametric",
  xlab = "Movies budget (in million US$)",
  grouping.var = genre, # grouping variable
  normal.curve = TRUE, # superimpose a normal distribution curve
  normal.curve.args = list(color = "red", size = 1),
  title.prefix = "Movie genre",
  ggtheme = hrbrthemes::theme_ipsum(base_family = "Roboto Condensed"),
  # modify the defaults from `ggstatsplot` for each plot
  ggplot.component = ggplot2::labs(caption = "Source: IMDB.com"),
  plotgrid.args = list(nrow = 2),
  annotation.args = list(title = "Movies budgets for different genres")
)

plot6 <- ggscatterstats(
  data = ggplot2::msleep,
  x = sleep_rem,
  y = awake,
  xlab = "REM sleep (in hours)",
  ylab = "Amount of time spent awake (in hours)",
  title = "Understanding mammalian sleep",
  ggtheme = hrbrthemes::theme_ipsum(base_family = "Roboto Condensed")
)

# for reproducibility
set.seed(123)

# as a default this function outputs a correlation matrix plot
plot7 <- ggcorrmat(
  data = ggplot2::msleep,
  colors = c("#B2182B", "white", "#4D4D4D"),
  title = "Correlalogram for mammals sleep dataset",
  subtitle = "sleep units: hours; weight units: kilograms",
  ggtheme = hrbrthemes::theme_ipsum(base_family = "Roboto Condensed")
)

# for reproducibility
set.seed(123)
library(ggplot2)

# plot
plot8 <- ggbarstats(
  data = movies_long,
  x = mpaa,
  y = genre,
  title = "MPAA Ratings by Genre",
  xlab = "movie genre",
  legend.title = "MPAA rating",
  ggtheme = hrbrthemes::theme_ipsum(base_family = "Roboto Condensed"),
  ggplot.component = list(ggplot2::scale_x_discrete(guide = ggplot2::guide_axis(n.dodge = 2))),
  palette = "Set2"
)