Preliminaries

library(ggplot2)
library(ggpmisc)
library(xts)
## Loading required package: zoo
## 
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric
library(lubridate)

try_data_frame()

Time series

Several different formats for storing time series data are used in R. Here we use in the examples objects of class ts but several other classes are supported as try.xts() is used internally. The first example is a quarterly series.

class(austres)
## [1] "ts"
austres.df <- try_data_frame(austres)
class(austres.df)
## [1] "data.frame"
lapply(austres.df, "class")
## $time
## [1] "POSIXct" "POSIXt" 
## 
## $V.austres
## [1] "numeric"
head(austres.df, 4)
##         time V.austres
## 1 1971-04-01   13067.3
## 2 1971-07-01   13130.5
## 3 1971-10-01   13198.4
## 4 1972-01-01   13254.2

The next chunk demonstrates that numeric times are expressed as decimal years in the returned data frame.

austres.df <- try_data_frame(austres, as.numeric = TRUE)
lapply(austres.df, "class")
## $time
## [1] "numeric"
## 
## $V.austres
## [1] "numeric"
head(austres.df, 4)
##       time V.austres
## 1 1971.247   13067.3
## 2 1971.496   13130.5
## 3 1971.748   13198.4
## 4 1972.000   13254.2

This second example is for a series of yearly values.

class(lynx)
## [1] "ts"
lynx.df <- try_data_frame(lynx)
class(lynx.df)
## [1] "data.frame"
lapply(lynx.df, "class")
## $time
## [1] "POSIXct" "POSIXt" 
## 
## $V.lynx
## [1] "numeric"
head(lynx.df, 3)
##                  time V.lynx
## 1 1821-01-01 00:00:01    269
## 2 1822-01-01 00:00:01    321
## 3 1823-01-01 00:00:01    585

Above there is a small rounding error of 1 s for these old dates. We can correct this by rounding to year.

lynx.df <- try_data_frame(lynx, "year")
head(lynx.df, 3)
##         time V.lynx
## 1 1821-01-01    269
## 2 1822-01-01    321
## 3 1823-01-01    585

In addition we can convert the POSIXct values into numeric values in calendar years plus a decimal fraction.

lynx_n.df <- try_data_frame(lynx, "year", as.numeric = TRUE)
lapply(lynx_n.df, "class")
## $time
## [1] "numeric"
## 
## $V.lynx
## [1] "numeric"
head(lynx_n.df, 3)
##   time V.lynx
## 1 1821    269
## 2 1822    321
## 3 1823    585

Other classes

try_data_frame() attempts to handle gracefully objects that are not time series.

try_data_frame(1:5)
##   x
## 1 1
## 2 2
## 3 3
## 4 4
## 5 5
try_data_frame(letters[1:5])
##   x
## 1 a
## 2 b
## 3 c
## 4 d
## 5 e
try_data_frame(factor(letters[1:5]))
##   x
## 1 a
## 2 b
## 3 c
## 4 d
## 5 e
try_data_frame(list(x = rep(1,5), y = 1:5))
##   x y
## 1 1 1
## 2 1 2
## 3 1 3
## 4 1 4
## 5 1 5
try_data_frame(data.frame(x = rep(1,5), y = 1:5))
##   x y
## 1 1 1
## 2 1 2
## 3 1 3
## 4 1 4
## 5 1 5
try_data_frame(matrix(1:10, ncol = 2))
##   V1 V2
## 1  1  6
## 2  2  7
## 3  3  8
## 4  4  9
## 5  5 10

stat_peaks() and stat_valleys()

Using POSIXct for time and the default formatting of labels.

ggplot(lynx.df, aes(time, V.lynx)) + geom_line() + 
  stat_peaks(colour = "red") +
  stat_peaks(geom = "text", colour = "red", vjust = -0.5) +
  ylim(-100, 7300)

Using numeric values for time and the default formatting of labels.

ggplot(lynx_n.df, aes(time, V.lynx)) + geom_line() + 
  stat_peaks(colour = "red") +
  stat_peaks(geom = "text", colour = "red", vjust = -0.5) +
  ylim(-100, 7300)

