Expand on docs/example for cases with non-equal-width bins in stat_bin()

[mattansb]

This PR addresses the points brought up in #5895:

• The default behavior of stat_bin() of mapping counts to height instead of area is suitable for most common applications.
• This is because most common applications use equal-width bins.
• When non-equal-width bins are used, this behavior produces histograms that are hard to interpret and violate the proportional ink principle.
• Therefore, I suggested adding to the docs/examples something that discusses this / shows how to do it properly.

Which is what I did

The Changes

1. Slightly expanded the Computed variables bullet for width.

Previously was:

• after_stat(width)
  widths of bins.

Now is:

• after_stat(width)
  widths of bins. Use with after_stat(count / width) to obtain bars with areas representing counts (e.g., with non-equal-width bins). See example.

2. Added an example

# When using the non-equal-width bins, we need to set the area of the bars to
# represent the counts (not the height).
# Here we're using 10 equi-probable bins:
price_bins <- quantile(diamonds$price, probs = seq(0, 1, length = 11))

ggplot(diamonds, aes(price)) +
  geom_histogram(breaks = price_bins, color = "black") # wrong (height = count)

ggplot(diamonds, aes(price, after_stat(count / width))) +
  geom_histogram(breaks = price_bins, color = "black") # area = count

^{Created on 2024-10-21 with reprex v2.1.1}