Extracting and visualizing tidy draws from brms models

Introduction

This vignette describes how to use the tidybayes and ggdist packages to extract and visualize tidy data frames of draws from posterior distributions of model variables, means, and predictions from brms::brm. For a more general introduction to tidybayes and its use on general-purpose Bayesian modeling languages (like Stan and JAGS), see vignette("tidybayes").

Setup

The following libraries are required to run this vignette:

library(magrittr)
library(dplyr)
library(purrr)
library(forcats)
library(tidyr)
library(modelr)
library(ggdist)
library(tidybayes)
library(ggplot2)
library(cowplot)
library(rstan)
library(brms)
library(ggrepel)
library(RColorBrewer)
library(gganimate)
library(posterior)
library(distributional)

theme_set(theme_tidybayes() + panel_border())

These options help Stan run faster:

rstan_options(auto_write = TRUE)
options(mc.cores = parallel::detectCores())

Example dataset

To demonstrate tidybayes, we will use a simple dataset with 10 observations from 5 conditions each:

set.seed(5)
n = 10
n_condition = 5
ABC =
  tibble(
    condition = rep(c("A","B","C","D","E"), n),
    response = rnorm(n * 5, c(0,1,2,1,-1), 0.5)
  )

A snapshot of the data looks like this:

head(ABC, 10)

This is a typical tidy format data frame: one observation per row. Graphically:

ABC %>%
  ggplot(aes(y = condition, x = response)) +
  geom_point()

Model

Let’s fit a hierarchical model with shrinkage towards a global mean:

m = brm(
  response ~ (1|condition), 
  data = ABC, 
  prior = c(
    prior(normal(0, 1), class = Intercept),
    prior(student_t(3, 0, 1), class = sd),
    prior(student_t(3, 0, 1), class = sigma)
  ),
  control = list(adapt_delta = .99),
  
  file = "models/tidy-brms_m.rds" # cache model (can be removed)  
)

The results look like this:

m

##  Family: gaussian 
##   Links: mu = identity; sigma = identity 
## Formula: response ~ (1 | condition) 
##    Data: ABC (Number of observations: 50) 
##   Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
##          total post-warmup draws = 4000
## 
## Multilevel Hyperparameters:
## ~condition (Number of levels: 5) 
##               Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept)     1.17      0.43     0.60     2.22 1.00      944     1542
## 
## Regression Coefficients:
##           Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept     0.50      0.48    -0.49     1.41 1.00      904     1204
## 
## Further Distributional Parameters:
##       Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma     0.56      0.06     0.46     0.70 1.00     2057     2243
## 
## Draws were sampled using sampling(NUTS). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).

Extracting draws from a fit in tidy-format using spread_draws

Now that we have our results, the fun begins: getting the draws out in a tidy format! First, we’ll use the get_variables() function to get a list of raw model variable names so that we know what variables we can extract from the model:

get_variables(m)

##  [1] "b_Intercept"              "sd_condition__Intercept"  "sigma"                    "r_condition[A,Intercept]"
##  [5] "r_condition[B,Intercept]" "r_condition[C,Intercept]" "r_condition[D,Intercept]" "r_condition[E,Intercept]"
##  [9] "lp__"                     "accept_stat__"            "stepsize__"               "treedepth__"             
## [13] "n_leapfrog__"             "divergent__"              "energy__"

Here, b_Intercept is the global mean, and the r_condition[] variables are offsets from that mean for each condition. Given these variables:

• r_condition[A,Intercept]
• r_condition[B,Intercept]
• r_condition[C,Intercept]
• r_condition[D,Intercept]
• r_condition[E,Intercept]

We might want a data frame where each row is a draw from either r_condition[A,Intercept], r_condition[B,Intercept], ...[C,...], ...[D,...], or ...[E,...], and where we have columns indexing which chain/iteration/draw the row came from and which condition (A to E) it is for. That would allow us to easily compute quantities grouped by condition, or generate plots by condition using ggplot, or even merge draws with the original data to plot data and posteriors simultaneously.

