Type: Package
Title: Network-Based Clustering
Version: 1.2.0
Description: Network-based clustering using a Bayesian network mixture model with optional covariate adjustment.
Depends: R (≥ 3.5.0)
Encoding: UTF-8
License: GPL-3
RoxygenNote: 7.2.3
Suggests: knitr, rmarkdown, ggraph, ggpubr, ggplot2, grDevices, reshape2, car, ks, testthat (≥ 3.0.0)
VignetteBuilder: knitr
Imports: BiDAG (≥ 2.0.2), pcalg, RBGL, parallel, clue, methods, graph, igraph
Config/testthat/edition: 3
NeedsCompilation: no
Packaged: 2024-02-14 12:23:00 UTC; frbayer
Author: Fritz Bayer [aut, cre, cph], Jack Kuipers [ctb]
Maintainer: Fritz Bayer <frbayer@ethz.ch>
Repository: CRAN
Date/Publication: 2024-02-14 15:20:02 UTC

bestAICsearch

Description

best AIC search

Usage

bestAICsearch(
  binaryMatrix,
  minK = 2,
  maxK = 5,
  chiVec = c(0.001, 0.5, 1, 2, 3),
  startseed = 100,
  nIterations = 50,
  AICrange = 100,
  plot_heatmap = TRUE
)

Arguments

binaryMatrix

Data to be clustered

minK

Min number of clusters

maxK

Max number of clusters

chiVec

Vector of chi values

startseed

Seed

nIterations

Number of iterations

AICrange

AIC range

plot_heatmap

TRUE if plotting directly

Value

list of AIC scrores

density_plot

Description

Create 2d dimensionality reduction of sample fit to Bayesian network clusters

Usage

density_plot(cluster_results, var_selection = NULL, colourys = NULL)

Arguments

cluster_results

Cluster results from function get_clusters

var_selection

Selected variables to consider, e.g. c(1:5) for first five only

colourys

A vector specifying the colors of each cluster (optional)

Value

A density plot of class recordedplot.

Examples


# Simulate data
sampled_data <- sampleData(n_vars = 15, n_samples = c(200,200,200))$sampled_data
# Learn clusters
cluster_results <- get_clusters(sampled_data)
# Load additional pacakges to create a 2d dimensionality reduction
library(car)
library(ks)
library(ggplot2)
library(graphics)
library(stats)
# Plot a 2d dimensionality reduction
density_plot(cluster_results)

get_classification

Description

Classification based on clustering

Usage

get_classification(cluster_results, data_classify)

Arguments

cluster_results

Output from get_clusters()

data_classify

Data that should be classified; colnames need to match the ones of cluster_results$data; missing cols are allowed

Value

a list containing the classification as "clustermembership" and the probabilities of belonging to the clusters as "allrelativeprobabs"

Examples


# choose data
sampled_data <- sampleData(n_vars = 15, n_samples = c(300,300,300))$sampled_data
# learn clusters
cluster_results <- get_clusters(sampled_data)
# visualize the networks
classification_results <- get_classification(cluster_results, sampled_data)

get_clusters

Description

Network-based clustering

Usage

get_clusters(
  myData,
  k_clust = 3,
  n_bg = 0,
  quick = TRUE,
  EMseeds = 1,
  edgepmat = NULL,
  blacklist = NULL,
  bdepar = list(chi = 0.5, edgepf = 8),
  newallrelativeprobabs = NULL
)

Arguments

myData

Data to be clustered, must be either binary (with levels "0"/"1") or categorical (with levels "0"/"1"/"2"/...)

k_clust

Number of clusters

n_bg

Number of covariates to be adjusted for; the position of the covariates must be in the last column of the myData matrix

quick

if TRUE, then the runtime is quick but accuracy is lower

EMseeds

Seeds

edgepmat

Matrix of penalized edges in the search space

blacklist

Matrix of forbidden edges in the search space

bdepar

Hyperparameters for structure learning (BDE score)

newallrelativeprobabs

relative probability of cluster assignment of each sample

Value

a list containing the clusterMemberships and "assignprogress"

Examples


# choose data
sampled_data <- sampleData(n_vars = 15, n_samples = c(300,300,300))$sampled_data
# learn clusters
cluster_results <- get_clusters(sampled_data)
# visualize the networks
library(ggplot2)
library(ggraph)
library(igraph)
library(ggpubr)
plot_clusters(cluster_results)

get_clusters_bernoulli

Description

Categorical version of Bernoulli mixture model (binary clustering function BBMMclusterEM)

Usage

get_clusters_bernoulli(
  binaryMatrix,
  chi = 0.5,
  k_clust = 5,
  startseed = 100,
  nIterations = 10,
  verbose = FALSE
)

Arguments

binaryMatrix

Data to be clustered

chi

hyperparameter chi

k_clust

Number of clusters

startseed

Start seed

nIterations

number of iterations

verbose

set TRUE to display progress

Value

a list containing the clusterMemberships

nice_DAG_plot

Description

DAG visualization

Usage

nice_DAG_plot(
  my_DAG,
  print_direct = TRUE,
  node_size = NULL,
  CPDAG = TRUE,
  node_colours = "#fdae61",
  directed = TRUE
)

Arguments

my_DAG

DAG

print_direct

print DAG if TRUE

node_size

node size vector

CPDAG

if TRUE, then plot CPDAG instead of DAG

node_colours

node colours

directed

TRUE if nodes should be directed

Value

A plot of the DAG of class c("gg", "ggplot").

plot_clusters

Description

Plot clusters

Usage

plot_clusters(
  cluster_results,
  node_colours = "#fdae61",
  scale_entropy = FALSE,
  directed = TRUE
)

Arguments

cluster_results

Cluster results

node_colours

node colours

scale_entropy

if true, entropy measure will be used to determine size of the nodes

directed

TRUE if nodes should be directed

Value

A summary plot of all cluster networks of class c("gg", "ggplot", "ggarrange").

Examples


# Simulate data
sampled_data <- sampleData(n_vars = 15, n_bg = 0)$sampled_data
# learn clusters
cluster_results <- get_clusters(sampled_data)
# Load additional pacakges to visualize the networks
library(ggplot2)
library(ggraph)
library(igraph)
library(ggpubr)
# Visualize networks
plot_clusters(cluster_results)

sampleData

Description

Sample binary data from different Bayes nets

Usage

sampleData(
  k_clust = 3,
  n_vars = 20,
  n_bg = 0,
  n_samples = NULL,
  bgedges = "different",
  equal_cpt_bg = TRUE
)

Arguments

k_clust

Number of clusters

n_vars

Number of variables

n_bg

number of conditioned covariates

n_samples

number of samples

bgedges

type of background edges

equal_cpt_bg

specify if conditional probability table of the background edges is constant across clusters

Value

sampled binary data

Examples


# sample data
simulation_data <- sampleData(k_clust = 3, n_vars = 15, n_samples = c(200,200,200))
sampled_data <- simulation_data$sampled_data
head(sampled_data)