Using POSIXct for time but supplying a format string. In addition marking both peaks and valleys.

ggplot(lynx.df, aes(time, V.lynx)) + geom_line() + 
  stat_peaks(colour = "red") +
  stat_peaks(geom = "text", colour = "red", vjust = -0.5, x.label.fmt = "%Y") +
  stat_valleys(colour = "blue") +
  stat_valleys(geom = "text", colour = "blue", vjust = 1.5, x.label.fmt = "%Y") +
  ylim(-100, 7300)

Using numeric for time but supplying a format string. In addition marking both peaks and valleys.

ggplot(lynx_n.df, aes(time, V.lynx)) + geom_line() + 
  stat_peaks(colour = "red") +
  stat_peaks(geom = "text", colour = "red", vjust = -0.5, x.label.fmt = "%4.0f") +
  stat_valleys(colour = "blue") +
  stat_valleys(geom = "text", colour = "blue", vjust = 1.5, x.label.fmt = "%4.0f") +
  ylim(-100, 7300)

Rotating the labels.

ggplot(lynx.df, aes(time, V.lynx)) + geom_line() + 
  stat_peaks(colour = "red") +
  stat_peaks(geom = "text", colour = "red", angle = 66,
             hjust = -0.1, x.label.fmt = "%Y") +
  ylim(NA, 7800)

Using geom_rug for the peaks and valleys.

ggplot(lynx.df, aes(time, V.lynx)) + geom_line() + 
  stat_peaks(colour = "red") +
  stat_peaks(geom = "rug", colour = "red") +
  stat_valleys(colour = "blue") +
  stat_valleys(geom = "rug", colour = "blue")

stat_poly_eq()

We generate some artificial data.

set.seed(4321)
# generate artificial data
x <- 1:100
y <- (x + x^2 + x^3) + rnorm(length(x), mean = 0, sd = mean(x^3) / 4)
my.data <- data.frame(x, 
                      y, 
                      group = c("A", "B"), 
                      y2 = y * c(0.5,2),
                      block = c("a", "a", "b", "b"))

First one example using defaults.

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(formula = formula, parse = TRUE)

stat_poly_eq() makes available three different labels in the returned data frame. One of these is used by default, but aes() can be used to select a different one.

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..adj.rr.label..), formula = formula, 
               parse = TRUE)

BIC and AIC labels are also returned.

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..AIC.label..), 
               formula = formula, 
               parse = TRUE)

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..eq.label..), formula = formula, 
               parse = TRUE)

Within aes() it is possible to compute new labels based on those returned plus “arbitrary” text. The supplied labels are meant to be parsed into expressions, so any text added should be valid for a string that will be parsed.

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label =  paste(..eq.label.., ..adj.rr.label.., sep = "~~~~")),
               formula = formula, parse = TRUE)

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = paste("atop(", ..AIC.label.., ",", ..BIC.label.., ")", sep = "")), 
               formula = formula, 
               parse = TRUE)

Two examples of removing and changing the lhs and/or rhs of the equation.

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..eq.label..),
               eq.with.lhs = FALSE,
               formula = formula, parse = TRUE)

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..eq.label..),
               eq.with.lhs = "italic(hat(y))~`=`~",
               formula = formula, parse = TRUE)

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  labs(x = expression(italic(z)), y = expression(italic(h)) ) + 
  stat_poly_eq(aes(label = ..eq.label..),
               eq.with.lhs = "italic(h)~`=`~",
               eq.x.rhs = "~italic(z)",
               formula = formula, parse = TRUE)

As any valid R expression can be used, Greek letters are also supported, as well as the inclusion in the label of variable transformations used in the model formula.

formula <- y ~ poly(x, 2, raw = TRUE)
ggplot(my.data, aes(x, log10(y + 1e6))) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..eq.label..),
               eq.with.lhs = "plain(log)[10](italic(y)+10^6)~`=`~",
               formula = formula, parse = TRUE)

A couple of additional examples of polynomials of different orders, and specified in different ways.