The workhorse of tidybayes is the spread_draws() function, which does this extraction for us. It includes a simple specification format that we can use to extract variables and their indices into tidy-format data frames.

m %>%
  spread_draws(r_condition[condition,term]) %>%
  head(10)

m %>%
  spread_draws(r_condition[c,t]) %>%
  head(10)

m %>%
  spread_draws(r_condition[condition,]) %>%
  head(10)

Point summaries and intervals

m %>%
  spread_draws(b_Intercept, sigma) %>%
  head(10)

m %>%
  spread_draws(b_Intercept, sigma) %>%
  median_qi(b_Intercept, sigma)

m %>%
  spread_draws(b_Intercept, sigma) %>%
  median_qi()

m %>%
  gather_draws(b_Intercept, sigma) %>%
  median_qi()

m %>%
  spread_draws(r_condition[condition,]) %>%
  median_qi()

m %>%
  spread_draws(r_condition[condition,]) %>%
  group_by(condition) %>%   # this line not necessary (done by spread_draws)
  median_qi(r_condition)      # b is not necessary (it is the only non-group column)

m %>%
  spread_draws(r_condition[condition,]) %>%
  summarise_draws()

Combining variables with different indices in a single tidy format data frame

spread_draws() and gather_draws() support extracting variables that have different indices into the same data frame. Indices with the same name are automatically matched up, and values are duplicated as necessary to produce one row per all combination of levels of all indices. For example, we might want to calculate the mean within each condition (call this condition_mean). In this model, that mean is the intercept (b_Intercept) plus the effect for a given condition (r_condition).

We can gather draws from b_Intercept and r_condition together in a single data frame:

m %>% 
  spread_draws(b_Intercept, r_condition[condition,]) %>%
  head(10)

Within each draw, b_Intercept is repeated as necessary to correspond to every index of r_condition. Thus, the mutate function from dplyr can be used to find their sum, condition_mean (which is the mean for each condition):

m %>%
  spread_draws(`b_Intercept`, r_condition[condition,]) %>%
  mutate(condition_mean = b_Intercept + r_condition) %>%
  median_qi(condition_mean)

median_qi() uses tidy evaluation (see vignette("tidy-evaluation", package = "rlang")), so it can take column expressions, not just column names. Thus, we can simplify the above example by moving the calculation of condition_mean from mutate into median_qi():

m %>%
  spread_draws(b_Intercept, r_condition[condition,]) %>%
  median_qi(condition_mean = b_Intercept + r_condition)

Plotting intervals with multiple probability levels

median_qi() and its sister functions can produce an arbitrary number of probability intervals by setting the .width = argument:

m %>%
  spread_draws(b_Intercept, r_condition[condition,]) %>%
  median_qi(condition_mean = b_Intercept + r_condition, .width = c(.95, .8, .5))

The results are in a tidy format: one row per group and uncertainty interval width (.width). This facilitates plotting. For example, assigning -.width to the linewidth aesthetic will show all intervals, making thicker lines correspond to smaller intervals. The ggdist::geom_pointinterval() geom automatically sets the linewidth aesthetic appropriately based on the .width column in the data to produce plots of points with multiple probability levels:

m %>%
  spread_draws(b_Intercept, r_condition[condition,]) %>%
  median_qi(condition_mean = b_Intercept + r_condition, .width = c(.95, .66)) %>%
  ggplot(aes(y = condition, x = condition_mean, xmin = .lower, xmax = .upper)) +
  geom_pointinterval() 

Intervals with densities

To see the density along with the intervals, we can use ggdist::stat_eye() (“eye plots”, which combine intervals with violin plots), or ggdist::stat_halfeye() (interval + density plots):

m %>%
  spread_draws(b_Intercept, r_condition[condition,]) %>%
  mutate(condition_mean = b_Intercept + r_condition) %>%
  ggplot(aes(y = condition, x = condition_mean)) +
  stat_halfeye()

Or say you want to annotate portions of the densities in color; the fill aesthetic can vary within a slab in all geoms and stats in the ggdist::geom_slabinterval() family, including ggdist::stat_halfeye(). For example, if you want to annotate a domain-specific region of practical equivalence (ROPE), you could do something like this:

m %>%
  spread_draws(b_Intercept, r_condition[condition,]) %>%
  mutate(condition_mean = b_Intercept + r_condition) %>%
  ggplot(aes(y = condition, x = condition_mean, fill = after_stat(abs(x) < .8))) +
  stat_halfeye() +
  geom_vline(xintercept = c(-.8, .8), linetype = "dashed") +
  scale_fill_manual(values = c("gray80", "skyblue"))

Other visualizations of distributions: stat_slabinterval

There are a variety of additional stats for visualizing distributions in the ggdist::geom_slabinterval() family of stats and geoms:

See vignette("slabinterval", package = "ggdist") for an overview.

