Saqrlab Reference — Visualization

This reference covers Saqrlab’s ggplot2-based plotting verbs for comparison results. plot_network_estimation() visualizes the output of compare_network_estimation(), plot_tna_comparison() plots the per-iteration metric distributions from a comparison, and plot_sampling_distribution() draws a single metric’s distribution from run_sampling_analysis(). Each example first builds the minimal result object the plot consumes, then renders the figure.

# Shared inputs: simulate sequences, fit a model, and run the comparisons
# that the plotting verbs consume.
set.seed(1)
trans_mat <- matrix(c(
  0.7, 0.2, 0.1,
  0.3, 0.5, 0.2,
  0.2, 0.3, 0.5
), nrow = 3, byrow = TRUE)
rownames(trans_mat) <- colnames(trans_mat) <- c("A", "B", "C")
init_probs <- c(A = 0.5, B = 0.3, C = 0.2)

seqs <- simulate_sequences(
  transition_matrix = trans_mat,
  initial_probabilities = init_probs,
  max_seq_length = 12,
  num_rows = 40
)

estimation <- compare_network_estimation(
  seqs,
  model_types = c("tna", "ftna"),
  iterations = 15,
  seed = 1,
  verbose = FALSE
)

model <- fit_network_model(seqs, "tna")
sampling <- run_sampling_analysis(model, iterations = 15, seed = 1, verbose = FALSE)

plot_network_estimation()

Plot the distribution of a metric (default Pearson) across sampling iterations for each model type from a compare_network_estimation() result, returning a ggplot object.

Signature

args(plot_network_estimation)
#> function (results, metric_name = "Pearson", plot_type = "histogram", 
#>     show_stats = TRUE, bins = NULL) 
#> NULL

Example

plot_network_estimation(estimation, metric_name = "Pearson", plot_type = "histogram")

plot_sampling_distribution()

Plot the distribution of a single metric within a category (e.g. Pearson within “Correlations”) from the individual data frame of a run_sampling_analysis() result, returning a ggplot object.

Signature

args(plot_sampling_distribution)
#> function (individual_results, category, metric) 
#> NULL

Example

plot_sampling_distribution(
  sampling$individual,
  category = "Correlations",
  metric = "Pearson"
)

plot_tna_comparison()

Plot per-iteration comparison metrics (histogram, boxplot, ridgeline, bar, or density) from the individual data frame of a comparison result, returning a ggplot object.

Signature

args(plot_tna_comparison)
#> function (results, plot_type = "histogram", metric_name = "Pearson", 
#>     model_types = NULL, binwidth = NULL) 
#> NULL

Example

plot_tna_comparison(estimation$individual, plot_type = "boxplot", metric_name = "Pearson")