cograph (version 2.0.0)

as_tna: Convert cluster_summary to tna Objects

Description

Converts a cluster_summary object to proper tna objects that can be used with all functions from the tna package. Creates a macro (cluster-level) tna model and per-cluster tna models (internal transitions within each cluster), returned as a flat group_tna object.

Usage

as_tna(x)
# S3 method for cluster_summary
as_tna(x)
# S3 method for mcml
as_tna(x)
# S3 method for default
as_tna(x)

Value

A group_tna object (S3 class) -- a flat named list of tna objects. The first element is named "macro" and represents the cluster-level transitions. Subsequent elements are named by cluster name and represent internal transitions within each cluster.

macro

A tna object representing cluster-level transitions. Contains $weights (k x k transition matrix), $inits (initial distribution), and $labels (cluster names). Use this for analyzing how learners/entities move between high-level groups or phases.

<cluster_name>

Per-cluster tna objects, one per cluster. Each tna object represents internal transitions within that cluster. Contains $weights (n_i x n_i matrix), $inits (initial distribution), and $labels (node labels). Clusters with single nodes or zero-row nodes are excluded (tna requires positive row sums).

A group_tna object (flat list of tna objects: macro + per-cluster).

A group_tna object (flat list of tna objects: macro + per-cluster).

A tna object constructed from the input.

Arguments

x

A cluster_summary object created by cluster_summary. The cluster_summary should typically be created with type = "tna" to ensure row-normalized transition probabilities. If created with type = "raw", the raw counts will be passed to tna::tna() which will normalize them.

Details

This is the final step in the MCML workflow, enabling full integration with the tna package for centrality analysis, bootstrap validation, permutation tests, and visualization.

Requirements

The tna package must be installed. If not available, the function throws an error with installation instructions.

Workflow

# Full MCML workflow
net <- cograph(edges, nodes = nodes)
net$nodes$clusters <- group_assignments
cs <- cluster_summary(net, type = "tna")
tna_models <- as_tna(cs)

# Now use tna package functions plot(tna_models$macro) tna::centralities(tna_models$macro) tna::bootstrap(tna_models$macro, iter = 1000)

# Analyze per-cluster patterns plot(tna_models$ClusterA) tna::centralities(tna_models$ClusterA)

Excluded Clusters

A per-cluster tna cannot be created when:

• The cluster has only 1 node (no internal transitions possible)

• Some nodes in the cluster have no outgoing edges (row sums to 0)

These clusters are silently excluded. The macro (cluster-level) model still includes all clusters.

See Also

cluster_summary to create the input object, plot_mcml for visualization without conversion, tna::tna for the underlying tna constructor

Examples

# -----------------------------------------------------
# Basic usage
# -----------------------------------------------------
mat <- matrix(runif(36), 6, 6)
diag(mat) <- 0
rownames(mat) <- colnames(mat) <- LETTERS[1:6]

clusters <- list(
  G1 = c("A", "B"),
  G2 = c("C", "D"),
  G3 = c("E", "F")
)

cs <- cluster_summary(mat, clusters, type = "tna")
tna_models <- as_tna(cs)

# Print summary
tna_models

# -----------------------------------------------------
# Access components
# -----------------------------------------------------
# Macro (cluster-level) tna
tna_models$macro
tna_models$macro$weights  # 3x3 transition matrix
tna_models$macro$inits    # Initial distribution
tna_models$macro$labels   # c("G1", "G2", "G3")

# Per-cluster tnas
names(tna_models)          # "macro", "G1", "G2", "G3"
tna_models$G1              # tna for cluster G1
tna_models$G1$weights      # 2x2 matrix (A, B)

# -----------------------------------------------------
# Use with tna package (requires tna)
# -----------------------------------------------------
if (requireNamespace("tna", quietly = TRUE)) {
  # Plot
  plot(tna_models$macro)
  plot(tna_models$G1)

  # Centrality analysis
  tna::centralities(tna_models$macro)
  tna::centralities(tna_models$G1)
  tna::centralities(tna_models$G2)
}

if (FALSE) {
# Bootstrap requires a tna object built from raw sequence data (has $data)
# as_tna() returns weight-matrix-based tnas which don't satisfy that requirement
if (requireNamespace("tna", quietly = TRUE)) {
  boot <- tna::bootstrap(tna_models$macro, iter = 1000)
  summary(boot)
}
}

# -----------------------------------------------------
# Check which within-cluster models were created
# -----------------------------------------------------
cs <- cluster_summary(mat, clusters, type = "tna")
tna_models <- as_tna(cs)

# All cluster names
names(cs$cluster_members)

# Clusters with valid per-cluster models
setdiff(names(tna_models), "macro")

# Clusters excluded (single node or zero rows)
setdiff(names(cs$cluster_members), names(tna_models))