Posterior means and predictions

Rather than calculating conditional means manually as in the previous example, we could use add_epred_draws(), which is analogous to brms::posterior_epred() (giving posterior draws from the expectation of the posterior predictive; i.e. posterior distributions of conditional means), but uses a tidy data format. We can combine it with modelr::data_grid() to first generate a grid describing the predictions we want, then transform that grid into a long-format data frame of draws from conditional means:

ABC %>%
  data_grid(condition) %>%
  add_epred_draws(m) %>%
  head(10)

To plot this example, we’ll also show the use of ggdist::stat_pointinterval() instead of ggdist::geom_pointinterval(), which summarizes draws into points and intervals within ggplot:

ABC %>%
  data_grid(condition) %>%
  add_epred_draws(m) %>%
  ggplot(aes(x = .epred, y = condition)) +
  stat_pointinterval(.width = c(.66, .95))

Quantile dotplots

Intervals are nice if the alpha level happens to line up with whatever decision you are trying to make, but getting a shape of the posterior is better (hence eye plots, above). On the other hand, making inferences from density plots is imprecise (estimating the area of one shape as a proportion of another is a hard perceptual task). Reasoning about probability in frequency formats is easier, motivating quantile dotplots (Kay et al. 2016, Fernandes et al. 2018), which also allow precise estimation of arbitrary intervals (down to the dot resolution of the plot, 100 in the example below).

Within the slabinterval family of geoms in tidybayes is the dots and dotsinterval family, which automatically determine appropriate bin sizes for dotplots and can calculate quantiles from samples to construct quantile dotplots. ggdist::stat_dotsinterval() is the variant designed for use on samples:

ABC %>%
  data_grid(condition) %>%
  add_epred_draws(m) %>%
  ggplot(aes(x = .epred, y = condition)) +
  stat_dotsinterval(quantiles = 100)

The idea is to get away from thinking about the posterior as indicating one canonical point or interval, but instead to represent it as (say) 100 approximately equally likely points.

Posterior predictions

Where add_epred_draws() is analogous to brms::posterior_epred(), add_predicted_draws() is analogous to brms::posterior_predict(), giving draws from the posterior predictive distribution.

Here is an example of posterior predictive distributions plotted using ggdist::stat_slab():

ABC %>%
  data_grid(condition) %>%
  add_predicted_draws(m) %>%
  ggplot(aes(x = .prediction, y = condition)) +
  stat_slab()

We could also use ggdist::stat_interval() to plot predictive bands alongside the data:

ABC %>%
  data_grid(condition) %>%
  add_predicted_draws(m) %>%
  ggplot(aes(y = condition, x = .prediction)) +
  stat_interval(.width = c(.50, .80, .95, .99)) +
  geom_point(aes(x = response), data = ABC) +
  scale_color_brewer()

Altogether, data, posterior predictions, and posterior distributions of the means:

grid = ABC %>%
  data_grid(condition)

means = grid %>%
  add_epred_draws(m)

preds = grid %>%
  add_predicted_draws(m)

ABC %>%
  ggplot(aes(y = condition, x = response)) +
  stat_interval(aes(x = .prediction), data = preds) +
  stat_pointinterval(aes(x = .epred), data = means, .width = c(.66, .95), position = position_nudge(y = -0.3)) +
  geom_point() +
  scale_color_brewer()

Posterior predictions, Kruschke-style

The above approach to posterior predictions integrates over the parameter uncertainty to give a single posterior predictive distribution. Another approach, often used by John Kruschke in his book Doing Bayesian Data Analysis, is to attempt to show both the predictive uncertainty and the parameter uncertainty simultaneously by showing several possible predictive distributions implied by the posterior.

