R ggplot2 geom_histogram 直方图和频数多边形

geom_freqpoly(
  mapping = NULL,
  data = NULL,
  stat = "bin",
  position = "identity",
  ...,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

geom_histogram(
  mapping = NULL,
  data = NULL,
  stat = "bin",
  position = "stack",
  ...,
  binwidth = NULL,
  bins = NULL,
  na.rm = FALSE,
  orientation = NA,
  show.legend = NA,
  inherit.aes = TRUE
)

stat_bin(
  mapping = NULL,
  data = NULL,
  geom = "bar",
  position = "stack",
  ...,
  binwidth = NULL,
  bins = NULL,
  center = NULL,
  boundary = NULL,
  breaks = NULL,
  closed = c("right", "left"),
  pad = FALSE,
  na.rm = FALSE,
  orientation = NA,
  show.legend = NA,
  inherit.aes = TRUE
)

stat_count() ，计算每个 x 位置的案例数，不进行分箱。它适用于离散和连续 x 数据，而 stat_bin() 仅适用于连续 x 数据。

ggplot(diamonds, aes(carat)) +
  geom_histogram()
#> `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(diamonds, aes(carat)) +
  geom_histogram(binwidth = 0.01)

ggplot(diamonds, aes(carat)) +
  geom_histogram(bins = 200)

# Map values to y to flip the orientation
ggplot(diamonds, aes(y = carat)) +
  geom_histogram()
#> `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.


# For histograms with tick marks between each bin, use `geom_bar()` with
# `scale_x_binned()`.
ggplot(diamonds, aes(carat)) +
  geom_bar() +
  scale_x_binned()


# Rather than stacking histograms, it's easier to compare frequency
# polygons
ggplot(diamonds, aes(price, fill = cut)) +
  geom_histogram(binwidth = 500)

ggplot(diamonds, aes(price, colour = cut)) +
  geom_freqpoly(binwidth = 500)


# To make it easier to compare distributions with very different counts,
# put density on the y axis instead of the default count
ggplot(diamonds, aes(price, after_stat(density), colour = cut)) +
  geom_freqpoly(binwidth = 500)


if (require("ggplot2movies")) {
# Often we don't want the height of the bar to represent the
# count of observations, but the sum of some other variable.
# For example, the following plot shows the number of movies
# in each rating.
m <- ggplot(movies, aes(rating))
m + geom_histogram(binwidth = 0.1)

# If, however, we want to see the number of votes cast in each
# category, we need to weight by the votes variable
m +
  geom_histogram(aes(weight = votes), binwidth = 0.1) +
  ylab("votes")

# For transformed scales, binwidth applies to the transformed data.
# The bins have constant width on the transformed scale.
m +
 geom_histogram() +
 scale_x_log10()
m +
  geom_histogram(binwidth = 0.05) +
  scale_x_log10()

# For transformed coordinate systems, the binwidth applies to the
# raw data. The bins have constant width on the original scale.

# Using log scales does not work here, because the first
# bar is anchored at zero, and so when transformed becomes negative
# infinity. This is not a problem when transforming the scales, because
# no observations have 0 ratings.
m +
  geom_histogram(boundary = 0) +
  coord_trans(x = "log10")
# Use boundary = 0, to make sure we don't take sqrt of negative values
m +
  geom_histogram(boundary = 0) +
  coord_trans(x = "sqrt")

# You can also transform the y axis.  Remember that the base of the bars
# has value 0, so log transformations are not appropriate
m <- ggplot(movies, aes(x = rating))
m +
  geom_histogram(binwidth = 0.5) +
  scale_y_sqrt()
}


# You can specify a function for calculating binwidth, which is
# particularly useful when faceting along variables with
# different ranges because the function will be called once per facet
ggplot(economics_long, aes(value)) +
  facet_wrap(~variable, scales = 'free_x') +
  geom_histogram(binwidth = function(x) 2 * IQR(x) / (length(x)^(1/3)))