Using Optuna Dashboard with rCISSVAE

2026-01-20

What is Optuna Dashboard?

Optuna dashboard is a visualization tool that allows you to view the history and results of optuna hyperparameter optimization studies. To install it, activate your rCISSVAE virtual environment and use pip install optuna-dashboard from command line.

If you are using Positron as your IDE, you can install the Optuna Dashboard Extension and easily open optuna database files. For others, the simplest way to use Optuna Dashboard is from the command line. Please note that the command line version of Optuna Dashboard has some features that are not in the Extension.

Creating an Optuna Dashboard with the Autotune Function

The autotune_cissvae() function has an option for creating an Optuna Dashboard database.

In R:

library(tidyverse)
library(reticulate)
library(rCISSVAE)
library(kableExtra)

## Set the virtual environment
# reticulate::use_virtualenv("./.venv", required = TRUE)

## Load the data
data(df_missing)
data(clusters)

aut <- autotune_cissvae(
  data = df_missing,
  index_col = "index",
  clusters = clusters$clusters,
  n_trials = 3, ## Using low number of trials for demo
  study_name = "ShowOptunaDB",
  device_preference = "cpu",
  optuna_dashboard_db = "sqlite:///optuna_study_demo.db",  # Save results to database
  load_if_exists = TRUE, ## Set true to load and continue study if it exists
  seed = 42, 
  verbose = FALSE,
  
  ## Hyperparameter search space
  num_hidden_layers = c(2, 5),     # Try 2-5 hidden layers
  hidden_dims = c(64, 512),        # Layer sizes from 64 to 512
  latent_dim = c(10, 100),         # Latent dimension range
  latent_shared = c(TRUE, FALSE),
  output_shared = c(TRUE, FALSE),
  lr = 0.01,  # Learning rate range
  decay_factor = 0.99,
  beta = 0.01,  # KL weight range
  num_epochs = 5,                # Fixed epochs for demo
  batch_size = c(1000, 4000),     # Batch size options
  num_shared_encode = c(0, 1, 2, 3),
  num_shared_decode = c(0, 1, 2, 3),
  
  # Layer placement strategies - try different arrangements
  encoder_shared_placement = c("at_end", "at_start", "alternating", "random"),
  decoder_shared_placement = c("at_start", "at_end", "alternating", "random"),
  
  refit_patience = 2,        # Early stopping patience
  refit_loops = 10,                # Fixed refit loops
  epochs_per_loop = 5,   # Epochs per refit loop
  reset_lr_refit = FALSE
)

# Analyze results
imputed <- aut$imputed
best_model <- aut$model
results <- aut$results

# View best hyperparameters
print("Trial results:")
results |> kable() |>
  kable_styling(font_size=12)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.1     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.2
## ✔ purrr     1.2.0     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

## [1] "Trial results:"

trial_number	imputation_error	num_hidden_layers	hidden_dim_0	hidden_dim_1	hidden_dim_2	hidden_dim_3	hidden_dim_4	latent_dim	latent_shared	output_shared	batch_size	num_shared_encode	num_shared_decode	encoder_shared_placement	decoder_shared_placement	layer_order_enc_used	layer_order_dec_used
0	29.62110	5	512	64	512	64	64	100	FALSE	FALSE	1000	1	1	alternating	at_start	S,U,U,U,U	S,U,U,U,U
1	33.00819	5	64	64	64	512	64	10	TRUE	TRUE	1000	1	0	alternating	alternating	S,U,U,U,U	U,U,U,U,U
2	58.28946	2	512	64	NaN	NaN	NaN	10	TRUE	FALSE	4000	0	3	alternating	random	U,U	S,S

To view the dashboard:

From Command Line

optuna-dashboard "sqlite:///optuna_study_demo.db"

For more information see the optuna dashboard documentation.