We can do this pretty easily by asking for the distributional parameters for a given prediction implied by the posterior. We’ll do it explicitly here by setting dpar = c("mu", "sigma") in add_epred_draws(). Rather than specifying the parameters explicitly, you can also just set dpar = TRUE to get draws from all distributional parameters in a model, and this will work for any response distribution supported by brms. Then, we can select a small number of draws using sample_draws() and then use ggdist::stat_slab() to visualize each predictive distribution implied by the values of mu and sigma:

ABC %>%
  data_grid(condition) %>%
  add_epred_draws(m, dpar = c("mu", "sigma")) %>%
  sample_draws(30) %>%
  ggplot(aes(y = condition)) +
  stat_slab(aes(xdist = dist_normal(mu, sigma)), 
    slab_color = "gray65", alpha = 1/10, fill = NA
  ) +
  geom_point(aes(x = response), data = ABC, shape = 21, fill = "#9ECAE1", size = 2)

We could even combine the Kruschke-style plots of predictive distributions with half-eyes showing the posterior means:

ABC %>%
  data_grid(condition) %>%
  add_epred_draws(m, dpar = c("mu", "sigma")) %>%
  ggplot(aes(x = condition)) +
  stat_slab(aes(ydist = dist_normal(mu, sigma)), 
    slab_color = "gray65", alpha = 1/10, fill = NA, data = . %>% sample_draws(30), scale = .5
  ) +
  stat_halfeye(aes(y = .epred), side = "bottom", scale = .5) +
  geom_point(aes(y = response), data = ABC, shape = 21, fill = "#9ECAE1", size = 2, position = position_nudge(x = -.2))

Fit/prediction curves

To demonstrate drawing fit curves with uncertainty, let’s fit a slightly naive model to part of the mtcars dataset:

m_mpg = brm(
  mpg ~ hp * cyl, 
  data = mtcars, 
  
  file = "models/tidy-brms_m_mpg.rds"  # cache model (can be removed)
)

We can draw fit curves with probability bands:

mtcars %>%
  group_by(cyl) %>%
  data_grid(hp = seq_range(hp, n = 51)) %>%
  add_epred_draws(m_mpg) %>%
  ggplot(aes(x = hp, y = mpg, color = ordered(cyl))) +
  stat_lineribbon(aes(y = .epred)) +
  geom_point(data = mtcars) +
  scale_fill_brewer(palette = "Greys") +
  scale_color_brewer(palette = "Set2")

Or we can sample a reasonable number of fit lines (say 100) and overplot them:

mtcars %>%
  group_by(cyl) %>%
  data_grid(hp = seq_range(hp, n = 101)) %>%
  # NOTE: this shows the use of ndraws to subsample within add_epred_draws()
  # ONLY do this IF you are planning to make spaghetti plots, etc.
  # NEVER subsample to a small sample to plot intervals, densities, etc.
  add_epred_draws(m_mpg, ndraws = 100) %>%
  ggplot(aes(x = hp, y = mpg, color = ordered(cyl))) +
  geom_line(aes(y = .epred, group = paste(cyl, .draw)), alpha = .1) +
  geom_point(data = mtcars) +
  scale_color_brewer(palette = "Dark2")

Or we can create animated hypothetical outcome plots (HOPs) of fit lines:

set.seed(123456)
# NOTE: using a small number of draws to keep this example
# small, but in practice you probably want 50 or 100
ndraws = 20

p = mtcars %>%
  group_by(cyl) %>%
  data_grid(hp = seq_range(hp, n = 101)) %>%
  add_epred_draws(m_mpg, ndraws = ndraws) %>%
  ggplot(aes(x = hp, y = mpg, color = ordered(cyl))) +
  geom_line(aes(y = .epred, group = paste(cyl, .draw))) +
  geom_point(data = mtcars) +
  scale_color_brewer(palette = "Dark2") +
  transition_states(.draw, 0, 1) +
  shadow_mark(future = TRUE, color = "gray50", alpha = 1/20)

animate(p, nframes = ndraws, fps = 2.5, width = 432, height = 288, units = "px", res = 96, dev = "ragg_png")