Higher order polynomial.

formula <- y ~ poly(x, 5, raw = TRUE)
ggplot(my.data, aes(x, y)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..eq.label..), formula = formula, parse = TRUE)

Intercept forced to zero.

formula <- y ~ x + I(x^2) + I(x^3) - 1
ggplot(my.data, aes(x, y)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..eq.label..), formula = formula, 
               parse = TRUE)

We give below several examples to demonstrate how other components of the ggplot object affect the behaviour of this statistic.

Facets work as expected either with fixed or free scales. Although bellow we had to adjust the size of the font used for the equation. In addition to we manually position the equation label by supplying coordinates.

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y2)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..eq.label..), size = rel(3),
               formula = formula, parse = TRUE,
               label.x = 0, label.y = 2e6) +
  facet_wrap(~group)

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y2)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..eq.label..), size = rel(3),
               formula = formula, parse = TRUE) +
  facet_wrap(~group, scales = "free_y")

Grouping, in this example using the colour aesthetic also works as expected. We can use justification and supply an absolute location for the equation.

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y2, colour = group)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..eq.label..),
               formula = formula, parse = TRUE,
               label.x = 0, label.y = c(1.8e6, 2e6)) +
  theme_bw()

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y2, colour = group)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..eq.label..),
               formula = formula, parse = TRUE,
               label.x = 0, label.y = 2e6,
               vjust = c(1.2, 0)) +
  theme_bw()

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y2, colour = group, fill = block)) +
  geom_point(shape = 21, size = rel(3)) +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..rr.label..), size = rel(3),
               geom = "label", alpha = 0.2,
               formula = formula, parse = TRUE,
               label.x = 0, label.y = c(5e5, 5e5, 2e6, 2e6),
               vjust = c(1.2,0,1.2,0)) +
  facet_wrap(~group, scales = "free_y") +
  theme_bw()

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y2, fill = block)) +
  geom_point(shape = 21, size = rel(3)) +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..rr.label..), size = rel(3),
               geom = "label", alpha = 0.33,
               formula = formula, parse = TRUE,
               label.x = 0,
               vjust = c(1.2,0,1.2,0)) +
  facet_wrap(~group, scales = "free_y") +
  theme_bw()

Debugging ggplots

These stats are very simple and print a summary of their data input to the console. In addition they also return a data frame containing labels suitable for plotting as with geom “text” or geom “label”. However, starting from version 0.2.7 of the package the default geom is “null”. The values are listed to the console at the time when the ggplot object is printed.

As shown here, no other geom or stat is required, however in the remaining examples we include geom_point() to make the data on the plot visible.

ggplot(my.data, aes(x, y)) + stat_debug_group()
## [1] "Input 'data' to 'compute_group()':"
## Source: local data frame [100 x 4]
## 
##        x          y PANEL group
##    (dbl)      (dbl) (int) (int)
## 1      1 -27205.450     1    -1
## 2      2 -14242.651     1    -1
## 3      3  45790.918     1    -1
## 4      4  53731.420     1    -1
## 5      5  -8028.578     1    -1
## 6      6 102863.943     1    -1
## 7      7 -18547.282     1    -1
## 8      8  13080.521     1    -1
## 9      9  79924.325     1    -1
## 10    10 -44711.499     1    -1
## ..   ...        ...   ...   ...

In the absence of facets or groups we get just get the summary from one data frame.

ggplot(my.data, aes(x, y)) + geom_point() + stat_debug_group()
## [1] "Input 'data' to 'compute_group()':"
## Source: local data frame [100 x 4]
## 
##        x          y PANEL group
##    (dbl)      (dbl) (int) (int)
## 1      1 -27205.450     1    -1
## 2      2 -14242.651     1    -1
## 3      3  45790.918     1    -1
## 4      4  53731.420     1    -1
## 5      5  -8028.578     1    -1
## 6      6 102863.943     1    -1
## 7      7 -18547.282     1    -1
## 8      8  13080.521     1    -1
## 9      9  79924.325     1    -1
## 10    10 -44711.499     1    -1
## ..   ...        ...   ...   ...

