add_draws: Add draws to a data frame in tidy format

Description

Add draws from a matrix of draws (usually draws from a predictive distribution) to a data frame in tidy format. This is a generic version of add_fitted_draws/add_predicted_draws that can be used with model types that have their own prediction functions that are not yet supported by tidybayes.

Usage

add_draws(data, draws, value = ".value")

Arguments

data

Data frame to add draws to, with M rows.

draws

N by M matrix of draws, with M columns corresponding to the M rows in data, and N draws in each column.

value

The name of the output column; default ".value".

Value

A data frame (actually, a tibble) with a .row column (a factor grouping rows from the input data), a .draw column (a unique index corresponding to each draw from the distribution), and a column with its name specified by the value argument (default is .value) containing the values of draws from draws. The data frame is grouped by all rows in data plus the .row column.

Details

Given a data frame with M rows and an N by M matrix of N draws, adds a .row, .draw, and .value column (or another name if value is set) to data, and expands data into a long-format dataframe of draws.

add_fitted_draws(df, m) is roughly equivalent to add_draws(df, posterior_linpred(m)), except that add_fitted_draws standardizes argument names and values across packages.

add_predicted_draws(df, m) is roughly equivalent to add_draws(df, posterior_predict(m)), except that add_predicted_draws standardizes argument names and values across packages.

Examples

Run this code

# NOT RUN {
library(ggplot2)
library(dplyr)

if (
  require("rstanarm", quietly = TRUE) &&
  require("modelr", quietly = TRUE)
) {

  theme_set(theme_light())

  m_mpg = stan_glm(mpg ~ hp * cyl, data = mtcars,
    # 1 chain / few iterations just so example runs quickly
    # do not use in practice
    chains = 1, iter = 500)

  # plot posterior predictive intervals
  mtcars %>%
    group_by(cyl) %>%
    data_grid(hp = seq_range(hp, n = 101)) %>%
    # the line below is equivalent to add_fitted_draws(m_mpg), except that it does not
    # standardize arguments across model types
    add_draws(posterior_linpred(m_mpg, newdata = .)) %>%
    ggplot(aes(x = hp, y = mpg, color = ordered(cyl))) +
    stat_lineribbon(aes(y = .value), alpha = 0.25) +
    geom_point(data = mtcars) +
    scale_fill_brewer(palette = "Greys")
}
# }