Or we could plot posterior predictions (instead of means). For this example we’ll also use alpha to make it easier to see overlapping bands:

mtcars %>%
  group_by(cyl) %>%
  data_grid(hp = seq_range(hp, n = 101)) %>%
  add_predicted_draws(m_mpg) %>%
  ggplot(aes(x = hp, y = mpg, color = ordered(cyl), fill = ordered(cyl))) +
  stat_lineribbon(aes(y = .prediction), .width = c(.95, .80, .50), alpha = 1/4) +
  geom_point(data = mtcars) +
  scale_fill_brewer(palette = "Set2") +
  scale_color_brewer(palette = "Dark2")

This gets difficult to judge by group, so probably better to facet into multiple plots. Fortunately, since we are using ggplot, that functionality is built in:

mtcars %>%
  group_by(cyl) %>%
  data_grid(hp = seq_range(hp, n = 101)) %>%
  add_predicted_draws(m_mpg) %>%
  ggplot(aes(x = hp, y = mpg)) +
  stat_lineribbon(aes(y = .prediction), .width = c(.99, .95, .8, .5), color = brewer.pal(5, "Blues")[[5]]) +
  geom_point(data = mtcars) +
  scale_fill_brewer() +
  facet_grid(. ~ cyl, space = "free_x", scales = "free_x")

set.seed(1234)
AB = tibble(
  group = rep(c("a", "b"), each = 20),
  response = rnorm(40, mean = rep(c(1, 5), each = 20), sd = rep(c(1, 3), each = 20))
)

AB %>%
  ggplot(aes(x = response, y = group)) +
  geom_point()

m_ab = brm(
  bf(
    response ~ group,
    sigma ~ group
  ),
  data = AB,
  
  file = "models/tidy-brms_m_ab.rds"  # cache model (can be removed)
)

grid = AB %>%
  data_grid(group)

means = grid %>%
  add_epred_draws(m_ab)

preds = grid %>%
  add_predicted_draws(m_ab)

AB %>%
  ggplot(aes(x = response, y = group)) +
  stat_halfeye(aes(x = .epred), scale = 0.6, position = position_nudge(y = 0.175), data = means) +
  stat_interval(aes(x = .prediction), data = preds) +
  geom_point(data = AB) +
  scale_color_brewer()

grid %>%
  add_epred_draws(m_ab, dpar = TRUE) %>%
  ggplot(aes(x = sigma, y = group)) +
  stat_halfeye() +
  geom_vline(xintercept = 0, linetype = "dashed")

Comparing levels of a factor

If we wish compare the means from each condition, compare_levels() facilitates comparisons of the value of some variable across levels of a factor. By default it computes all pairwise differences.

Let’s demonstrate compare_levels() with ggdist::stat_halfeye(). We’ll also re-order by the mean of the difference:

m %>%
  spread_draws(r_condition[condition,]) %>%
  compare_levels(r_condition, by = condition) %>%
  ungroup() %>%
  mutate(condition = reorder(condition, r_condition)) %>%
  ggplot(aes(y = condition, x = r_condition)) +
  stat_halfeye() +
  geom_vline(xintercept = 0, linetype = "dashed") 

Ordinal models

The posterior_epred() function for ordinal and multinomial regression models in brms returns multiple variables for each draw: one for each outcome category (in contrast to rstanarm::stan_polr() models, which return draws from the latent linear predictor). The philosophy of tidybayes is to tidy whatever format is output by a model, so in keeping with that philosophy, when applied to ordinal and multinomial brms models, add_epred_draws() adds an additional column called .category and a separate row containing the variable for each category is output for every draw and predictor.

mtcars_clean = mtcars %>%
  mutate(cyl = ordered(cyl))

head(mtcars_clean)

m_cyl = brm(
  cyl ~ mpg, 
  data = mtcars_clean, 
  family = cumulative,
  seed = 58393,
  
  file = "models/tidy-brms_m_cyl.rds"  # cache model (can be removed)
)

tibble(mpg = 21) %>%
  add_epred_draws(m_cyl) %>%
  median_qi(.epred)

data_plot = mtcars_clean %>%
  ggplot(aes(x = mpg, y = cyl, color = cyl)) +
  geom_point() +
  scale_color_brewer(palette = "Dark2", name = "cyl")

fit_plot = mtcars_clean %>%
  data_grid(mpg = seq_range(mpg, n = 101)) %>%
  add_epred_draws(m_cyl, value = "P(cyl | mpg)", category = "cyl") %>%
  ggplot(aes(x = mpg, y = `P(cyl | mpg)`, color = cyl)) +
  stat_lineribbon(aes(fill = cyl), alpha = 1/5) +
  scale_color_brewer(palette = "Dark2") +
  scale_fill_brewer(palette = "Dark2")

plot_grid(ncol = 1, align = "v",
  data_plot,
  fit_plot
)

