cograph (version 2.0.0)

build_mcml: Build MCML from Raw Transition Data

Description

Builds a Multi-Cluster Multi-Level (MCML) model from raw transition data (edge lists or sequences) by recoding node labels to cluster labels and counting actual transitions. Unlike cluster_summary which aggregates a pre-computed weight matrix, this function works from the original transition data to produce the TRUE Markov chain over cluster states.

Usage

build_mcml(
  x,
  clusters = NULL,
  method = c("sum", "mean", "median", "max", "min", "density", "geomean"),
  type = c("tna", "frequency", "cooccurrence", "semi_markov", "raw"),
  directed = TRUE,
  compute_within = TRUE
)

Value

A cluster_summary object with meta$source = "transitions", fully compatible with plot_mcml, as_tna, and splot.

Arguments

x

Input data. Accepts multiple formats:

data.frame with from/to columns

Edge list. Columns named from/source/src/v1/node1/i and to/target/tgt/v2/node2/j are auto-detected. Optional weight column (weight/w/value/strength).

data.frame without from/to columns

Sequence data. Each row is a sequence, columns are time steps. Consecutive pairs (t, t+1) become transitions.

tna object

If x$data is non-NULL, uses sequence path on the raw data. Otherwise falls back to cluster_summary.

cograph_network

If x$data is non-NULL, detects edge list vs sequence data. Otherwise falls back to cluster_summary.

cluster_summary

Returns as-is.

square numeric matrix

Falls back to cluster_summary.

non-square or character matrix

Treated as sequence data.

clusters

Cluster/group assignments. Accepts:

named list

Direct mapping. List names = cluster names, values = character vectors of node labels. Example: list(A = c("N1","N2"), B = c("N3","N4"))

data.frame

A data frame where the first column contains node names and the second column contains group/cluster names. Example: data.frame(node = c("N1","N2","N3"), group = c("A","A","B"))

membership vector

Character or numeric vector. Node names are extracted from the data. Example: c("A","A","B","B")

column name string

For edge list data.frames, the name of a column containing cluster labels. The mapping is built from unique (node, group) pairs in both from and to columns.

NULL

Auto-detect from cograph_network$nodes or $node_groups (same logic as cluster_summary).

method

Aggregation method for combining edge weights: "sum", "mean", "median", "max", "min", "density", "geomean". Default "sum".

type

Post-processing: "tna" (row-normalize), "cooccurrence" (symmetrize), "semi_markov", or "raw". Default "tna".

directed

Logical. Treat as directed network? Default TRUE.

compute_within

Logical. Compute within-cluster matrices? Default TRUE.

See Also

cluster_summary for matrix-based aggregation, as_tna to convert to tna objects, plot_mcml for visualization

Examples

# Edge list with clusters
edges <- data.frame(
  from = c("A", "A", "B", "C", "C", "D"),
  to   = c("B", "C", "A", "D", "D", "A"),
  weight = c(1, 2, 1, 3, 1, 2)
)
clusters <- list(G1 = c("A", "B"), G2 = c("C", "D"))
cs <- build_mcml(edges, clusters)
cs$macro$weights

# Sequence data with clusters
seqs <- data.frame(
  T1 = c("A", "C", "B"),
  T2 = c("B", "D", "A"),
  T3 = c("C", "C", "D"),
  T4 = c("D", "A", "C")
)
cs <- build_mcml(seqs, clusters, type = "raw")
cs$macro$weights