ggplot(my.data, aes(x, y)) + geom_point() + stat_debug_panel()
## [1] "Input 'data' to 'compute_panel()':"
## Source: local data frame [100 x 4]
## 
##        x          y PANEL group
##    (dbl)      (dbl) (int) (int)
## 1      1 -27205.450     1    -1
## 2      2 -14242.651     1    -1
## 3      3  45790.918     1    -1
## 4      4  53731.420     1    -1
## 5      5  -8028.578     1    -1
## 6      6 102863.943     1    -1
## 7      7 -18547.282     1    -1
## 8      8  13080.521     1    -1
## 9      9  79924.325     1    -1
## 10    10 -44711.499     1    -1
## ..   ...        ...   ...   ...

In the case of grouping then one data frame is summarized for each group in the ggplot object.

ggplot(my.data, aes(x, y, colour = group)) + geom_point() + 
  stat_debug_group()
## [1] "Input 'data' to 'compute_group()':"
## Source: local data frame [50 x 5]
## 
##        x          y colour PANEL group
##    (dbl)      (dbl) (fctr) (int) (int)
## 1      1 -27205.450      A     1     1
## 2      3  45790.918      A     1     1
## 3      5  -8028.578      A     1     1
## 4      7 -18547.282      A     1     1
## 5      9  79924.325      A     1     1
## 6     11  -2823.736      A     1     1
## 7     13 -78016.690      A     1     1
## 8     15 -74281.234      A     1     1
## 9     17   9903.674      A     1     1
## 10    19 -94022.623      A     1     1
## ..   ...        ...    ...   ...   ...
## [1] "Input 'data' to 'compute_group()':"
## Source: local data frame [50 x 5]
## 
##        x         y colour PANEL group
##    (dbl)     (dbl) (fctr) (int) (int)
## 1      2 -14242.65      B     1     2
## 2      4  53731.42      B     1     2
## 3      6 102863.94      B     1     2
## 4      8  13080.52      B     1     2
## 5     10 -44711.50      B     1     2
## 6     12  23839.55      B     1     2
## 7     14  75601.96      B     1     2
## 8     16 104676.72      B     1     2
## 9     18 -68746.93      B     1     2
## 10    20 -39230.19      B     1     2
## ..   ...       ...    ...   ...   ...

Without facets, we still have only one panel.

ggplot(my.data, aes(x, y, colour = group)) + geom_point() + 
  stat_debug_panel()
## [1] "Input 'data' to 'compute_panel()':"
## Source: local data frame [100 x 5]
## 
##        x          y colour PANEL group
##    (dbl)      (dbl) (fctr) (int) (int)
## 1      1 -27205.450      A     1     1
## 2      2 -14242.651      B     1     2
## 3      3  45790.918      A     1     1
## 4      4  53731.420      B     1     2
## 5      5  -8028.578      A     1     1
## 6      6 102863.943      B     1     2
## 7      7 -18547.282      A     1     1
## 8      8  13080.521      B     1     2
## 9      9  79924.325      A     1     1
## 10    10 -44711.499      B     1     2
## ..   ...        ...    ...   ...   ...

The data are similar, except for the column named after the aesthetic, for the aesthetics used for grouping.

ggplot(my.data, aes(x, y, shape = group)) + geom_point() + 
  stat_debug_group()
## [1] "Input 'data' to 'compute_group()':"
## Source: local data frame [50 x 5]
## 
##        x          y  shape PANEL group
##    (dbl)      (dbl) (fctr) (int) (int)
## 1      1 -27205.450      A     1     1
## 2      3  45790.918      A     1     1
## 3      5  -8028.578      A     1     1
## 4      7 -18547.282      A     1     1
## 5      9  79924.325      A     1     1
## 6     11  -2823.736      A     1     1
## 7     13 -78016.690      A     1     1
## 8     15 -74281.234      A     1     1
## 9     17   9903.674      A     1     1
## 10    19 -94022.623      A     1     1
## ..   ...        ...    ...   ...   ...
## [1] "Input 'data' to 'compute_group()':"
## Source: local data frame [50 x 5]
## 
##        x         y  shape PANEL group
##    (dbl)     (dbl) (fctr) (int) (int)
## 1      2 -14242.65      B     1     2
## 2      4  53731.42      B     1     2
## 3      6 102863.94      B     1     2
## 4      8  13080.52      B     1     2
## 5     10 -44711.50      B     1     2
## 6     12  23839.55      B     1     2
## 7     14  75601.96      B     1     2
## 8     16 104676.72      B     1     2
## 9     18 -68746.93      B     1     2
## 10    20 -39230.19      B     1     2
## ..   ...       ...    ...   ...   ...