# NOTE: using a small number of draws to keep this example
# small, but in practice you probably want 50 or 100
ndraws = 20

p = mtcars_clean %>%
  data_grid(mpg = seq_range(mpg, n = 101)) %>%
  add_epred_draws(m_cyl, value = "P(cyl | mpg)", category = "cyl") %>%
  ggplot(aes(x = mpg, y = `P(cyl | mpg)`, color = cyl)) +
  # we remove the `.draw` column from the data for stat_lineribbon so that the same ribbons
  # are drawn on every frame (since we use .draw to determine the transitions below)
  stat_lineribbon(aes(fill = cyl), alpha = 1/5, color = NA, data = . %>% select(-.draw)) +
  # we use sample_draws to subsample at the level of geom_line (rather than for the full dataset
  # as in previous HOPs examples) because we need the full set of draws for stat_lineribbon above
  geom_line(aes(group = paste(.draw, cyl)), linewidth = 1, data = . %>% sample_draws(ndraws)) +
  scale_color_brewer(palette = "Dark2") +
  scale_fill_brewer(palette = "Dark2") +
  transition_manual(.draw)

animate(p, nframes = ndraws, fps = 2.5, width = 576, height = 192, units = "px", res = 96, dev = "ragg_png")

tibble(mpg = 20) %>%
  add_epred_draws(m_cyl, value = "P(cyl | mpg = 20)", category = "cyl") %>%
  ungroup() %>%
  select(.draw, cyl, `P(cyl | mpg = 20)`) %>%
  gather_pairs(cyl, `P(cyl | mpg = 20)`, triangle = "both") %>%
  filter(.row != .col) %>%
  ggplot(aes(.x, .y)) +
  geom_point(alpha = 1/50) +
  facet_grid(.row ~ .col) +
  ylab("P(cyl = row | mpg = 20)") +
  xlab("P(cyl = col | mpg = 20)")

label_data_function = . %>% 
  ungroup() %>%
  filter(mpg == quantile(mpg, .47)) %>%
  summarise_if(is.numeric, mean)

data_plot_with_mean = mtcars_clean %>%
  data_grid(mpg = seq_range(mpg, n = 101)) %>%
  # NOTE: this shows the use of ndraws to subsample within add_epred_draws()
  # ONLY do this IF you are planning to make spaghetti plots, etc.
  # NEVER subsample to a small sample to plot intervals, densities, etc.
  add_epred_draws(m_cyl, value = "P(cyl | mpg)", category = "cyl", ndraws = 100) %>%
  group_by(mpg, .draw) %>%
  # calculate expected cylinder value
  mutate(cyl = as.numeric(as.character(cyl))) %>%
  summarise(cyl = sum(cyl * `P(cyl | mpg)`), .groups = "drop") %>%
  ggplot(aes(x = mpg, y = cyl)) +
  geom_line(aes(group = .draw), alpha = 5/100) +
  geom_point(aes(y = as.numeric(as.character(cyl)), fill = cyl), data = mtcars_clean, shape = 21, size = 2) +
  geom_text(aes(x = mpg + 4), label = "E[cyl | mpg]", data = label_data_function, hjust = 0) +
  geom_segment(aes(yend = cyl, xend = mpg + 3.9), data = label_data_function) +
  scale_fill_brewer(palette = "Set2", name = "cyl")

plot_grid(ncol = 1, align = "v",
  data_plot_with_mean,
  fit_plot
)

