MCMC simulation data for AutoGibbs.jl benchmarks

<p>Chains and diagnostic data for the test models of <a href="https://github.com/phipsgabler/AutoGibbs.jl">AutoGibbs.jl.</a> Includes four CSV files for each of the models: GMM, HMM, and IMM.</p> <p>&nbsp;</p> <p>Files are all in long format. The files for chains, diagnostics, and sampling times all contain &quot;model&quot;, &quot;discrete_algorithm&quot; (AG or PG), &quot;continuous_algorithm&quot; (always HMC), &quot;particles&quot; (always 100), &quot;data_size&quot; (number of observations: 10, 25, or 50), and &quot;repetition&quot; (index of chain; there are 10 chains per parameter combination, except for HMC, there the benchmark has been killed somewhere after the eight chain). In addition to that, the sampling time files contain a column &quot;samping_time&quot; (in seconds), and the diagnostic files have columns &quot;parameter&quot; (name of the random variable), &quot;diagnostic&quot; (ESS or R_hat), and &quot;value&quot; with chain diagnostic values. Chain files have &quot;parameter&quot;, &quot;step&quot;, and &quot;value&quot; for the sampled values at each step of the chain.</p> <p>&nbsp;</p> <p>The compile time measurements consist just of columns &quot;model&quot;, &quot;data_size&quot;, &quot;repetition&quot;, &quot;compilation_time&quot; (in seconds).</p> <p>&nbsp;</p> <p>Note that the &quot;parameter&quot; column in the HMM data has been manually adjusted; see the file plotting.jl in the AutoGibbs.jl repository.</p>