downloads

ggalt : Extra Coordinate Systems, Geoms, Statistical Transformations, Scales & Fonts for ‘ggplot2’

A compendium of ‘geoms’, ‘coords’, ‘stats’, scales and fonts for ‘ggplot2’, including splines, 1d and 2d densities, univariate average shifted histograms, a new map coordinate system based on the ‘PROJ.4’-library and the ‘StateFace’ open source font ‘ProPublica’.

The following functions are implemented:

geom_ubar : Uniform width bar charts
geom_horizon : Horizon charts (modified from https://github.com/AtherEnergy/ggTimeSeries)
coord_proj : Like coord_map, only better (prbly shld use this with geom_cartogram as geom_map’s new defaults are ugh)
geom_xspline : Connect control points/observations with an X-spline
stat_xspline : Connect control points/observations with an X-spline
geom_bkde : Display a smooth density estimate (uses KernSmooth::bkde)
geom_stateface: Use ProPublica’s StateFace font in ggplot2 plots
geom_bkde2d : Contours from a 2d density estimate. (uses KernSmooth::bkde2D)
stat_bkde : Display a smooth density estimate (uses KernSmooth::bkde)
stat_bkde2d : Contours from a 2d density estimate. (uses KernSmooth::bkde2D)
stat_ash : Compute and display a univariate averaged shifted histogram (polynomial kernel) (uses ash::ash1/ash::bin1)
geom_encircle: Automatically enclose points in a polygon
byte_format: + helpers. e.g. turn 10000 into 10 Kb
geom_lollipop(): Dead easy lollipops (horizontal or vertical)
geom_dumbbell() : Dead easy dumbbell plots
stat_stepribbon() : Step ribbons
annotation_ticks() : Add minor ticks to identity, exp(1) and exp(10) axis scales independently of each other.
geom_spikelines() : Instead of geom_vline and geom_hline a pair of segments that originate from same c(x,y) are drawn to the respective axes.
plotly integration for a few of the ^^ geoms

Installation

# you'll want to see the vignettes, trust me
install.packages("ggplot2")
install.packages("ggalt")
# OR: devtools::install_github("hrbrmstr/ggalt")

Usage

library(ggplot2)
library(gridExtra)
library(ggalt)

# current verison
packageVersion("ggalt")
## [1] '0.6.1'

set.seed(1492)
dat <- data.frame(x=c(1:10, 1:10, 1:10),
                  y=c(sample(15:30, 10), 2*sample(15:30, 10), 3*sample(15:30, 10)),
                  group=factor(c(rep(1, 10), rep(2, 10), rep(3, 10)))
)

Horzon Chart

Example carved from: https://github.com/halhen/viz-pub/blob/master/sports-time-of-day/2_gen_chart.R

library(hrbrthemes)
library(ggalt)
library(tidyverse)

sports <- read_tsv("https://github.com/halhen/viz-pub/raw/master/sports-time-of-day/activity.tsv")

sports %>%
  group_by(activity) %>% 
  filter(max(p) > 3e-04, 
         !grepl('n\\.e\\.c', activity)) %>% 
  arrange(time) %>%
  mutate(p_peak = p / max(p), 
         p_smooth = (lag(p_peak) + p_peak + lead(p_peak)) / 3,
         p_smooth = coalesce(p_smooth, p_peak)) %>% 
  ungroup() %>%
  do({ 
    rbind(.,
          filter(., time == 0) %>%
            mutate(time = 24*60))
  }) %>%
  mutate(time = ifelse(time < 3 * 60, time + 24 * 60, time)) %>%
  mutate(activity = reorder(activity, p_peak, FUN=which.max)) %>% 
  arrange(activity) %>%
  mutate(activity.f = reorder(as.character(activity), desc(activity))) -> sports

sports <- mutate(sports, time2 = time/60)

ggplot(sports, aes(time2, p_smooth)) +
  geom_horizon(bandwidth=0.1) +
  facet_grid(activity.f~.) +
  scale_x_continuous(expand=c(0,0), breaks=seq(from = 3, to = 27, by = 3), labels = function(x) {sprintf("%02d:00", as.integer(x %% 24))}) +
  viridis::scale_fill_viridis(name = "Activity relative to peak", discrete=TRUE,
                              labels=scales::percent(seq(0, 1, 0.1)+0.1)) +
  labs(x=NULL, y=NULL, title="Peak time of day for sports and leisure",
       subtitle="Number of participants throughout the day compared to peak popularity.\nNote the morning-and-evening everyday workouts, the midday hobbies,\nand the evenings/late nights out.") +
  theme_ipsum_rc(grid="") +
  theme(panel.spacing.y=unit(-0.05, "lines")) +
  theme(strip.text.y = element_text(hjust=0, angle=360)) +
  theme(axis.text.y=element_blank())