mtcars_clean %>%
  # we use `select` instead of `data_grid` here because we want to make posterior predictions
  # for exactly the same set of observations we have in the original data
  select(mpg) %>%
  add_predicted_draws(m_cyl, seed = 1234) %>%
  # recover original factor labels
  mutate(cyl = levels(mtcars_clean$cyl)[.prediction]) %>%
  ggplot(aes(x = mpg, y = cyl)) +
  geom_count(color = "gray75") +
  geom_point(aes(fill = cyl), data = mtcars_clean, shape = 21, size = 2) +
  scale_fill_brewer(palette = "Dark2") +
  geom_label_repel(
    data = . %>% ungroup() %>% filter(cyl == "8") %>% filter(mpg == max(mpg)) %>% dplyr::slice(1),
    label = "posterior predictions", xlim = c(26, NA), ylim = c(NA, 2.8), point.padding = 0.3,
    label.size = NA, color = "gray50", segment.color = "gray75"
  ) +
  geom_label_repel(
    data = mtcars_clean %>% filter(cyl == "6") %>% filter(mpg == max(mpg)) %>% dplyr::slice(1),
    label = "observed data", xlim = c(26, NA), ylim = c(2.2, NA), point.padding = 0.2,
    label.size = NA, segment.color = "gray35"
  )

mtcars_clean %>%
  select(mpg) %>%
  add_predicted_draws(m_cyl, ndraws = 100, seed = 12345) %>%
  # recover original factor labels
  mutate(cyl = levels(mtcars_clean$cyl)[.prediction]) %>%
  ggplot(aes(x = cyl)) +
  stat_count(aes(group = NA), geom = "line", data = mtcars_clean, color = "red", linewidth = 3, alpha = .5) +
  stat_count(aes(group = .draw), geom = "line", position = "identity", alpha = .05) +
  geom_label(data = data.frame(cyl = "4"), y = 9.5, label = "posterior\npredictions",
    hjust = 1, color = "gray50", lineheight = 1, label.size = NA) +
  geom_label(data = data.frame(cyl = "8"), y = 14, label = "observed\ndata",
    hjust = 0, color = "red", lineheight = 1, label.size = NA)

set.seed(12345)

mtcars_clean %>%
  select(mpg) %>%
  add_predicted_draws(m_cyl) %>%
  # recover original factor labels. Must ungroup first so that the
  # factor is created in the same way in all groups; this is a workaround
  # because brms no longer returns labelled predictions (hopefully that
  # is fixed then this will no longer be necessary)
  ungroup() %>%
  mutate(cyl = ordered(levels(mtcars_clean$cyl)[.prediction], levels(mtcars_clean$cyl))) %>%
  # need .drop = FALSE to ensure 0 counts are not dropped
  group_by(.draw, .drop = FALSE) %>%
  count(cyl) %>%
  gather_pairs(cyl, n) %>%
  ggplot(aes(.x, .y)) +
  geom_count(color = "gray75") +
  geom_point(data = mtcars_clean %>% count(cyl) %>% gather_pairs(cyl, n), color = "red") +
  facet_grid(vars(.row), vars(.col)) +
  xlab("Number of observations with cyl = col") +
  ylab("Number of observations with cyl = row") 

data(esoph)
m_esoph_brm = brm(
  tobgp ~ agegp, 
  data = esoph, 
  family = cumulative(),

  file = "models/tidy-brms_m_esoph_brm.rds"  
)

esoph %>%
  data_grid(agegp) %>%
  add_epred_draws(m_esoph_brm, dpar = TRUE, category = "tobgp") %>%
  ggplot(aes(x = agegp, y = .epred, color = tobgp)) +
  stat_pointinterval(position = position_dodge(width = .4)) +
  scale_size_continuous(guide = "none") +
  scale_color_manual(values = brewer.pal(6, "Blues")[-c(1,2)])

esoph_plot = esoph %>%
  data_grid(agegp) %>%
  add_epred_draws(m_esoph_brm, category = "tobgp") %>%
  ggplot(aes(x = .epred, y = tobgp)) +
  coord_cartesian(expand = FALSE) +
  facet_grid(. ~ agegp, switch = "x") +
  theme_classic() +
  theme(strip.background = element_blank(), strip.placement = "outside") +
  ggtitle("P(tobacco consumption category | age group)") +
  xlab("age group")

esoph_plot +
  stat_summary(fun = median, geom = "bar", fill = "gray65", width = 1, color = "white") +
  stat_pointinterval()

esoph_plot +
  stat_ccdfinterval() +
  expand_limits(x = 0) #ensure bars go to 0