If we use as geom "label" or "text" a debug summary is added to the plot itself, we can use other arguments valid for the geom used, in this case vjust.

ggplot(my.data, aes(x, y, shape = group)) + geom_point() + 
  stat_debug_group(geom = "label", vjust = c(-0.5,1.5))
## [1] "Input 'data' to 'compute_group()':"
## Source: local data frame [50 x 5]
## 
##        x          y  shape PANEL group
##    (dbl)      (dbl) (fctr) (int) (int)
## 1      1 -27205.450      A     1     1
## 2      3  45790.918      A     1     1
## 3      5  -8028.578      A     1     1
## 4      7 -18547.282      A     1     1
## 5      9  79924.325      A     1     1
## 6     11  -2823.736      A     1     1
## 7     13 -78016.690      A     1     1
## 8     15 -74281.234      A     1     1
## 9     17   9903.674      A     1     1
## 10    19 -94022.623      A     1     1
## ..   ...        ...    ...   ...   ...
## [1] "Input 'data' to 'compute_group()':"
## Source: local data frame [50 x 5]
## 
##        x         y  shape PANEL group
##    (dbl)     (dbl) (fctr) (int) (int)
## 1      2 -14242.65      B     1     2
## 2      4  53731.42      B     1     2
## 3      6 102863.94      B     1     2
## 4      8  13080.52      B     1     2
## 5     10 -44711.50      B     1     2
## 6     12  23839.55      B     1     2
## 7     14  75601.96      B     1     2
## 8     16 104676.72      B     1     2
## 9     18 -68746.93      B     1     2
## 10    20 -39230.19      B     1     2
## ..   ...       ...    ...   ...   ...

The summary function can be a user defined one, which allows lots of flexibility.

ggplot(my.data, aes(x, y)) + geom_point() + 
  stat_debug_group(summary.fun = summary)
## [1] "Input 'data' to 'compute_group()':"
##        x                y               PANEL       group   
##  Min.   :  1.00   Min.   : -94023   Min.   :1   Min.   :-1  
##  1st Qu.: 25.75   1st Qu.:  40345   1st Qu.:1   1st Qu.:-1  
##  Median : 50.50   Median : 154036   Median :1   Median :-1  
##  Mean   : 50.50   Mean   : 266433   Mean   :1   Mean   :-1  
##  3rd Qu.: 75.25   3rd Qu.: 422069   3rd Qu.:1   3rd Qu.:-1  
##  Max.   :100.00   Max.   :1077469   Max.   :1   Max.   :-1

ggplot(my.data, aes(x, y)) + geom_point() + 
  stat_debug_group(summary.fun = head)
## [1] "Input 'data' to 'compute_group()':"
##   x          y PANEL group
## 1 1 -27205.450     1    -1
## 2 2 -14242.651     1    -1
## 3 3  45790.918     1    -1
## 4 4  53731.420     1    -1
## 5 5  -8028.578     1    -1
## 6 6 102863.943     1    -1

ggplot(my.data, aes(x, y)) + geom_point() + 
  stat_debug_group(summary.fun = nrow)
## [1] "Input 'data' to 'compute_group()':"
## [1] 100

The default.