Splines!

ggplot(dat, aes(x, y, group=group, color=group)) +
  geom_point() +
  geom_line()


ggplot(dat, aes(x, y, group=group, color=factor(group))) +
  geom_point() +
  geom_line() +
  geom_smooth(se=FALSE, linetype="dashed", size=0.5)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'


ggplot(dat, aes(x, y, group=group, color=factor(group))) +
  geom_point(color="black") +
  geom_smooth(se=FALSE, linetype="dashed", size=0.5) +
  geom_xspline(size=0.5)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'


ggplot(dat, aes(x, y, group=group, color=factor(group))) +
  geom_point(color="black") +
  geom_smooth(se=FALSE, linetype="dashed", size=0.5) +
  geom_xspline(spline_shape=-0.4, size=0.5)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'


ggplot(dat, aes(x, y, group=group, color=factor(group))) +
  geom_point(color="black") +
  geom_smooth(se=FALSE, linetype="dashed", size=0.5) +
  geom_xspline(spline_shape=0.4, size=0.5)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'


ggplot(dat, aes(x, y, group=group, color=factor(group))) +
  geom_point(color="black") +
  geom_smooth(se=FALSE, linetype="dashed", size=0.5) +
  geom_xspline(spline_shape=1, size=0.5)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'


ggplot(dat, aes(x, y, group=group, color=factor(group))) +
  geom_point(color="black") +
  geom_smooth(se=FALSE, linetype="dashed", size=0.5) +
  geom_xspline(spline_shape=0, size=0.5)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'


ggplot(dat, aes(x, y, group=group, color=factor(group))) +
  geom_point(color="black") +
  geom_smooth(se=FALSE, linetype="dashed", size=0.5) +
  geom_xspline(spline_shape=-1, size=0.5)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

Alternate (better) density plots

# bkde

data(geyser, package="MASS")

ggplot(geyser, aes(x=duration)) + 
  stat_bkde(alpha=1/2)
## Bandwidth not specified. Using '0.14', via KernSmooth::dpik.


ggplot(geyser, aes(x=duration)) +
  geom_bkde(alpha=1/2)
## Bandwidth not specified. Using '0.14', via KernSmooth::dpik.


ggplot(geyser, aes(x=duration)) + 
  stat_bkde(bandwidth=0.25)


ggplot(geyser, aes(x=duration)) +
  geom_bkde(bandwidth=0.25)


set.seed(1492)
dat <- data.frame(cond = factor(rep(c("A","B"), each=200)), 
                   rating = c(rnorm(200),rnorm(200, mean=.8)))

ggplot(dat, aes(x=rating, color=cond)) + geom_bkde(fill="#00000000")
## Bandwidth not specified. Using '0.36', via KernSmooth::dpik.
## Bandwidth not specified. Using '0.31', via KernSmooth::dpik.


ggplot(dat, aes(x=rating, fill=cond)) + geom_bkde(alpha=0.3)
## Bandwidth not specified. Using '0.36', via KernSmooth::dpik.
## Bandwidth not specified. Using '0.31', via KernSmooth::dpik.


# ash

set.seed(1492)
dat <- data.frame(x=rnorm(100))
grid.arrange(ggplot(dat, aes(x)) + stat_ash(),
             ggplot(dat, aes(x)) + stat_bkde(),
             ggplot(dat, aes(x)) + stat_density(),
             nrow=3)
## Estimate nonzero outside interval ab.
## Bandwidth not specified. Using '0.43', via KernSmooth::dpik.


cols <- RColorBrewer::brewer.pal(3, "Dark2")
ggplot(dat, aes(x)) + 
  stat_ash(alpha=1/3, fill=cols[3]) + 
  stat_bkde(alpha=1/3, fill=cols[2]) + 
  stat_density(alpha=1/3, fill=cols[1]) + 
  geom_rug() +
  labs(x=NULL, y="density/estimate") +
  scale_x_continuous(expand=c(0,0)) +
  theme_bw() +
  theme(panel.grid=element_blank()) +
  theme(panel.border=element_blank())
## Estimate nonzero outside interval ab.
## Bandwidth not specified. Using '0.43', via KernSmooth::dpik.

Alternate 2D density plots

m <- ggplot(faithful, aes(x = eruptions, y = waiting)) +
       geom_point() +
       xlim(0.5, 6) +
       ylim(40, 110)

m + ge

Ggalt

Install / Use

README