ggplot(my.data, aes(x, y)) + geom_point() + 
  stat_debug_group(summary.fun = dplyr::as_data_frame)
## [1] "Input 'data' to 'compute_group()':"
## Source: local data frame [100 x 4]
## 
##        x          y PANEL group
##    (dbl)      (dbl) (int) (int)
## 1      1 -27205.450     1    -1
## 2      2 -14242.651     1    -1
## 3      3  45790.918     1    -1
## 4      4  53731.420     1    -1
## 5      5  -8028.578     1    -1
## 6      6 102863.943     1    -1
## 7      7 -18547.282     1    -1
## 8      8  13080.521     1    -1
## 9      9  79924.325     1    -1
## 10    10 -44711.499     1    -1
## ..   ...        ...   ...   ...

ggplot(my.data, aes(x, y)) + geom_point() + 
  stat_debug_group(summary.fun = head, summary.fun.args = list(n = 3))
## [1] "Input 'data' to 'compute_group()':"
##   x         y PANEL group
## 1 1 -27205.45     1    -1
## 2 2 -14242.65     1    -1
## 3 3  45790.92     1    -1

This next chunk showing how to print the whole data frame is not run as its output is more than 100 lines long as the data set contains 100 observations.

ggplot(my.data, aes(x, y)) + geom_point() + 
  stat_debug_group(summary.fun = function(x) {x})

With grouping, for each group the compute_group() function is called with a subset of the data.

ggplot(my.data, aes(x, y, colour = group)) + geom_point() + 
  stat_debug_group(summary.fun = head, summary.fun.args = list(n = 3))
## [1] "Input 'data' to 'compute_group()':"
##   x          y colour PANEL group
## 1 1 -27205.450      A     1     1
## 3 3  45790.918      A     1     1
## 5 5  -8028.578      A     1     1
## [1] "Input 'data' to 'compute_group()':"
##   x         y colour PANEL group
## 2 2 -14242.65      B     1     2
## 4 4  53731.42      B     1     2
## 6 6 102863.94      B     1     2

In this example with grouping and facets, within each panel the compute_group() function is called for each group, in total four times.

ggplot(my.data, aes(x, y, colour = group)) + geom_point() + 
  stat_debug_group(summary.fun = nrow) +
  facet_wrap(~block)
## [1] "Input 'data' to 'compute_group()':"
## [1] 25
## [1] "Input 'data' to 'compute_group()':"
## [1] 25
## [1] "Input 'data' to 'compute_group()':"
## [1] 25
## [1] "Input 'data' to 'compute_group()':"
## [1] 25

With facets, for each panel the compute_panel() function is called with a subset of the data that is not split by groups. For our example, it is called twice.

ggplot(my.data, aes(x, y, colour = group)) + geom_point() + 
  stat_debug_panel(summary.fun = nrow) +
  facet_wrap(~block)
## [1] "Input 'data' to 'compute_panel()':"
## [1] 50
## [1] "Input 'data' to 'compute_panel()':"
## [1] 50

Finally we show how geom_debug() can be used. First to print to the console the data as passed to geoms.

ggplot(my.data, aes(x, y, colour = group)) + geom_point() + 
  geom_debug(summary.fun = head)
## [1] "Input 'data' to 'geom_debug()':"
##    colour x          y PANEL group
## 1 #F8766D 1 -27205.450     1     1
## 2 #00BFC4 2 -14242.651     1     2
## 3 #F8766D 3  45790.918     1     1
## 4 #00BFC4 4  53731.420     1     2
## 5 #F8766D 5  -8028.578     1     1
## 6 #00BFC4 6 102863.943     1     2

And also to print to the console the data returned by a stat.

ggplot(my.data, aes(x, y, colour = group)) + geom_point() + 
  stat_peaks(span = NULL,
             geom = "debug", 
             summary.fun = function(x) {x}, 
             summary.fun.args = list())
## [1] "Input 'data' to 'geom_debug()':"
##    colour xintercept yintercept label   x       y PANEL group x.label
## 1 #F8766D         95     984858    95  95  984858     1     1      95
## 2 #00BFC4        100    1077468   100 100 1077468     1     2     100
##     y.label
## 1 9.849e+05
## 2 1.077e+06

The package also defines a “null” geom, which is used as default by the debug stats described above.

ggplot(my.data, aes(x, y, colour = group)) + geom_null()